Improved Viola-Jones Face Detection Method Based on Cross-Examples for Thermal Images

Hong Tran, Dr. Chunhua Dong, and Dr. Xiangyan Zeng, Department of Mathematics and Computer Science, Fort Valley State University, 1005 State University Dr, Fort Valley, GA 31030

Face recognition is a popular area of research in the applications of artificial intelligence. Accurate detection of region of interest (ROI) is a key step in a face recognition system. Thermal images are widely used in many applications where normal visibility is reduced, impaired or ineffective, such as night surveillance and fugitive searches.  Face detection in thermal images is based on the fact that the temperature of faces is different from the background, body, clothes, and other objects

Viola Jones is an object detection framework widely used for face detection. However, the performance of the Viola-Jones algorithm may suffer from missed faces and wrongly detected non-face objects. To eliminate the non-face objects and improve the face detection performance for thermal images, we propose to incorporate the cross- examples into our framework. Our database is constructed to contain positive samples which are entirely thermal images of face objects, and negative samples (non-face objects) in which we utilizes “natural / visible cross-examples” as part of the negative samples. It means negative samples is a set of thermal and natural images. Performing cross-examples is more effectively by increasing the discriminability between the positive samples and negative samples. Experimental results show that the proposed scheme can effectively eliminate the non-face objects and thus achieves a higher accuracy of face detection than the classical Viola-Jones method. 

Additional Abstract Information

Presenter: Hong Tran

Institution: Fort Valley State University

Type: Poster

Subject: Computer Science

Status: Approved

Time and Location

Session: Poster 5
Date/Time: Tue 12:30pm-1:30pm
Session Number: 4049