Hallucination space relationship learning to improve very low resolution face recognition

Abstract

It is known that face recognition rate is affected by the resolution of probe image. Therefore it is natural to expect improving the resolution via face hallucination would increase the recognition rate. However, it was concluded in the previous works that improvement in the visual quality does not necessarily lead to a better recognition rate, and performance of face hallucination for recognition is especially poor when very low resolution (VLR) images are used. Experiment results in this paper will show that there is a correlation between visual quality and recognition rate. And hallucination space relationship learning algorithm is proposed which is robust on hallucinating VLR images to improve the performance in terms of both visual quality and recognition rate.