The International Arab Journal of Information Technology (IAJIT)

..............................
..............................
..............................


A Fusion Approach Based on HOG and Adaboost Algorithm for Face Detection under Low-

Detecting human faces in low-resolution images is more difficult than high quality images because people appear smaller and facial features are not as clear as high resolution face images. Furthermore, the regions of interest are often impoverished or blurred due to the large distance between the camera and the objects which can decrease detection rate and increase false alarms. As a result, the performance of face detection (detection rate and the number of false positives) in low- resolution images can affect directly subsequent applications such as face recognition or face tracking. In this paper, a novel method, based on cascade Adaboost and Histogram of Oriented Gradients (HOG), is proposed to improve face detection performance in low resolution images, while most of researches have been done and tested on high quality images. The focus of this work is to improve the performance of face detection by increasing the detection rate and at the same time decreasing the number of false alarms. The concept behind the proposed combination is based on the a-priori rejection of false positives for a more accurate detection. In other words in order to increase human face detection performance, the first stage (cascade Adaboost) removes the majority of the false alarms while keeping the detection rate high, however many false alarms still exist in the final output. To remove existing false alarms, a stage (HOG+SVM) is added to the first stage to act as a verification module for more accurate detection. The method has been extensively tested on the Carnegie Melon University (CMU) database and the low-resolution images database. The results show better performance compared with existing techniques.


[1] Cortes C. and Vapnik V., “Support-Vector NETWOrks,” Machine Learning, vol. 20, no. 3, pp. 273-297, 1995.

[2] Dalal N. and Trigg B., “Histograms of Oriented Gradients for Human Detection,” in Proceeding of the Computer Vision and Pattern Recognition, pp. 886-893, 2005.

[3] Elleuch M., Hani A., and Kherallah M., “Arabic Handwritten Script Recognition System Based on HOG and Gabor Features,” The International Arab Journal of Information Technology, vol. 14, no. 4A, pp. 639-646, 2017.

[4] Hayashi S. and Hasegawa O., “Robust Face Detection for Low-resolution Images,” Journal of Image Electronics Engineers of Japan, vol. 34, no. 6, pp. 726, 2005.

[5] Hsu C., Chang H., and Chang T., “An Improved Face Detection Method in Low-Resolution Vide,” in Proceeding of the 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 419-422, 2007.

[6] Kumar A., Kaur A., and Kumar M., “Face Detection Techniques: a Review,” Artificial Intelligence Review, vol. 52, no. 2, PP. 927-948, 2019.

[7] Li H., Lin Z., Shen X., Brandt J., and Hua G., “A Convolutional Neural Network Cascade for Face Detection,” in Proceeding of the IEEE Confrence on Computer Vision and Pattern Recognition, Boston, pp. 5325-5334, 2015.

[8] Liao S., Jain A., and Li S., “A Fast and Accurate Unconstrained Face Detector,” IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 38, no. 2, pp. 211-223, 2016.

[9] Liu Z., Luo P., Wang X., and Tang X., “Deep Learning Face Attributes in the Wild,” The IEEE International Conference on Computer Vision, pp. 3730-3738, 2015.

[10] Luaibi M. and Mohammed F., “Facial Recognition Based on DWT-HOG-PCA Features with MLP Classifier,” Journal of Southwest Jiaotong University, vol. 54, no. 6, 2019.

[11] Luo D., Wen G., Li D., Hu Y., and Huan E., “Deep-Learning-based Face Detection Using Iterative Bounding-box Regression,” Multimedia A Fusion Approach Based on HOG and Adaboost Algorithm for Face Detection under ... 735 Tools and Applications, vol. 77, no. 19, pp. 24663-24680, 2018.

[12] Marciniak T., Chmielewska A., Weychan R., Parzych M., and Dabrowsky A., “Influence of Low Resolution of Images on Reliability of Face Detection and Recognition,” Multimedia Tools and Applications, vol. 74, no. 12, pp. 4329-4349, 2013.

[13] Sinha A., “Efficient Face Detection Using Neural Networks,” Advances in Computer Intelligence, pp. 279-285, 2017.

[14] Soundararajan R. and Biswas S., “Machine Vision Quality Assessments for Robust Face Detection,” Signal Processing :Image Communication, vol. 72, pp. 92-104, 2019.

[15] Sun X., Wu P., and Hoi S., “Face Detection Using Deep Learning: An Improved Faster RCNN Approach,” Neurocomputing, vol. 299, pp. 42-50, 2018.

[16] Torralba A. and Sinha P., “Detecting Faces in Impoverished Images,” Massachusetts Inst of Tech Cambridge Artificial Intelligence Lab, Technical Report, 2001.

[17] Viola P. and Jones M., “Rapid Object Detection Using a Boosted Cascade of Simple Features,” in Proceeding of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Kauai, 2001.

[18] Zhang T., Li J., Jia W., Sun J., and Yang H. “Fast and Robust Occluded Face Detection in ATM Surveillance,” Pattern Recognition Letters, vol. 107, pp. 33-40, 2018.

[19] Zhang C. and Zhang Z., “A Survey of Recent Advances in Face Detection,” Microsoft Research, Technical Report, no. MSR-TR2010- 66, 2010.

[20] Zheng J., Ramírez G., and Fuentes O., “Face Detection in Low-Resolution Color Images,” in Proceeding of the International Conference Image Analysis and Recognition, Póvoa de Varzin, pp. 454-463, 2010. Farhad Navabifar was born in Esfahan, Iran in 1970. He received the B.S. and M.S. degrees in electrical engineering from Azad University, in 2000 and the Ph.D. degree in telecommunication engineering from University Technology Malaysia (UTM) in 2013. From 2013 to now he was Assistant professor in Mobarakeh Azad University. He is the author of one book, more than 15 articles. His research interests include signal processing, image processing and pattern recognition. Currently he is the head of electrical and computer group in Azad University of Mobarakeh. Mehran Emadi received the B.S. degree in Electrical Engineering (Electronics) in 1995, the M.S. degree in Electrical Engineering (Electronics) in 1999 from Azad University, NajafAbad branch, Iran, and the Ph.D. degree in Electrical Engineering (Image processing) from University Technology Malaysia (UTM), Malaysia in 2013. His researches include semiconductors in his M.S. degree and image processing, computer vision, biometric applications in his Ph.D. degree period. There have been more than 70 technical papers, published by him and he is an assistant professor in Azad University in Iran. He has been working as the program chair, and a committee member for some international conferences, and has been training several students in Universities by webinar.