Individual recognition from low quality and occluded images and videos using GAN

Thus, we designed an algorithm which is specific to the enhancement of faces for better recognition performance. Thus, we present a versatile GAN capable of recovering facial features from degraded videos and images. The proposed method enhances the degraded faces by restoring their lost facial features rather than its perceptual quality, which ultimately leads to better performance of any existing face recognition algorithm.

The limitation using a single image is that there is an upper bound to which we can enhance the images. This motivated us to develop the idea of synthesising the frontal face pose from multiple occluded images of the same identity, taken at different times and from different angles. This helps to further push the upper bound.

Our network crowdsources useful information from all images and rejects information that is not useful for recognition. We build our generator on top of TPGAN and use the concept of a U-net discriminator which evaluates the output both at a global and local level, thus boosting the image to be consistent at a global and local level.