GWTM and Crow Search Algorithm for Face Recognition in Low-Resolution Images

Abstract

Nowadays, face recognition has gained more consideration in the area of image processing and computer vision. The existing face recognition systems provide better performance using the frontal images with high resolution. The major issue in face recognition is the Low-Resolution face images. To alleviate this issue, this paper proposes the face recognition system by integrating the Gabor filter + wavelet + texture (GWTM) operator and the Crow search algorithm to increase the classification performance, while deploying the LR images. Initially, the input image is given to the preprocessing, and the low-resolution image is generated. Then, this low-resolution image is applied to the kernel regression model to produce the image with high-resolution. Then, both the low-resolution and the high-resolution images are applied to the GWTM operator for extracting the features. The result of the GWTM is provided to the Crow search algorithm for producing the intermediate images. Finally, the intermediate images are given to the spherical SVM classifier for optimal recognition. The performance of the proposed method is analyzed with the existing methods using three evaluation metrics, such as accuracy, FAR, and FRR. From the experimental results, it can be show that the proposed method attains the higher accuracy of 0.9500, minimum FAR and FRR of 0.0500.