To return to the home page click here.
To go to Coaching questions page click here.
Introduction and Description
Humans have been taking care of their hair since the Palaeolithic age, and nowadays hairstyles have become a staple in many different cultures and come in a variety of styles. In the western world, trends are usually established when celebrities appear in public with a new haircut, this often leads to a large number of people wanting a similar haircut. People rush to their hairdressers in demand for the exact same haircut not worried about the fact that it might look differently on them than it did on that celebrity. This can be due to various reasons like the difference in hair thickness, head shape or even lack of specific high-quality products and care needed to produce and maintain the haircuts. There is no real way to visualize the haircut on oneself apart from photoshopping images or using apps that give a poor representation. This is where Clairvoyance comes in.
There are multiple scenarios in which Clairvoyance can excel. Here are two of them.
You walk into the hairdresser's with a haircut in mind, you explain it to your hairdresser and they seem to understand it. They start cutting and styling your hair only for you to realise at the end that this is not what you wanted. The haircut you received is not what you expected the haircut to look like on you, and that you've actually prefered another haircut. There is no way, however, to roll back to before you got the haircut and you are stuck with an unsatisfactory hair do. With this modern product, you will now be able to avoid all these unnecessary and annoying issues.
You're a hairdresser and a customer walks into your store with an idea in mind. They present you that idea to the best of their ability, and you start cutting, styling and/or colouring their hair. When you present them with the final result they seem unsatisfied. This can be due to numerous reasons, you could simply have made a mistake, but most likely the haircut or style they requested is not what they expected it to be.
Use Case Diagram
The Clairvoyance preview imaging technology would allow for an easy bridge between a customer's expectation and a hairdresser's understanding! This can help them make a final decision on a haircut as well as concretise the idea customers have in mind. The product would allow for hairstyle and hair colour to be displayed and be easily customizable. No more miscommunications or disappointed customers.
The final product will be an app. It will be able to create a 3D-model of a person’s head out of 4 pictures and adopt a 3D-haircut-model on it. It will recognize the age and sex of the person automatically and show proper haircut options. The user will be able to modify the hair length and colour manually. Furthermore he will have the opportunity to view different styling options for each cut. These options will include links to styling tutorials and an overview over the for the style needed products. After the choosing process, the customer will be able to share his haircut with friends on social media platforms, such as Facebook, Instagram, Twitter, Snapchat or Pinterest. If he wants, he can localize the closest hairdresser offering the requested haircut. He can take a look at pictures of previous results of this specific hairdresser and post a picture of his haircut after visiting him. In addition to that the customer can load his new haircut, used hair colours and hair regarding hair issues (such as thyroid or skin problems) in his personal profile on his phone. In that way his data will be protected on his own device and he is still able to show it to the next hairdresser.
An extended version of the app will be offered for hairdressers. It has all functions the private version has but allows the hairdresser to sign up a profile for his shop. The location of his shop will be saved there. In addition to that, he can upload sample pictures or videos of our predesigned haircuts on his customers. Users of the app will find his profile under each specific haircut and will be able to check him out before making an appointment. The hairdresser has also the option to build new haircuts and upload them with a tool we provide.
Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression.
State of the art AI technique for reconstructing facial meshes from a single picture. Does so by using a novel neural network technique called volumetric CNNs. For Clairvoyance this is a large piece of the puzzle since it would let us create realistic renderings of person's face with a different hairstyle. It is not the whole puzzle though; see the section drawbacks below. An online interactive demo of this technique is available at http://cvl-demos.cs.nott.ac.uk/vrn/
Head Reconstruction from Internet Photos.
Reconstructs a whole head from hundredths of images. Results of the paper do not appear good enough for production.
3D Face Hallucination from a Single Depth Frame.
Reconstructs a whole head from a single depth camera image. Impressive results.
3D Reconstruction Products
Creates a 3D model of a person's head from a singular or multiple images. However, final results are not very personalized but instead are constructed from an existing database of the heads of many different people. The results seem more like avatars than realistic 3D models.
Reconstructs any object in 3D by recording 360 degrees around an object with an iPad. Requires the Structure Sensor third-party peripheral.
See the existing work section first. We have found very little mention in literature or otherwise of automatically generating a 3D model of a person's whole head from a few images. Existing research seems not yet ready for production or requires a calibrated setup where the background is eliminated, lighting is constant and motion of the camera is controlled. There also exists work where relatively cheap depth cameras are used that provide impressive results, depth cameras are however not yet available on most mobile devices. However, there is promising work in reconstructing the face part of a head. It is possible to generalize the rest of a person's head. That is, "glue" the face part on top of an average head model. The drawback of this is that we lose important details (in the case of applying hairstyles) such as the shape of a person's ears.
Primary Stakeholders are stakeholders using the system on a daily basis. In our case, they are hairdressers and private users. Both parties want all functions of the app to work properly. They want the user interface to look appealing and simple to use. The hairdressers want to attract more customers. First by the usage of the app, secondly by the personal advertisement profile they get. Furthermore, it makes it easier for them to spot their customer’s wishes. Private customers want to try out new styles and calculate the risk of a new haircut. They want to play with different styles. For each new haircut, they want to explore different styling options. In addition to that, they want to share their experience with friends or give their hairdresser a feedback. Their needs and the range of their needs will be specified more closely in the results of the user journey.
Secondary stakeholders work with the system through an intermediary. They do not use it on a daily basis. In our case, secondary stakeholders would be people working on the app such as software engineers, our marketing team and the management. They all want adequate working conditions, a huge salary and satisfied customers.
The salary can be reached by optimising the costs and maximising the profit. Bonuses can be offered for hard-working collaborators.
The working conditions should orientate themselves on regulations of trade unions. Furthermore, the working atmosphere can be improved by taking stress from the employees. Daily childcare, team building workshops, a laundry service would be an option for a further developed company. In the beginning, the atmosphere could be enhanced by a Christmas party or active teambuilding.
