SFTA Feature Descriptor for Matching Optical and Sketch Photo Image
This paper presents a novel approach to address the representation issue and the matching issue in face recognition (verification). Face recognition has gained a widespread attention due to its potential application values as well as theoretical challenges compared with other biometrics. The major difficulty lies in face recognition is modality gap may occur, texture, and shape in the sketch face image and corresponding optical face images because they are different dimension, resolution, memory size, etc. In order to recognize face sketch through face photo database is a challenging task for many reaches because face photo image in training set and face sketch image in testing set have different modality, texture and shape is main difficulty for recognition. It may also deals with many crimes occur when none of such information is present, but instead an eye witness of the crime is available in such situation a forensic artist is found used to work with the witness or the victim in order to draw a sketch that depicts the facial appearance of the culprit according to the verbal description such as sketch drawn depending on the description given by an eye witness is called forensic sketch.