Exploring Compression Impact on Face Detection Using Haar-like Features

The main goal in our experimental study was to explore the impact of image compression on face detection using Haar-like features. In our setup we used the JPEG, JPEG2000 and JPEG XR compression standards to compress images from selected databases at given compression ratios. We performed the face detection using OpenCV on the reference images from the database as well as on the compressed images. After the detection process we compared the detected areas between the reference and the compressed image gaining the average coverage, false positive and false negative areas. Experimental results comparing JPEG, JPEG2000 and JPEG XR are showing that the average coverage of the detected face area differ between 79,58% in the worst and 99,61% in the best case. The false negative (not covered) areas range between 0,33% and 19,75% and false positive (fallout) areas between 0,38% and 9,45%. We conclude that the JPEG compression standard is performing worse than JPEG2000 and JPEG XR while both latter providing quite equal and good results.

[1]  Nalini K. Ratha,et al.  A Comparative Performance Analysis of JPEG 2000 vs. WSQ for Fingerprint Image Compression , 2003, AVBPA.

[2]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[3]  Shang-Hong Lai,et al.  Face detection directly from h.264 compressed video with convolutional neural network , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[4]  George W. Quinn,et al.  Performance of Face Recognition Algorithms on Compressed Images , 2011 .

[5]  Gregory K. Wallace,et al.  The JPEG still picture compression standard , 1992 .

[6]  Marwan Mattar,et al.  Labeled Faces in the Wild: A Database forStudying Face Recognition in Unconstrained Environments , 2008 .

[7]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[8]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[9]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[10]  Mislav Grgic,et al.  Face recognition in JPEG and JPEG2000 compressed domain , 2009, Image Vis. Comput..

[11]  Robert C. Kidd,et al.  Comparison of wavelet scalar quantization and JPEG for fingerprint image compression , 1995, J. Electronic Imaging.

[12]  W. Marsden.  I and J , 2012 .

[13]  Mark J. Burge,et al.  Assessment of H.264 video compression on automated face recognition performance in surveillance and mobile video scenarios , 2010, Defense + Commercial Sensing.

[14]  Rainer Lienhart,et al.  An extended set of Haar-like features for rapid object detection , 2002, Proceedings. International Conference on Image Processing.

[15]  Wei Tsang Ooi,et al.  Video quality for face detection, recognition, and tracking , 2011, TOMCCAP.

[16]  Josef Kittler,et al.  Influence of compression on 3D face recognition , 2009, Pattern Recognit. Lett..

[17]  Mo Chen,et al.  Modification of standard image compression methods for correlation-based pattern recognition , 2004 .

[18]  Klaus J. Kirchberg,et al.  Robust Face Detection Using the Hausdorff Distance , 2001, AVBPA.

[19]  Mislav Grgic,et al.  Image Compression in Face Recognition - a Literature Survey , 2008 .

[20]  Hyun-Sik Ahn,et al.  JPEG Quantization Table Design for Face Images and Its Application to Face Recognition , 2006, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[21]  Jan Nesvadba,et al.  Face detection in the compressed domain , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[22]  Huitao Luo,et al.  On face detection in the compressed domain , 2000, ACM Multimedia.

[23]  Donald M. Monro,et al.  An Evaluation of Image Sampling and Compression for Human Iris Recognition , 2007, IEEE Transactions on Information Forensics and Security.

[24]  Andreas Uhl,et al.  Evolutionary Optimisation of JPEG2000 Part 2 Wavelet Packet Structures for Polar Iris Image Compression , 2013, CIARP.

[25]  Andreas Uhl,et al.  Effects of JPEG XR Compression Settings on Iris Recognition Systems , 2011, CAIP.