Improving Face Recognition Accuracy through Optimization of Haar and LBP Features in MATLAB

Abstract

As we hasten into the digital age, facial recognition technology has emerged as a pivotal innovation across various domains such as security authentication, surveillance, and identity verification. This research delves into and enhances the Convolutional Neural Network (CNN) framework within the MATLAB environment, substantially augmenting the efficacy of facial recognition algorithms. The manuscript begins by tracing the evolution and current achievements within the facial recognition field, followed by an exploration into the theoretical foundation and key technologies of facial recognition. The aim of this study is to develop an advanced facial recognition algorithm based on CNN, employing efficient image preprocessing techniques such as grayscale conversion, noise reduction, and feature extraction, thereby significantly improving recognition accuracy and processing speed. Experiments conducted within MATLAB showcase the dual advancements in efficiency and speed offered by the optimized algorithm compared to traditional methods. Moreover, the paper discusses the adaptability of this algorithm in complex scenarios and the challenges and strategies likely to be encountered during pragmatic application. The outcomes of this research not only validate the practicality of the proposed algorithm but also illuminate directions and methodologies for the future exploration of facial recognition technology.