Tertiary stakeholders are affected by the system or have an influence on the purchase. In our case, those stakeholders are society and the government. Society might or might not accept the app. Beauty blogger might have an influence on how the product sells itself. The government might restrict the development of the app through laws regarding privacy issues.
The Conjoint-Analysis (CONsidered JOINTly) is a process that tries to calculate the use value of each component of a product based on the product’s empirical total use value. It assumes that the partly use values of the function added yield in the product’s total use value.
To determine the customer value of the single functions of the product, we used a survey. It was send out to private customers and hairdressers. By letting them prioritise functions first on a superficial then on deeper levels, we could find out in detail which features are important for the customer. Based on the results of the study we build up our development strategie.
User Survey for private customers
45 students between 20 and 25 and from both sexes took part in our study.
For private users it was important to share their styles with friends. This is why we included a social media sharing function in the final app.
About 78 % of asked private users are seeing the app as something positive, but only 51% would spend money on it. For 51% of all asked users the price was the most important attribute of the app. That is why the app needs to be as cheap as possible for the users and we need to have a good selling concept. It might make sense to increase the number of downloads with a cheaper app and receive more money for advertisements instead.
A proper 3D model was for most respondents (60%) the technical priority number 1. In detail, was it not necessary that the model of the head is movable (Only 18% have chosen it as their priority.), but the haircut (Priority for 32% of the respondents.) and the head (Priority for 29% of the respondents.) should be modelled as realistic as possible. As a conclusion time should be spend on modelling the actual hair structure. To make the development easier and because only 20% of the respondents saw it as a priority, the customer should choose manually between thin, middle and thick hair. In a later development stage, the hair structure can also be recognized automatically. Because 56% of the respondents would take the risk of a new haircut more often than without the app, we should implement a number of “more risky” haircuts and -styles.
The variance was technical priority number 2 according to private respondents (32%). To reach a high visible variance without investing too much time, the internal variance* should be kept as small as possible, the external as high as possible. The internal variance is the variance causing more development and production effort, but is not obviously recognised by the customer. The external variance is the variance that is visible for the customer but not effect production or the development that much.
In our app we can do that by the opportunity to choose different colours for each haircut. We also should implement the same haircut predefined in different length or with different volumes. Single elements, like bangs, of each haircut should be used twice or only be modified a bit. The focus in the variance should be on creating different haircuts by using the synergy effects. Modifying the length manually was also very important for 40% of the customers, but it may technically be easier to realise that by more predefined cuts with different length. Changing the colour was not as important as the other two things (Priority for 9% of the respondents), but might be done very easily and should be implemented.
Another way to increase the external variance by giving more options and stimulate creativity is to add different hairstyles for each haircut. This can easily be done by a picture of the style and a link to a styling tutorial on YouTube.
The study also has shown that the appearance of the user interface is only for 11% of the asked people the most important technical attribute of the app. Therefore it should be kept simple, time should be spend first on the exact creation of haircut models.
User Survey For Hairdressers
A major requirement for hairdressers were fashionable haircuts.
The results of the survey for hairdressers were similar to the responses to the survey for private customers. Certainly we also asked how much hairdressers would spend on the app. All of them responded between 15 and 50 Euro. We included those values in our selling concept.
We estimated the market value of the product based on 3 influences. The first one was how much a customer would pay for the app by himself, the second which amount of money could be reached by advertisements in the app. Last but not least we also took a look at how much money could be earned by selling personal data.
Most cosmetic simulation apps use a picture as basis and project make-up or haircut on this picture. The haircut is not well adjusted or looks artificial. In addition to that, it is only possible to see the haircut in the front of the face. For changing the hair colour those apps try to extract the hair from the picture and give it another colour. This method only works when the background and skin colour are very different to the customer's original hair colour. I cannot be applied to predesigned haircuts. Sometimes apps ask for the hair structure, but it does not have any consequences for predesigned haircuts. Our approach builds a 3D model of the head and applies the haircut on it. It fits the head and is turnable. Furthermore, hair colours and length can be changed for each model exactly. The model considers the structure of the customer's hair.
After choosing a haircut our app also gives ideas to style the hair including tutorials and needed products. Cosmetic apps are mostly free when the customer buys the app without special functions. Special functions can be for example trend information or a taller number of haircuts. We chose to offer the hairdresser version of the app for 10 Euro and the private customer version for free. Comparable apps have about 100,000 and 50 Million downloads. If we assume 10,000 downloads in first 6 months worldwide, 10% of the hairdressers. Furthermore, we expect 100,000 downloads after 2 years. That would be 10,000 Euro in the first 6 months and 100,000 Euro after 2 years.
Instagram takes about 16 Euro for 1000 looks on a sponsored picture. Assuming 10,000 users in the first 6 months we could take for each advertisement 1600 Euro in the first half year and 16,000 after 2 years. Assuming a range of 20 different products (e.g. gel, hairspray, salt water spray, hairdryer) that would mean 32,000 Euro after 6 months and 320,000 Euro after 2 years.
The list of rights apps in the section has been long. Access to camera, media, location and WLAN has to be given to most styling apps. It is not said what this data is used for. Personal data could easily be sold via moving profiles, filming, audio data collection or analysing media on the advice. All of this is nothing we can accept responsibility for. The only thing we should evaluate is an anonymous statistics about most tried or shared hairstyles and sell it to fashion magazines or cosmetic companies. It would help them to identify new trends for the coming season and prepare a concept. For the development of our app, it could also lead to adjusting our haircut portfolio.
