Improving Facial Recognition Accuracy Using Local Binary Patterns

The proposed method involves pre-processing of the dataset, which includes normalization and resizing of the images to a standard size. Local binary pattern is then used to extract features from the pre-processed images. These features are used to train a machine learning model, specifically a support vector machine, to recognize faces in the images. The effectiveness of the proposed approach was evaluated using a publicly available dataset, and the results indicate a high level of accuracy in face detection, with a recognition rate of over 90%. The approach was also tested on images with varying contrast and rotation angles, and the results demonstrate its ability to accurately identify faces under such conditions. The proposed method has practical applications in various areas such as surveillance, access control, and forensics. It has the potential to be integrated into security systems for real-time face recognition and identification, improving the accuracy and efficiency of such systems. Furthermore, the method can be extended to include more complex features for more accurate and robust face detection. Overall, this research contributes to the growing body of knowledge on face detection techniques and their practical applications.