Deep Face Quality Assessment
This work addresses the need for better image filtering in facial recognition systems, but it appears incremental as it builds on existing deep learning methods without introducing major innovations.
The paper tackles the problem of face image quality assessment to improve facial recognition accuracy by training a deep convolutional neural network to predict quality scores between 0 and 1, using a two-stage approach involving label generation from similarity comparisons with high-quality templates.
Face image quality is an important factor in facial recognition systems as its verification and recognition accuracy is highly dependent on the quality of image presented. Rejecting low quality images can significantly increase the accuracy of any facial recognition system. In this project, a simple approach is presented to train a deep convolutional neural network to perform end-to-end face image quality assessment. The work is done in 2 stages : First, generation of quality score label and secondly, training a deep convolutional neural network in a supervised manner to predict quality score between 0 and 1. The generation of quality labels is done by comparing the face image with a template of best quality images and then evaluating the normalized score based on the similarity.