Laws and Ethics
Laws surrounding the issue
Universal Declaration of Human Rights
The idea of the mirror doesn’t violate any of the human rights since you voluntarily visit the hairdresser and can still decide to not have your hair cut after you dislike what you see. It is legal to put a price tag on the ‘’hair scanning’’ because it takes time and labour hours can legally be charged. The idea even really nicely complies with Article 27.
Everyone has the right freely to participate in the cultural life of the community, to enjoy the arts and to share in scientific advancement and its benefits.
As the concept of the mirror is very approachable for people from all classes, genders/cultures or religions, it is very easy to let everybody share in this scientific advancement and its benefits.
There are a couple of laws concerning the Privately-Identifiable Information and how that can be processed. From the 25th of May 2018 onwards, there will be a new law called ‘Algemeen verorderning gegevensbescherming’ (AVG). Before then the law ‘Wet bescherming persoonsgegevens’ (Wbp) must be followed. Before continuing with the law about personal information, we first need a clear understanding about what is personal information and what not. In general, ‘personal information’ means all the information about an identified or identifiable person natural person. This definition corelates with ‘personal data’ which means any information relating to an identified or identifiable individual (MvT, II, nr. 3, blz. 45). 
This means that the information must be about a person. Furthermore, the person must be identifiable or identified. If one if these to elements are not cleared, then we are not talking about personal information. Using this definition, the obvious things like, name, address and personal phone number are classified as personal information. However, when we ask for a username and password to make an account this doesn’t count as PII. Location is not per definition personal data. It becomes personal data when it is used to determine a patern of the personal life of the user. There is special personal information. The AVG sees personal information as the following:
- Personal data showing race or ethnic origin;
- Personal data showing political opinions;
- Personal data showing religious or philosophical beliefs;
- Personal data showing the membership of a trade union;
- Health data;
- Data relating to a person's sexual behavior or sexual orientation;
- Genetic data;
- Biometric data with a view to the unique identification of a person.
other type of personal information are:
- Genetic personal information
- Genetic personal data provide unique information about a person's physiology or health and / or the health of family members. That makes the information so sensitive.
- In practice this mainly concerns information about heredity and genetic characteristics that is the result of a biological sample. For example, information from analysis of the DNA.
- Biometric personal information
- Biometric personal data provide unique information about a person's physical, physiological or behavior-related characteristics. That makes it so sensitive.
- In practice, this mainly concerns biometric personal data that are the result of a specific technical processing that makes the data traceable to an individual. As with fingerprint data.
For criminal personal information there are other regulations namely:
- he processing must be under the supervision of the government.
- processing is permitted under national law. These are EU law provisions or Member State law provisions, which offer appropriate guarantees for the rights and freedoms of the persons concerned. 
The Wbp law
The law Wbp is based on the European guideline for privacy protection that was made in 1995 24 October. The law had been in force since 2001 1 September. The law states that the following can happen with the personal information:
- Personal information can only be used in things that do not break the law.
- Personal information can only be used for activities that have been determined clearly before the obtaining the information.
- The owner of the information must know the organisation or person that is using the personal information.
- The personal information must be protected, for special personal information there are more strict laws.
Every organisation that uses personal information must report this to ‘Autoriteit Persoonsgegevens’. There is a time to bridge before the AVG goes into effect. In this time organisation can prepare themselves so that they have to abide by the new law. The law has been implemented in 2016 4 mei but it takes effect on may 25 2018 so there is a 2-year gap for organisations to prepare. The AVG does bring changes with it. One of the main changes is that it will be a law that all EU countries have to abide by.
This means that for example, Facebook is an organisation that collects PII, name address etc, in different countries. At the moment they are allowed to do different things with PII in different countries while in others it will not be allowed. When the AVG is in effect this will change so that all countries have the same rules and protocols. The reason is that all the laws in the countries concerning PII is because they are based on the EU guideline but are interpreted differently. Furthermore, the effect of this law is that people have more influence what happens to their information. In the AVG it is stated the owner of the information has to give permission to the organisation so that the can use the information for what they want to process it. The Organisation has to be able to prove that the owner of the information has given his or her permission. Furthermore, it has to be as easy to retract given permission as it is to give permission. Additionally, there are some new rights that people will have concerning their PII.
Right to forgetfulness: This law states that people have to right to tell an organisation that they have to remove all the information that they have on them. When somebody has told an organisation that they have to remove their information, also other organisations that have gotten the information from the organisation in question have to remove the information.
Right to data portability: This law states that people have the right (tied to some conditions) to receive all the information that an organisation has in a standard format. This is so that people can quickly change from one provider to the other by themselves. They could even ask the old provider to send their information to the new provider if this is technically possible. 
How this affects us
For us, this means that we will have to do document everything what we have about the personal information of people. After 25 may we would not need to report to AP. We are obligated to conform to DPIA and to have an FG. DPIA stands for Data protection impact assessment. It is only obligated when the information has a high privacy risk for the owner of the information. In the following situation DPIA has to be carried out when an organisation:
- Systematically and thoroughly evaluate personal aspect, such as profiling
- On a large scale process personal data
- On a large scale follow people in public places.
Outside these 3 situations, the AVG doesn’t have an example what a high risk is. 
An FG is a ‘Functionaris voor de gegevensbescherming’. That is somebody who is responsible that the rules of AVG are followed. There are 3 situations when an FG has to be implemented by the organisation:
- Government and public organisation are obligated to have an FG.
- If an organisation follow individual on a large scale as an example, when profiling people who could be a safety hazard.
- When an organisation gathers personal data that’s classified as special personal data. Special personal data is, for example, political preferences, religious beliefs and criminal past.
EU-countries can determine in what other situations the organisation has to have an FG.  The AVG has six foundations when you can use and process personal information namely:
- Permission from the person concerned.
- The data processing is necessary for the execution of an agreement.
- The data processing is necessary for compliance with a legal obligation.
- Data processing is necessary to protect the vital interests.
