Video Face Recognition via Learned Representation on Feature-Rich key Frames

Abstract

 Nowadays, facial verification based authentication has become an important area of research in law enforcement and surveillance applications to combat widespread occurrences of security threat incidents,. It is satisfactory that the existing methodologies  have  marked  great verification results at equal error rate, but have poor  results  at lower fault acceptable rates Therefore further research is required  to increase verification performance while lowering the fault acceptance  rate.

This paper, introduces a new face matching algorithm, that constitutes  1) Discrete Wavelet Transform  and Entropy calculations for getting feature-rich key frames of a video  .Then,

2)A Deep Learning Architecture, that consists of a Stacked Denoising Sparse Autoencoder (SDAE) and deep Boltzmann machine (DBM); is helpful for feature extraction..finally After completion of all these steps 3) a multilayer Feed Forward Neural Network System has been used as a classifier to get proper verification result.

 The output is analyzed on two different openly accessible databases, YouTube Video Faces and  Android Mobile Phone Database a type of point and shoot challenge(PaSC).

Results shows that the algorithm is successful: 1) in achieving sharpen increase in performance compared to histogram based frames, arbitrary frames, or frame collection  with no reference   image eminence measures  2) joint feature learning in SDAE and sparse and low rank regularization in DBM contributes to improve the face verification rate. The suggested method yields the success rate of  matching faces about 95% s at equal error rate  for the You Tube Video Faces database, and it  is possible to achieve  even  better results for PaSC database on the other hand.