Feature-based Sketch-Photo Matching for Face Recognition

Matching of sketch and photo is very important in police verification and intelligence as it is used to track the criminals or some person. Therefore, it should be accurate so that mismatching of the sketch with photo can be avoided. For this, feature based matching method is introduced through this paper. Feature based matching includes a feature vector which contains features of the face image (either it is a sketch or a photo) in terms of histogram of oriented gradients (HoG) features and gray level co-occurrence matrix (GLCM) features. Computing the features, first, increases the chances of correct matches. It can be depicted from the results as well that, comparing with other state-of-art approaches, proposed method is more accurate in matching the sketches with photos of the same person. (C) 2020 The Authors. Published by Elsevier B.V.