- The processing of data is necessary for the fulfilment of a task of general interest or exercise of public authority.
- The data processing is necessary for the representation of the legitimate interests.
We will have to determine by our self if we satisfy one of the 6 foundations. For children under the age 16, we will need permission from the parents. Furthermore, when concerning children we will have to show an effort to try and confirm that the parents did give permission to us to use the information of the child. When the children do not live in the Netherlands it is possible that the age limit is 13 instead of 16 because the country is allowed to decide for themselves how to want to translate the law. However in the Netherlands changes are that it will be 16. 
Conclusion: For the final version when we would use 2 apps, 1 for the customer and 1 for the barber we would ask the following of the customer:
- Email address
The reason we will need all the information as stated above is that we want to make a profile for the user. Furthermore, we want to be able to categorize what product is used by who so that we can improve what we show our users. This can then be done by filtering the where which hairstyle is used and those hairstyles can be then be offered earlier to the user when they are looking for a haircut. The email is then used so that we can send our user information about their haircut and barbers who frequently cut those styles. The Username and password are necessary solely to be able to create a personal account.
Privacy is a fundamental human right recognized in the UN Declaration of Human Rights, the International Covenant on Civil and Political Rights and in many other international and regional treaties.
In the Netherlands, a business must follow the Dutch Data Protection Act (Wet bescherming persoonsgegevens, Wbp). This act outlines and emphasizes the amount of care needed when handling a customer's personal data. Without such acts, the data would be vulnerable to criminal activities. Transparency about the usage of the data is crucial, users should be informed of where and how their data is being used. In some cases, the data must be reported to the Dutch Data Protection Authority, DPA (Autoriteit Persoonsgegevens). Also, the customer should be made aware of your details such as your address and company names. In addition, users should be informed when you intend to share their data with other companies. 
A model that can be used when dealing with privacy factors in multimedia information sharing context is the Adams' privacy model. This model helps multimedia communication systems to "determine which information users regard as private, from whom, and in which context". Instead of dealing with privacy as a black/white (or binary yes/no) variable, the model attempts to define "privacy boundaries". If these privacy boundaries are violated, this will reduce the effectiveness of the system. Furthermore, these boundaries are defined by the privacy "perception" of the users.
According to Adams' model, the user is anyone who has their data transmitted. This can happen either directly or indirectly. Direct information may, for instance, be a person's consumption habits or medical records. Indirect information might be their image or voice. The user may not actually be actively using the system and may be totally unaware that their data is being transmitted to outsiders.
As shown in the figure below, Adams' model defines three main factors which interact with one another to create the users' overall perception of their privacy.  These factors are defined as:
- Information Sensitivity: is the primary privacy factor which the other factors affect to determine the perceived sensitivity level. Information Sensitivity in a way defines the users' perceptions of the confidentiality of the information being transmitted. Also, users' judgment of the sensitivity levels of the information is not binary (private/not private), but multi-dimensional. This means it has varying degrees of sensitivity.
- Information Receiver: is the users' perception of the person who receives and/or manipulates their information. Although a range of factors would influence the users' assessment of the Information Receiver, the issue of trust seems to be the most important one in defining the users' perception of the Information Receiver.
- Information Usage: is the users' perception of how and for what purpose their information will be used at present as well as in the future. The potential importance that the users attribute to the perceived Information Usage is crucial to the users' estimation of privacy risk/benefit trade-offs.
No single factor of the Adams´ model-Information Sensitivity, Information Receiver, or Information Usage-is a sufficient base for a privacy mechanism in an online personal photo collection. No subject or type of image is always/never perceived as sensitive, no receiver is trusted with all/none of the photos, and no type of usage is always/never allowed.
Posting pictures of clients
Using pictures that you've taken exclusively for the business' Facebook page is the safest option. Since you own the photos, you don't have to get permission from anyone else before using them, unless the images contain customers or employees. In those cases, simply ask the people in the photo to give you written permission to use the image. This can be in the form of an informal email or a consent form that you prepare and ask them to sign. This protects you from anyone coming back later to say that they're upset or angry that you've included them on Facebook without their permission.
Facebook prevents businesses and personal users from uploading images of an extremely graphic nature, especially if those images contain nudity. While Facebook does not prevent you from doing so, you might also want to watch out for posting pictures of children. Anyone under the age of 18 cannot legally consent to being included in your Facebook page, so veer away from posting their photos unless you get permission from their parents or legal guardians.
Social Media Concept
We decided to focus our marketing on social media. The reasons are obvious: Advertisement there is effective and cheap. Furthermore, it approaches exactly our target audience. People tending to use “new media” are also more likely to download an app. Especially apps such as Snapchat, Instagram or Pinterest focussing on pictures and the looks are very likely to be used by our audience.
To create our marketing as effective as possible, we created a concept for our brand including some basic social media rules:
It is important to make target audience specific advertisement. Not every platform addresses its audience in the same way. Facebook users are for example 50-60 years in average, whereas users of Instagram, Snapchat, Pinterest and Twitter are mainly between 15 and 35 years old.
The more follower of the brand has, the more likely it is to be seen by a lot of people. In order to get a follower, it is important to first build a solid base. This can be done by adding all friends and friends of friends.
After that, it is important to find so-called “multiplier”. Those are people attracting many others and can be used to advertise our brand. Influencers or bloggers are examples of multipliers. We can make offers to beauty bloggers to link their channel in the styling tutorials in our app in exchange for being named in their videos or being connected to their accounts. We can comment and like what they do, in exchange for them liking and commenting our product. In social media, it is all about interaction. The technique here would be linking influencer with a high reachability in our tutorials and comment and like at channels of the more unknown ones, who are still thankful for every follower.
