The International Arab Journal of Information Technology (IAJIT)


An Improved Statistical Model of Appearance under Partial Occlusion

The Appearance Models (AMs) are widely used in many applications related to face recognition, expression analysis and computer vision. Despite its popularity, the AMs are not much more accurate due to partial occlusion. Therefore, the authors have developed Robust Normalization Inverse Compositional Image Alignment (RNICIA) algorithm to solve partial occlusion problem. However, the RNICIA algorithm is not efficient due to high complexity and un-effective due to poor selection of Robust Error Function and scale parameter that depends on a particular training dataset. In this paper, an Improved Statistical Model of Appearance (ISMA) method is proposed by integration techniques of perceptual-oriented uniform Color Appearance Model (CAM) and Jensen-Shannon Divergence (JSD) to overcome these limitations. To reduce iteration steps which decrease computational complexity, the distribution of probability of each occluded and un-occluded image regions is measured. The ISMA method is tested by using convergence measure on 600 facial images by varying degree of occlusion from 10% to 50%. The experimental results indicate that the ISMA method is achieved more than 95% convergence compared to RNICIA algorithm thus the performance of appearance models have significantly improved in terms of partial occlusion.

[1] Abbas Q., Celebi M., Serrano C., Garcia I., and Ma G., Pattern Classification of Dermoscopy Images: A Perceptually Uniform Model, Pattern Recognition, vol. 46, no. 1, pp. 86-97, 2013.

[2] Azeem A., Sharif M., Raza M. and Murtaza M., A Survey: Face Recognition Techniques under Partial Occlusion, The International Arab Journal of Information Technology, vol. 11, no. 1, pp. 1-10, 2014.

[3] Bagnato L., Sorci M., Antonini G., Baruffa G., Maier A., Leathwood P., and Thiran J., Advances in Visual Computing, Springerlink, 2007.

[4] Baker S., Gross R., and Matthews I., Lucas- Kanade 20 Years on: A Unifying Framework: Part 2, Technical Report Number CMU-RI-TR- 03-01, 2003.

[5] Cao X., Wei Y., Wen F., and Sun J., Face Alignment by Explicit Shape Regression, International Journal of Computer Vision, vol. 107, no. 2, pp. 177-190, 2014.

[6] Cha S. and Srihari S., On Measuring the Distance Between Histograms, Pattern Recognition, vol. 35, no. 6, pp. 1355-1370, 2002.

[7] Chen X., Udupa J., Bagci U., Zhuge Y., and Yao J., Medical Image Segmentation by Combining Graph Cuts and Oriented Active Appearance Models, IEEE Transactions on Image Processing, vol. 21, no. 4, pp. 2035-2046, 2012.

[8] Cootes T., Edwards G., and Taylor C., Active Appearance Models, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 681-685, 2001.

[9] Cootes T. and Taylor C., Anatomical Statistical Models and their Role in Feature Extraction, An Improved Statistical Model of Appearance under Partial Occlusion 669 The British Journal of Radiology, vol. 77, no. 2, pp. 133-139, 2004.

[10] Dopfer A., Wang H., and Wang C., 3D Active Appearance Model Alignment using Intensity and Range Data, Robotics and Autonomous Systems, vol. 62, no. 2, pp. 168-176, 2014.

[11] Fairchild M., A Revision of CIECAM97s for Practical Applications, Color research and applications, vol. 26, no. 6, pp. 418-427, 2001.

[12] Grossc R., Matthews I., and Baker S., Active Appearance Models with Occlusion, Image and Vision Computing, vol. 24, no. 6, pp. 593-604, 2006.

[13] Liu X., Video-Based Face Model Fitting using Adaptive Active Appearance Model, Image and Vision Computing, vol. 28, no. 7, pp. 1162-1172, 2010.

[14] Martinez B. and Pantic M., Facial Landmarking for in-the-Wild Images with Local Inference based on Global Appearance, Image and Vision Computing, vol. 36, pp. 40-50, 2015.

[15] Martinez A. and Benavente R.,, Last Visited 2014.

[16] Papandreou G. and Maragos P., Adaptive and Constrained Algorithms for Inverse Compositional Active Appearance Model Fitting, in Proceeding of IEEE International Conference on Computer Vision and Pattern Recognition, Anchorage, pp. 1-8, 2008.

[17] Stegmann M.,, Last Visited 2014.

[18] Stegmann M. and Gomez D., A Brief Introduction to Statistical Shape Analysis, Technical Report, 2002.

[19] Storer M., Roth P., Urschler M., and Bischof H., Fast-Robust PCA, Image Analysis Lecture Notes in Computer Science, vol. 5575, pp. 430- 439, 2009.

[20] Theobald B., Matthews I., and Baker S., Evaluating Error Functions for Robust Active Appearance Models, in Proceeding of the 7th International Conference on Automatic Face and Gesture Recognition, Southampton, pp. 149-154, 2006.

[21] Wu X., Du J., and Zhai C., Face Verification across Age Progressing Based on Active Appearance Model and Gradient Orientation Pyramid, Intelligent Computing Theories Lecture Notes in Computer Science, vol. 7995, pp. 427- 434, 2013.

[22] Yan J., Chen X., Deng D., and Zhu Q., Structured Partial Least Squares based Appearance Model for Visual Tracking, Neurocomputing, vol. 144, pp. 58-595, 2014.

[23] Yu X., Tian J., and Liu J., Active Appearance Models Fitting with Occlusion, Energy Minimization Methods in Computer Vision and Pattern Recognition Lecture Notes in Computer Science, vol. 4679, pp. 137-144, 2007.

[24] Zhang W. and Shan S., Local Gabor Binary Patterns Based on Kullback-Leibler Divergence for Partially Occluded Face Recognition, IEEE Signal Processing Letters, vol. 14, no. 11, pp. 875-878, 2007. Qaisar Abbas has done PhD in 2011 and he is currently working as an assistant professor at College of Computer and Information Sciences, Al Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi Arabia. He is currently doing research in Computer vision and Biomedical Image processing. Tanzila Saba earned PhD in document information security and management from Faculty of Computing Universiti Teknologi Malaysia (UTM), Malaysia in 2012. She won best student award in the Faculty for 2012. Currently, she is serving as Assistant Prof. in College of Computer and Information Sciences Prince Sultan University Riyadh KSA. Her main research interest include soft computing, image processing and data mining. Due to her excellent research achievement, she is included in Marquis Who s Who (S and T) 2012. Currently she is member of editorial board of some reputed journals and on panel of TPC of international conferences.