Image Segmentation using Sparse Subspace Clustering

Siddharth Jain, Vinith Rejathalal, V K Govindan

Abstract


Image segmentation is one of the fundamental problems in computer vision. Machine learning approaches to solving the problem of partitioning pixels into disjoint and meaningful subsets is a major area of research. Both supervised and unsupervised techniques have been applied on this pattern classification problem. Among supervised learning, sparse dictionary learning is a relatively new technique that has given good performance on image segmentation problem. Training a dictionary on each class of features extracted from the images has resulted in creating an overcomplete basis that spans the subspace to which the particular class feature set belongs. We are investigating to address the problem in the unsupervised setting, where prior information on the class features are unavailable. We address the problem by classifying the features based on the subspace to which they belong. This is done by graph-cut segmentation by defining similarity matrix based on subspace clustering. The results obtained are encouraging and strongly indicates the fact that higher dimensional features may be classified more accurately by utilizing subspace characteristics than by using functions of distance measures.


References


E. Elhamifar and R. Vidal. Sparse subspace clustering: Algorithm, theory, and applications. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 35(11):2765–2781, Nov 2013.

A Adler and M. Elad. Probabilistic subspace clustering via sparse representations. Signal Processing Letters, IEEE, 20(1):63–66, Jan 2013.

Xiaofang Wang, Huibin Li and Charles-Edmond , A graph-cut approach to image segmentation using anaffinity graph based on l0-sparse representationof features. In IEEE International Conference on Image Processing, ICIP 2013, Melbourne, Australia, September 15-18, 2013, pages 4019–4023,2013.

K. Santle Camilus, V. K. Govindan, P. S. Sathidevi, "A Robust Graph Theoretic Approach for Image Segmentation", In proceedings of 4th IEEE international conference on signal image technology and internet based systems, Pages: 382-386, Nov.30- Dec 3, 2008, Bali, Indonesia.

JianZhou Feng, Li Song, XiaoKang Yang and Wenjun Zhang . Sub clustering K-SVD: Size variable Dictionary learning for Sparse Representations,45(7):2764–2774 2008.

Amir Adler, Michael Elad, and Yacov Hel-Or. Probabilistic subspace clustering via sparse representations. IEEE Signal Process. Lett., 20(1):63–66, 2013.

Idan Ram, Michael Elad, and Israel Cohen.Image processing using smooth ordering of its patches. IEEE Transactions on Image Processing, 22(7):2764–2774, 2013.

.K.Santle Camilus, V. K. Govindan and P. S. Sathidevi, A mean based graph theoretic approach for image segmentation”, International Journal of Signal and Imaging Systems Engineering, Inderscience Publishers Ltd., Vol. 2, No ½, 2009

A. Jayachandran and R. Dhanasekaran . Brain Tumor Detection and Classification of MR Images Using Texture Features and Fuzzy SVM Classifier , 2013.

.Jobin Raj and Govindan V K; Unsupervised color image segmentation by clustering into multivariate Gaussians, Communications in computer and information science, 1, Vol 157, part 10, pp. 639-645, 2011

M. Aharon, M. Elad, and A Bruckstein, k-svd An algorithm for designing overcomplete dictionaries for sparse representation. Signal Processing, IEEE Transactions on, 54(11):4311–4322,Nov 2006.

.K. Santle Camilus and V. K. Govindan; “A Review on Graph Based Segmentation”, International Journal of Image, Graphics and Signal Processing (IJIGSP), 2012, 5, 1-13.

Ron Rubinstein, Michael Zibulevsky, and Michael Elad. Double sparsity: learning sparse dictionaries for sparse signal approximation. IEEE Transactions on Signal Processing, 58(3):1553–1564, 2010.

Fritz Albregtsen, Statistical Texture Measures Computed from Gray Level Coocurrence Matrices,

University of Oslo, Vol. 28, pp. 199-219, 2008.


پاراگلایدر Full Text: PDF

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.

ISSN : 2251-1563