The user should feel emotionally connected to the brand. It is important to face users on a personal level and make the brand more human. That can be reached by providing insights in the personal life of the people behind the app. For example, the social media account of the brand can be given to one person of the team and let him or her post every day. First about what they do for developing the product, but secondly about their daily life. Hairdresser and influencer should also get the opportunity to take over the account for a month.
In addition to that, it is eligible to put some user stories online. Users are given a voice. They feel part of a community, in which they are welcome and appreciated. The same community influencer they adore is part of. Those stories can be for instance their experiences with the app or previous hair styling faux pas. Users also can be asked about their opinion of new predefined haircuts or styles.
To deepen the connection between users and brand influencer can be used even more intense. They already have the connection to users. A haircut called after the influencer or an influencer’s face as example model are ways to connect the brand to the user unconsciously to his reputation. Furthermore, links of well-known beauty bloggers can be listed in our styling tips. In exchange for this advertisement, influencer might use our app for their videos or pictures.
- The profile picture in every app should be the logo of the brand.
- The title picture on Facebook should be a pic of a group of people using the app together. Positions should be open and the user should feel as a part of the group. In this way, he feels connected and welcome.
- The highest reachability on pictures will be reached if pictures touch their audience emotionally.
Nostalgic pictures arouse nice and warm feelings. People will feel connected to their childhood and to the brand the same moment. It will generate trust. We can post a picture of a girl getting her hair done by her mother. Historic hairstyles (from the 20th, 40th, 70th, 90th) would also work. To increase the effect we can use pictures of idols people had in their childhood. At this point, it is necessary to keep attention to the user’s age in each social media.
Being funny is also a way to attract people’s attention. It causes sympathy and good feelings, which immediately connect with the brand. It is also a good way to get connect the brand and the user. Laughing about the same things causes bondings. In our concrete situation, we could let users post pictures of their failed haircuts in the past. We could also take pictures of animals instead of people and project the haircut model on them.
Hashtags are a way to tag or find posts on social media. The widest scope is reachable with eleven hashtags. We need a scientific and personal hashtag for our product, in our case we choose #clairvoyance. In addition to that is is always good to stick with trendy hashtags. A weekly overview you can find at this link: http://hashtagify.me/popular
Requirements, Preferences and Constraints
- The application allows the user to take pictures and form a picture set.
- A picture set consists of 4 pictures, capturing the front, back, left and right side of the user's head.
- The application has to be able to create a 3D model of the user's head out of a picture set.
- The application is able to extract the specific side of the user's head from each picture in the picture set.
- The application has to be able to apply a 3D model of a haircut on the head of the 3D model of the person’s head.
- The user should be able to manually choose and change the applied hairstyle.
- The application must be able to show the results of applying a 3D model of a hairstyle on the head of the 3D model of the person’s head (3D view).
- The user is able to pan the 3D view by swiping left and right; thereby allowing the user to see the whole of his generated head and applied hairstyle.
- The product should offer a well-received user experience (as determined by user tests).
- The product should offer a tutorial in which the user is told how to use the product.
- The application will initially contain at least 3 hairstyles per gender (male and female).
- The application will allow changing the colour of the hairstyles.
- The application will be able to download and use new hairstyles from a central server hosting our hairstyle files.
- The hairdresser can pre-select which hairstyles he/she is able to cut/style.
- The hairdresser can pre-select which hairstyles can actually be cut/styled for the current client.
- The application will provide a realistic lighting solution for the 3D view.
- The user is able to select different lighting.
- The user is able to select light colour.
- The user is able to select light position.
- The user is able to select light intensity.
- The application must run in iOS 10 devices.
- The application must run suitably (as determined by user tests) on a fifth-generation iPad or later iPads.
- The application must run on Android 8 devices.
- The application must run suitably (as determined by user tests) on a Samsung Galaxy Tab S3.
- The application must run suitably (as determined by user tests) on an Asus ZenPad 3S 10.
The prototype will have:
- User interface to take 4 pictures of the user.
- A 3D view showing a 3D mesh of a head.
- At least 2 different hairstyles. The exact number will depend on the time required to create (or download and use) a single hairstyle (TBD).
- User interface to select different hairstyles.
- The 3D view shows the selected hairstyle on top of the user's head.
- The 3D view is rotatable so that user can see his whole head with the selected hairstyle.
The prototype will not have:
- The ability to convert from picture to 3D mesh. Instead, we will pre-generate a 3D mesh.
- The ability to dynamically add the hair to the 3D mesh. Instead, we will pre-generate this.
- A realistic lighting solution. Instead, we will use a simpler lightning solution.
The app is created in Android Studio using the programming language Kotlin and Java. Functionality such as taking pictures, showing a 3D view and selecting hair styles and hair colors are successfully implemented. The user interface has been designed in accordance with Android's standards for user interface design (Material Design). Furthermore, the 3D view is purposefully designed to be similar to SnapChat's interface for editing photos. Designing a user interface to be similar to existing and familiar user interfaces helps the user quickly understand our app without being explicitly told what to do.
A short video demonstrating the current features of the app is available here
The .apk file containing the app can be found here. It can be installed on any Android device running Android 7.0 or higher.
The code and project files for the protoype can be found here
Fashionable haircuts and -styles are extremely important for the hairdressers, which took part in the survey. This is why all our haircuts are predicated on haircut trends of 2018 according to different fashion magazines and fashion bloggers    . Furthermore we implemented current styling trends of well known beauty bloggers in our styling options. Each of the options are introduced to the customer by a picture of the style, a small description and the link to the tutorial for the style.
Short hair gives a younger appearance. Who does not want to cut off all hair, is in good hands with a blunt bob. It looks more feminine than a Pixie and the version without bangs also suits rounder faces. Kendall Jenner,Kristen Bell, Selena Gomez also chosed to wear their hair in a bob.
