Fuzzy Hamming Distance and Perfect Face Ratios Based Face Sketch Recognition

摘要

This paper presents a novel method for matching of face sketch images with face photo images. The basic idea is to extract perfect face ratios for face and sketch as features and calculate the distance between them by using fuzzy hamming distance. To extract perfect face ratios, we use the point landmarks in the face then sixteen features will be extract. An experimental evaluation demonstrates the satisfactory performance of our approach on CUHK dataset. It can be applied with any existing sketches set. It is observed that the proposed algorithm will be a competitor of the other proposed relative approaches. The recognition rate reaches 100% especially in the CUHK dataset.