Speaker
Merve Özer
Description
Face detection is a crucial task in computer vision, with applications ranging from security systems to human-computer interaction. In this study, we evaluate the performance of three face detection algorithms: Haar Cascade, Histogram of Oriented Gradients (HOG), and Multi-task Cascaded Convolutional Networks (MTCNN). The experiments are conducted using the Labeled Faces in the Wild (LFW) dataset to ensure a robust evaluation. Our results reveal that MTCNN outperforms the other methods, achieving a detection accuracy of 90%, while HOG demonstrates the lowest performance among the tested algorithms. These findings highlight the effectiveness of deep learning-based approaches like MTCNN for accurate face detection in challenging datasets.
| Paper Language | English |
|---|---|
| Contribution Type | In-Person |
Primary author
Co-author
Erdal Alimovski
(IZU)