Sexy, effortless waves are always trendy. They flatter the face and make the whole style more playful and wild. Be a powerful woman and make your day a little more exciting!
In spring blooms love: With this charming and lovable bun you will feel like a princess stepping out of your favourite Disney movie.
Recently discovered your romantic side? Then this look is just made for you! It flatters especially round faces, makes them appear elf alike.
Rock it baby! With this look you will rule every retro party like a queen. This look is also nice to give your outfit the little extra power it needs to make you shine.
The 90s are back and they want curls, curls, curls! Playful, happy, free. This is how you will feel with this extraordinary hairstyle.
Blunt Bob with bangs
According to Marie Claire, the Blunt Bob will be one of the most popular haircuts in 2018. The bangs hide forehead crinkles and short hair gives a younger appearance. The bob version with bangs suits especially oval faces with a too long forehead. Bella Hadid, Vanessa Hudgens (High School Musical) and Kerry Washington are only a few examples of celebrities choosing it as their hairstyle of 2018.
French, vintage and wild. With this look you enchant everyone!
A look Mickey Mouse would be jealous of!
One bun is not enough? Spice up your hipster bun with a second one!
Pixie with bangs
Short hair can give a more masculin and strong look. It is very suitable for "too nice and innocent" looking women with a feminine face. It give a refreshing and cheeky appearance. Furthermore it symbolizes assertiveness, which is useful for more shy women.
With this look you will be the boho beauty on the next festival. 
A pund of rock, a teaspoon punk and... Done. This look makes you look more powerful than any witch potion could.
Short hair lets you look like a guy? No. This super easy style makes you more girly than ever! 
Long hair with bangs
Long hair suit especially round faces. It lets the face look slimmer and more oval. The bangs are excellent to hide first aging symptoms.
Effortless waves and bangs? You can have it! Simple, classy, chick and working with every possible outfit you find in your closet!
Even too hip for hipsters? Then this is your style. Combine it with a casual look or with a cute dress. It will always look fabulous!
Sportive day, but no time to do a real workout? This look lets you look athletic wherever you are! The right look for studying in the library, a college party or a day off with your girls.
Lively and playful boho style for sunny afternoons in nature or on a festival.
A little bit Brigitte Bardot, a little bit Katherine Deneuve. This innocent, but elegant look brings the effortless french feeling back.
During the final weeks, the final version of the prototype was made in order to demonstrate it during the presentation. For this two of the haircuts were implemented on a single face model. Furthermore, on one of the models, a link can be clicked which leads to a tutorial showing how to perform this haircut.
In this section, we will focus on the what we were not able to do during this project, as well as areas where increased research and experimentation is needed.
Since what we have as our final product for this course is a prototype, we don't have a fully functioning product. This prototype doesn't provide some important technical features such as the following.
High-quality resolution of the hair:
The current resolution of the hair is simply what Maya has to offer and while this is useful for a prototype, customers will request more accurate and realistic hair in order to improve the immersion of the application.
Although trends and culture can cause hairstyles to be similar within communities, there are many hair types that need to be taken into account. From straight hair to afros, hair varies in curliness, in fact, many people choose to go from one hair type to another. The current application does not take this into account due to the number of hairstyles made in the limited amount of time. This is an important feature because people sometimes enjoy straightening or curling their hair for a change and therefore seeing the possible drastic result is crucial.
Hair length is another factor that should not be ignored, although people can't instantly grow their hair at the hairdresser, people let their hair grow different amounts based on preference and sometimes people decide to go for drastic changes.
The thickness and the amount of hair on are variables affected by genes, age, and even stress. Many hairstyles require a certain degree of these variables in order to hold or even just to look similar. This is obviously an essential part of the final product.
Another issue is that some hairstyles may have to be fitted differently onto a head depending on its shape. The prototype doesn't allow the base of the hair to alter to fit the head shape of a person, because of this, hairstyles might look odd on people with heads different from the default head model.
Accurate hair movement and physics when rotating the face:
Since hair is made up of hundreds of thousands of thin hair strands, its individual as well general position can be changed by just a small breeze. Because we live actively and constantly move our heads and bodies around, our hair is subjected to this movement and moves depending on its length and the force issued onto it. Not every single strand of hair can be simulated in real-time on a mobile device. However, physics models that look accurate to the human eye but are computationally less expensive do exist, albeit with some research challenges remaining. A comprehensive review of the techniques used and the challenges remaining can be found here .
Hair reflectivity from various light sources:
Although this is a minor adjustment, it might be interesting to add different settings in which the hair is illuminated by different light sources and light types. In its current state, the lighting is suboptimal and not very realistic.
Accurate real-time customizability such as:
- Hair length customization
- Hair type (thickness or curls)
- Hair colour
Hair customizability is a crucial feature in this application because its the primary component that facilitates the interaction between the hairdresser and their customer. Furthermore, it allows for more creative freedom as well as quick visualization of the expected final product. Although our prototype already fulfils some of these features, it does so in a limited fashion and thus doesn't represent the full potential of these features.
The solutions for these all involve having better technology that allows for these features. Nvidia has developed a program, Hairworks, to create realistic virtual hair as seen in video games, and it grants very good results. However, this sort of programs requires a lot of computation power which can not be reproduced on a mobile. Hairworks runs on DirectX12 which requires high-end GPUs. It would be a very bad selling point if the user had to spend thousands of euros to be able to visualize and edit the hair.
Furthermore, some developments could be made to the app itself in regards to:
Data transfer from one app to the other:
It might be interesting to a customer or hairdresser to be able to share haircuts they would like to have or have been customizing or working on.
This would either be possible by sharing it on social media and messaging apps or through the app itself if both parties have the app. Not only would that boost the popularity of the app without advertising, it would also make people more likely to download the app and try it out themselves.
Server storage of data for personal use application:
The prototype does not have a way to store personal information but this would be part of the final product.
