Heterogeneous Face Recognition Framework Using Multiple Filters for Person Identification

Face recognition is the task of identifying an already detected face as known or unknown face and has attracted much attention due to its potential value in security, biometrics and law enforcement applications. One of the most difficult challenges in automated face recognition is computing facial similarities between face images which are acquired in alternate modalities. To address this problem Heterogeneous Face recognition comes takes place. Heterogeneous face recognition (HFR) involves matching two face images from alternate imaging modalities, such as sketch to a photograph or an infrared image to a photograph. The Proposed work is based on experimentation using Heterogeneous Face Recognition framework using Prototype Random Subspace Approach for both probe and gallery images which are represented in terms of nonlinear similarities to a collection of prototype face images. The proposed work will be evaluated on various performance parameters with accuracy as the main focus and pre-processing time required for filtering the images using DOG, GF, and CSDN filters. This framework performs equally well for different modalities whereas the focus of the study is specifically for Face Photo-Sketch Recognition Accuracy and Recognition time required using DOG, GF, and CSDN filters. The accuracy of this nonlinear prototype representation is improved by projecting the features with the help of PCA The outcome of this work will be useful in the areas like forensic sciences, video surveillance etc. The paper also shows a comparative study of Heterogeneous Face Recognition framework for both probe and gallery images which are represented in terms of nonlinear similarities to a collection of prototype face images and an approach to Heterogeneous face recognition which needs feature descriptors that are effective within each domain.