SVM-Based Approach For Human Face Detection And Recognition

Support Vector Machines (SVM) have emerged as a powerful machine learning technique for human face detection and recognition due to their robustness in high-dimensional spaces and ability to handle complex classification tasks [12]. This paper explores the application of SVM in face detection and recognition, emphasizing its role in distinguishing facial features by constructing an optimal hyperplane in a transformed feature space. The study reviews various kernel functions, particularly the Radial Basis Function (RBF) and polynomial kernels, for enhancing classification accuracy [5],[12]. Experimental results demonstrate the effectiveness of SVM in achieving high detection and recognition rates while maintaining computational efficiency [9] ,[14]. The findings suggest that SVM, when integrated with feature extraction techniques such as Principal Component Analysis (PCA) [1],[13] or Histogram of Oriented Gradients (HOG) [2],[19], can significantly improve performance in real-world face recognition systems.