In this way, users will have a history of their haircuts that can be shared with any hairdresser and possibly any of their friends. This, however, requires backend services as well as a thorough understanding of privacy which has been expanded on in this wiki.
UI improvements to make the app look better:
The current interface is simple and effective, but by no means is it optimal in terms of aesthetic and design.
This can be achieved by hiring a good frontend designer or by relying on user feedback to improve it.
Ratings in terms of difficulty for the desired hairstyle to be realised:
If the haircut you desire is quite complex to get right it might be more effective to go to a higher end hairdresser. By adding a rating both the customer and the hairdresser are aware of the risk they are going to take. This is a good selling point for more experienced hairdressers and could boost the competitiveness of the hairdressing sector.
Additionally, it would be interesting to create a social network for the users which allows them to
- Share haircuts they have created using the app
- Rate and comment on other haircuts
- Rate and comment on hairdressers
- Save haircuts to a favourites tab to see how it would look on them
Using a social network, we can create a community for the application which would popularise its use and enhance the content of the app itself through community submissions.
Hair model production
The hairstyles that were created in the prototype were done in Maya and took multiple hours to complete, this can scale very quickly when we take into account the thousands of different haircuts that exist, with even more small variations. In addition, hairstyle trends change over time and the app would need to stay updated to stay relevant. There are different solutions for this.
- The first solution is to contract a company to create these haircuts for us. The advantage is that we are guaranteed high-quality haircuts, however, hiring these designers would cost a considerable amount of money, which is something we will not have at the start especially.
- Another solution has already been mentioned and it goes with the social network idea. If the platform becomes big enough hairdressers, aspiring hairdressers and artist will see the app as a place where they can create and display haircuts which can then be used by other people (with permission). This solution goes hand in hand with developing easy-to-use software for producing high-quality hair models. While existing software exists for generating high-quality hair (for example what we used - Maya), these programs require days to learn and months to master. To the best of our knowledge no software currently exists that gives the every day user the ability to do so.
- The final solution is to simply create these ourselves and release them over time.
Based on feedback from a hair dresser
We met with our primary user the hairdresser and pitched our prototype. There was a lot of enthusiasm, however, there were also things we still had to take into consideration when finalizing the product. The crux of the tips he gave us was how it would be in practice. Because while the theory is fantastic, in practice there would be problems with the following: Hair type, hair whorl and time.
Going further into hair type, people are born with a specific type of hair. There are 4 types of hair, namely
In these 4 categories there are also sub-categories so the list above will look more like this:
Where the intensity increases from A to C.  of course if hair type was this simple we would already be able to implement it into our prototype. However, it is the case that customers with parents from a different ethnicity can have different hair types on their head. This makes it more complicated because it can be that different locations on the head have a different hair type or that the hair type changes as the hair are growing. This raises the complexity of implementing realistic hair onto the model that we create of the head. We could have the hairdresser to manually implement the hairstyle onto the model of the head and from there on the customer could choose a possible style. However, this raises a second issue, namely the number of, location and orientation of the hair whorl.
The hair whorl determines how the hair grows and how it will stand naturally. Therefore when trying to have a style that actually goes into the natural stands of the hair, maintaining the hairstyle will be difficult. Of course, a hairdresser can create the style on the head, however, if the customer cannot maintain it the next day or recreate the style by his or herself, they will have wasted their money on a style that they cannot recreate in their own time. This would result into more visits to the hairdresser to fix the style again and the customer would have to come back every other day because he or she wants a specific style that’s not always possible depending on the natural hair whorl. This all would cost time for the customer.
Even if we would be able to address the points made above. An important factor is time. In simple terms, the more costumes a hairdresser can cut in a day, the more money it makes that day. If our model would be able to have the hair type and hair whorl manually editable to the point where it is a one on one view, the time it would take would be wasted when compared to how fast a human being with a trained eye can actually see the possibilities. For a hairdresser, it could take more time to draw the same conclusion with the app then when he would have done it without the app. Of course, customers can have a 3D model of their head and show the style, but a barber is able to create such a model from a simple picture and determine if it would be possible for the customer to maintain the hair, especially when the customer has been coming to the hairdresser for a while. Furthermore, on the final day of editing the wiki one of the members wasn't able to access their computer and thus some elements (the hairstyles in Maya) are missing from the wiki.
This all means that allot would have to be implemented before the product would actually do what we intended it to do in a way that would be feasible for the barber. However the prototype that we have developed is a good template to integrate the implementations to achieve this goal.
