Human Face Detection Improvement using Subclass Learning and Low Variance Directions

Abstract

In order to increase the face detection rate in complicated images, a novel approach is presented in this work. The suggested method seeks to improve accuracy by utilizing low-variance directions for data projection and one-class subclass learning. Previous studies have demonstrated that taking into account the data carried by low-variance directions enhances the performance of models in one-class classification. For dispersion data, subclass learning is extremely successful. To evaluate the effectiveness of our subclass method, we conducted a comparison between our proposed approach and other one-class classifiers on multiple face detection datasets. Results reveal that the suggested method performs better than other methods, demonstrating its potential to develop face identification technologies.