Year of Graduation
Facial clustering of photos from a social network for mobile platforms
The present work is aimed to explore different clustering algorithms and convolutional neural networks that extract face features for finding the best combination. The dataset for experimental runs of algorithms was created using Instagram social network. Instagram was chosen due to there are a lot of photos of different people that allows creating a satisfactory dataset for face clustering. An analytic review of the literature on the methods of face clustering was conducted and algorithms which can show good clustering quality was chosen. As the result the Android mobile application was created which clusters faces and makes a directory per cluster, using the best combination of feature extractor and clustering algorithm after the exploration step.