- ↑  Jackson, A., S., et al., (2017). Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression
- ↑  Liang, S., Shapiro, L. G., & Kemelmacher-Shlizerman, I. (2016). Head Reconstruction from Internet Photos. Computer Vision – ECCV 2016 Lecture Notes in Computer Science, 360-374. doi:10.1007/978-3-319-46475-6_23
- ↑  (n.d.). Retrieved from http://grail.cs.washington.edu/projects/liangshu/3DHeadPage.html
- ↑  FaceGen - 3D Human Faces. (n.d.). Retrieved from https://facegen.com/
- ↑  Turn your mobile device into a powerful 3D scanner. (n.d.). Retrieved from https://itseez3d.com/]
- ↑  3D scanning, augmented reality, and more for mobile devices. (n.d.). Retrieved from https://structure.io/
- ↑  What Are Primary, Secondary & Tertiary Stakeholders? (n.d.). Retrieved from https://bizfluent.com/info-8353421-primary-secondary-tertiary-stakeholders.html
- ↑  Alsos, O. A., & Svanæs, D. (2011). Designing for the Secondary User Experience. Human-Computer Interaction – INTERACT 2011 Lecture Notes in Computer Science, 84-91. doi:10.1007/978-3-642-23768-3_7
- ↑  What It Costs: Ad Prices From TV's Biggest Buys to the Smallest Screens. (2015, April 06). Retrieved from http://adage.com/article/news/costs-ad-prices-tv-mobile-billboards/297928/
- ↑ [http://www.ohchr.org/EN/UDHR/Documents/UDHR_Translations/eng.pdf
- ↑  Artikel 1 sub a Wbp. (n.d.). Retrieved from https://autoriteitpersoonsgegevens.nl/nl/over-privacy/wetten/wbp-naslag/hoofdstuk-1-algemene-bepalingen-art-1-tm-5/artikel-1-sub-wbp
- ↑  Are 'usernames' Privately-Identifiable Information (PII)? (2014, October 31). Retrieved from https://www.clickinsight.ca/blog/usernames-privately-identifiable-information
- ↑  Guidance Note for Data Controllers on Location Data . (n.d.). Retrieved from https://www.dataprotection.ie/docs/Guidance-Note-for-Data-Controllers-on-Location-Data/1587.html
- ↑  Mag u persoonsgegevens verwerken? (n.d.). Retrieved from https://autoriteitpersoonsgegevens.nl/nl/onderwerpen/avg-nieuwe-europese-privacywetgeving/mag-u-persoonsgegevens-verwerken#wanneer-mag-u-strafrechtelijke-persoonsgegevens-verwerken-6342
- ↑  Mag u persoonsgegevens verwerken? (n.d.). Retrieved from https://autoriteitpersoonsgegevens.nl/nl/onderwerpen/avg-nieuwe-europese-privacywetgeving/mag-u-persoonsgegevens-verwerken#hoe-weet-u-of-u-persoonsgegevens-mag-verwerken-6310
- ↑  Algemene informatie AVG. (n.d.). Retrieved from https://autoriteitpersoonsgegevens.nl/nl/onderwerpen/avg-nieuwe-europese-privacywetgeving/algemene-informatie-avg
- ↑  Data protection impact assessment (DPIA). (n.d.). Retrieved from https://autoriteitpersoonsgegevens.nl/nl/onderwerpen/avg-nieuwe-europese-privacywetgeving/data-protection-impact-assessment-dpia
- ↑  Functionaris voor de gegevensbescherming (FG). (n.d.). Retrieved from https://autoriteitpersoonsgegevens.nl/nl/onderwerpen/avg-nieuwe-europese-privacywetgeving/functionaris-voor-de-gegevensbescherming-fg
- ↑  Mag u persoonsgegevens verwerken? (n.d.). Retrieved from https://autoriteitpersoonsgegevens.nl/nl/onderwerpen/avg-nieuwe-europese-privacywetgeving/mag-u-persoonsgegevens-verwerken#hoe-weet-u-of-u-persoonsgegevens-mag-verwerken-6310
- ↑  Zaken, M. V. (2017, September 11). Privacy. Retrieved from https://www.government.nl/privacy
- ↑  Cunningham, S. J., Masoodian, M., & Adams, A. (2010). Privacy issues for online personal photograph collections. Journal of theoretical and applied electronic commerce research, 5(2), 26-40.
- ↑  Social Media Fact Sheet. (2018, February 05). Retrieved from http://www.pewinternet.org/fact-sheet/social-media/
- ↑  Andrews, M., Leeuwen, M. L., & Baaren, R. V. (2014). Hidden persuasion: 33 psychological influence techniques in advertising. BIS.
- ↑  Williams, J. (2016). Social media: Marketing strategies for rapid growth using: Facebook, Twitter, Instagram, LinkedIn, Pinterest and YouTube. S.n.
- ↑  Lewis, R. M. (2017) Social Media Marketing: Wie man Soziale Medien Benutzt, um Ihre Marke zu Bauen und den Verkehr zu Ihrem Geschäft zu Fahren
- ↑ http://www.instyle.com/hair/best-new-haircuts-2018
- ↑ https://www.marieclaire.com/beauty/a19640772/demi-lovato-short-bob-haircut/
- ↑ https://www.cosmopolitan.com/uk/beauty-hair/beauty-trends/g12451844/spring-summer-2018-hair-makeup-trends/
- ↑ http://www.vogue.co.uk/gallery/hair-trends-2018
- ↑ https://therighthairstyles.com/category/haircuts/hairstyles-with-bangs/
- ↑ https://www.youtube.com/watch?v=qMX5lH4QJMs
- ↑ https://www.youtube.com/watch?v=xXY4VkO4zcY
- ↑ https://www.youtube.com/watch?v=4UFq4F2_H9E
- ↑ https://www.youtube.com/watch?v=-NZRV-V3JsQ
- ↑ https://www.youtube.com/watch?v=-NZRV-V3JsQ
- ↑ http://www.glamourmagazine.co.uk/gallery/celebrities-with-bobs-bob-cut-hairstyles
- ↑ https://www.youtube.com/watch?v=t42mgQ1pf00
- ↑ https://www.youtube.com/watch?v=_-W4xbfX-uY
- ↑ https://www.youtube.com/watch?v=_-W4xbfX-uY
- ↑ https://www.youtube.com/watch?v=6EsvGGtGb4k
- ↑ https://www.youtube.com/watch?v=mtEfx-PJ2UI
- ↑ https://www.youtube.com/watch?v=6EsvGGtGb4k
- ↑ https://www.youtube.com/watch?v=BuTR_g36n8A
- ↑ https://www.youtube.com/watch?v=BuTR_g36n8A
- ↑ https://www.youtube.com/watch?v=zwv7L4yW81Y
- ↑ https://www.youtube.com/watch?v=zwv7L4yW81Y
- ↑ https://www.youtube.com/watch?v=zwv7L4yW81Y
- ↑ http://ieeexplore.ieee.org/abstract/document/4069232/
- ↑ https://www.curls.biz/curly-hair-type-guide.html