A new Adaptive Approach for Histogram based Mouth Segmentation

Authors: Axel Panning, Robert Niese, Ayoub Al-Hamadi, Bernd Michaelis

Abstract:

The segmentation of mouth and lips is a fundamental problem in facial image analyisis. In this paper we propose a method for lip segmentation based on rg-color histogram. Statistical analysis shows, using the rg-color-space is optimal for this purpose of a pure color based segmentation. Initially a rough adaptive threshold selects a histogram region, that assures that all pixels in that region are skin pixels. Based on that pixels we build a gaussian model which represents the skin pixels distribution and is utilized to obtain a refined, optimal threshold. We are not incorporating shape or edge information. In experiments we show the performance of our lip pixel segmentation method compared to the ground truth of our dataset and a conventional watershed algorithm.

Keywords: Feature extraction, Segmentation, Image processing, Application

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1074679

References:

[1] A. Al-Hamadi, A. Panning, R. Niese, and B. Michaelis. A modelbased image analysis method for extraction and tracking of facial features in video sequence. In The 4th International Multi-conference on Computer Science and Information Technology CSIT 2006, Spo. by IEEE, Amman,Vol.3, pages 499-509, 2006.
[2] S. Arca, P. Campadelli, and R. Lanzarotti. A face recognition system based on local feature analysis. In Audio- and Video-Based Biometric Person Authentication, pages 182-189, 2003.
[3] C. Bouvier, P.Y. Coulon, and X. Maldague. Unsupervised lips segmentation based on roi optimisation and parametric model. In IEEE International Conference on Image Processing, pages IV: 301-304, 2007.
[4] Jingying Chen, Bernard Tiddeman, and Gang Zhao. Advances in Visual Computing, volume 5359/2008 of Lecture Notes in Computer Science, chapter Real-Time Lip Contour Extraction and Tracking Using an Improved Active Contour Model, pages 236-245. Springer Berlin / Heidelberg, 2008.
[5] P. Cisar and Zelezny M. Using of lip-reading for speech recognition in noisy environments. In Speech Processing, pages 137-142, Prague, 2004. Academy of Sciences of the Czech Republic.
[6] N. Eveno, A. Caplier, and P.Y. Coulon. Accurate and quasi-automatic lip tracking. Circuits and Systems for Video Technology, 14(5):706-715, May 2004.
[7] Erhan AliRiza Ince and Syed Amjad Ali. An adept segmentation algorithm and its application to the extraction of local regions containing fiducial points. In ISCIS, pages 553-562, 2006.
[8] K.S. Jang, S. Han, I. Lee, and Y.W. Woo. Lip localization based on active shape model and gaussian mixture model. In Pacific-Rim Symposium on Image and Video Technology, pages 1049-1058, Hsinchu , TAIWAN, 2006.
[9] J.Y. Kim, S.Y. Na, and R. Cole. Lip detection using confidence-based adaptive thresholding. In International Symposium on Visual Computing, pages I: 731-740, 2006.
[10] S.H. Leung, S.L. Wang, and W.H. Lau. Lip image segmentation using fuzzy clustering incorporating an elliptic shape function. IEEE Transaction on Image Processing, 13(1):51-62, January 2004.
[11] Trent W. Lewis and David M.W. Powers. Lip feature extraction using red exclusion. In Peter Eades and Jesse Jin, editors, Selected papers from Pan-Sydney Area Workshop on Visual Information Processing (VIP2000), volume 2 of CRPIT, pages 61-67, Sydney, Australia, 2001. ACS.
[12] D. Nguyen, D. Halupka, P. Aarabi, and A. Sheikholeslami. Real-time face detection and lip feature extraction using field-programmable gate arrays. IEEE Trans. Systems, Man and Cybernetics, SMC-B, 36(4):902- 912, August 2006.
[13] California Institute of Technology. Faces 1999 (front). http://www.vision.caltech.edu/archive.html, 1999.
[14] A. Panning, A. Al-Hamadi, R. Niese, and B. Michaelis. Facial expression recognition based on haar-like feature detection. Pattern Recognition and Image Analysis, 18(3):447-452, 2008.
[15] Paul Viola and Michael Jones. Robust real-time object detection. Second international workshop on statistical and computational theories of vision modeling, learning, computing, and sampling, 2001.