Video Face Recognition
- Face Tracking
- Mean Sequence Sparse Representation-based Classification
- Movie Trailer Face Data Set
- Video Face Recognition Toolbox
- Related Publication
SHORE face detection. We generate tracks using two metrics one spatial and the other appearance. The spatial metric computes the percent overlap of the current bounding box with the previous. The appearance metric computes a histogram intersection of the local bounding box, which can handle abrupt changes in the scene and the face. We compare each new face detection to existing tracks; if the location and appearance metric is similar, the face is added to the track, otherwise a new track is created. Finally, we use a global histogram for the entire frame, encoding scene information, to detect scene boundaries and impose a lifespan of 20 frames of no detection to detect the end of tracks.
Sparse Representation-based Classification (SRC) has received much attention due to its high precision and ability to handle occlusions. More recently, we found that combined with several features SRC works well for real-world face recognition and excels at rejecting unknown identities (see Face Recognition for Web-Scale Datasets). Now, given a face track with frames, we make the strong assumption that they will result in a single coefficient vector based on the fact that all of the frames belong to the same person and should intuitively be linearly represented by the same people in the dictionary. Based on this assumption we produce the following formulation:
in which we minimize the sum residual error between every frame and the linear combination and maximizing the sparsity of . By analyzing the least-squares formulation of the residual error, we find the interesting result that it reduces to the mean face track vector as follows:
where . This formulation results in at least a 5x speedup depending on the average length of the input face tracks over a naive frame-by-frame application of SRC.
- trailerExperiments: Entry script for the execution of methods.
- trailerResults: Consolidates all results and outputs PR curves.
Movie Trailer Face DatasetFeatures [3.93 GB] Labels [2 MB] Trailer Downloader [5.5 KB]
PubFig+10Public Figures (PubFig) Original Dataset Images [852.6 MB] Features [1.06 GB]
Matlab Video Face Recognition ToolboxVFR Toolbox [2.3MB]
Face Recognition in Movie Trailers via Mean Sequence Sparse Representation-based Classification, Computer Vision and Pattern Recognition 2013, Portland, Oregon, June 23-28, 2013.