Choosing a new hairstyle can be a difficult, impactful decision. Especially envisioning if a haircut would suit the individual is hard. With the analysis responses from facial recognition APIs and supervised machine learning, a relation between facial features and hairstyle is ought to be found in this project, so that a hairstyle recommender system, called “hAIr”, can be created. The system recommends hairstyles that suit the individual’s characteristics. This is based on a neural network learning algorithm, which is trained with features, extracted from 1,060 images of people, relating to 53 different hairstyles. The trained network reaches an accuracy of 28.10% when validated with images that were not used for training. This can be improved by trying different combinations of input variables, or using a different conversion for the values that were gained from the APIs. It is also possible that the APIs are not completely accurate. A third possibility for improvement would be to use a different learning algorithm, such as k-Nearest Neighbors or naive Bayes.
hAIr: Intelligent Hairstyle Recommender System
Featured Areas of Expertise
- Technology and Realization (TR)
- Math, Data and Computing (MDC)