Face Recognition Based on SRCS Algorithm and Score of Exponential Weighting

Face recognition is a prominent research area within computer vision, offering significant value across various fields of life, including certificate verification, security systems, and human-computer interactions. Nonetheless, enhancing the reliability and precision of face recognition systems is persistently challenging due to variables like facial expressions, various scenes, and occlusion. This paper introduces an enhanced SRCS (Sum of Representation Coefficients as Score) algorithm, which builds upon the two-stage sparse representation approach. The underlying principle is that a higher representation value of each class of training images vis-à-vis test images suggests a stronger correlation between the test image and the respective class. Consequently, the algorithm computes the sum of representation coefficients for the training images to ascertain the distances between the classes and the test images. Following this, it identifies classes with high scores as prospective representatives of the test samples. Moreover, the setting of reasonable weights in the weighted fusion of addition weighting, based on the TSFR (The Two-Step Face Recognition) method, presents challenges, and varying training samples require different optimal weights. Therefore, this paper proposes an exponential weighting method score that obviates the need for setting any weights while effectively enhancing recognition accuracy. This proposed method undergoes rigorous validation through comprehensive experiments conducted on renowned databases such as FERET, PRL, YALE, and GT, with the results consistently affirming the effectiveness of the method.