Unsupervised Grouping of Local Components for Object Segmentation

  • Mohammad Khairul Islam
  • Farah Jahan
  • Joong Hwan Baek
  • Seung-Jun Hwang
Keywords: SUFT, object detection, Color histogram.


In this paper, we propose a novel object segmentation method for image understanding. Due to challenges such as variations in object size, orientation, illumination etc. object segmentation is extraordinarily difficult task in the domain of image understanding. It is well-founded concept that a small portion of the pixel set in an image contributes most in image description. Based on this concept, we hypothesize that an image consists of many components or parts each of which represent a small local area in the image and they are very meaningful in visual perception. For object segmentation, we propose spatial segmentation method on such prototypical components of images. Given an image this segmentation method acts as coarse to fine search for object(s) iteratively. The proposed method demonstrate its excellence in localizing objects in various complex backgrounds, multiple objects in a single image even if they have variation in size, orientation, lighting conditions etc. The detection efficiency of our object detector on our self-collected image set which consists of images from six different object categories climbs up to 93% in average.  


[1] J. Shotton, A. Blake, and R. Cipolla, “Multi-scale categorical object recognition using contour fragments,” IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 30, no. 7, pp. 1270–1281, 2008.
[2] L. Zhu, Y. Chen, Y. Lin, C. Lin, and A. Yuille, “Recursive segmentation and recognition templates for 2D parsing,” In Proceedings of the International Conference on Neural Information Processing Systems (NIPS), pp. 1985-1992, 2008.
[3] N. Dalal, and B. Triggs, “Histograms of oriented gradients for human detection,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, USA, pp. 886-893, 20-26 June, 2005.
[4] P. Viola, and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii, vol. 1, pp. 511-518, 2001.
[5] S. Maji, and J. Malik, “Object detection using a max-margin hough transform,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , Miami, FL, USA, pp. 1038, 2009.
[6] I. Biederman, “Recognition-by-components: A theory of human image understanding,” Psychological Review, vol. 94, no. 2, pp. 115-147, 1987.
[7] Y. Amit, and D. Geman, “A computational model for visual selection,” Neural Computation, vol. 11, pp. 1691-1715, 1999.
[8] D. Roth, M. H. Yang, and N. Ahuja, “Learning to recognize 3D objects”, Neural Computation, vol. 14, no. 5, pp. 1071-1104, 2002.

[9] E. Rosten, and T. Drummond, "Machine learning for high-speed corner detection,” European Conference on Computer Vision (ECCV), Graz, Austria, pp. 430-443, 11-14 May, 2006.
[10] H. Bay, A. Ess, T. Tuytelaars, L. V. Gool, “SURF: Speeded Up Robust Features,” Journal of Computer Vision and Image Understanding (CVIU), vol. 110, no. 3, pp. 346-359, 2008.
[11] O. Javed, Z. Rasheed, K. Shafique, and M. Shah, “Tracking across multiple cameras with disjoint views,” Proceeding of the IEEE International Conference on Computer Vision (ICCV), Nice, France, pp. 952-957, 13-16 October, 2003.
[12] M. K. Islam, F. Jahan, J. H. Min, and J. H. Baek, “Object classification based on visual and extended features for video surveillance application,” Proceedings of the 8th Asian Control Conference (ASCC), Kaohsiung, Taiwan, pp. 1398 – 140, May 15-18, 2011.
[13] J. Sivic, B. C. Russell, A. A. Efros, A. Zisserman, and W. T. Freeman, “Discovering objects and their location in images,” Proceedings of the IEEE International Conference on Computer Vision (ICCV), San Diego, USA, pp. 370-377 , 2005.