Advancements in Face Detection: A Comparative Analysis of Classifiers and Feature Extraction Methods
Napa Komal Kumar, Angati Kalvan Kumar, Shaik Mohammed Yousuf, G. Bindusree, Chinnagopannagari Anand Reddy · 2024
Face detection is a fundamental task in computer vision with applications spanning from facial recognition to surveillance systems. This research aims to advance the state-of-the-art in face detection by conducting a comprehensive comparative analysis of various classifiers and feature extraction methods across three different frameworks: OpenCV, TensorFlow, and Pillow. The primary focus is on evaluating the accuracy of classifiers, including Support Vector Machine (SVM), Logistic Regression, Naive Bayes, Random Forest, and Decision Tree, when combined with feature extraction techniques such as Convolutional Neural Networks (CNN), Local Binary Patterns (LBP), and CASCADE, using different values of K as a parameter. The results reveal notable variations in classifier performance, with SVM consistently demonstrating high accuracy, particularly in combination with the CNN feature extraction method. Logistic regression also emerges as a strong performer across frameworks, while Naive Bayes, Random Forest, and Decision Tree show varying degrees of accuracy.