Enhancing Face Recognition Accuracy On Low-Resolution Databases Using Interpolation Techniques And Feature Extraction Techniques

Abstract

The images in high resolution contain more useful information than the images in low resolution. Thus, high-resolution digital images are preferred over low-resolution images. Image super-resolution is one of the principal techniques for generating high-resolution images. This research investigates the impact of image resolution on the performance of face recognition systems and proposes methods to enhance recognition accuracy on low-resolution face databases. In the first phase, several holistic face recognition algorithms, including Support Vector Machine (SVM), Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), and RESNET50, are evaluated for their performance on low-resolution face images. Subsequently, three interpolation techniques-nearest neighbor, bilinear, and bicubic interpolant-are applied as preprocessing steps to increase the resolution of the input images. The study aims to determine the effectiveness of these techniques in improving recognition accuracy. Various evaluation metrics, including accuracy, precision, sensitivity, specificity, Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), and Structural Similarity Index (SSIM), are employed to assess the performance of the recognition systems. The results demonstrate the efficacy of the proposed approach in enhancing recognition accuracy on low-resolution face datasets, thereby contributing to the advancement of face recognition technology in practical applications.