Automatic Image Segmentation by Positioning a Seed

We present a method that automatically partitions a single image into non-overlapping regions coherent in texture and colour. An assumption that each textured or coloured region can be represented by a small template, called the seed, is used. Positioning of the seed across the input image gives many possible sub-segmentations of the image having same texture and colour property as the pixels behind the seed. A probability map constructed during the sub-segmentations helps to assign each pixel to just one most probable region and produce the final pyramid representing various detailed segmentations at each level. Each sub-segmentation is obtained as the min-cut/max-flow in the graph built from the image and the seed. One segment may consist of several isolated parts. Compared to other methods our approach does not need a learning process or a priori information about the textures in the image. Performance of the method is evaluated on images from the Berkeley database.

[1]  Vladimir Kolmogorov,et al.  An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision , 2001, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Stella X. Yu.  Segmentation using multiscale cues , 2004, CVPR 2004.

[3]  Vladimir Kolmogorov,et al.  Spatially coherent clustering using graph cuts , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[4]  David A. Forsyth,et al.  Matching Words and Pictures , 2003, J. Mach. Learn. Res..

[5]  Allan Hanbury,et al.  Supervised Texture Detection in Images , 2005, CAIP.

[6]  Stella X. Yu.  Segmentation using multiscale cues , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[7]  Jitendra Malik,et al.  Learning to detect natural image boundaries using local brightness, color, and texture cues , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Vladimir Kolmogorov,et al.  What energy functions can be minimized via graph cuts? , 2002, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  S. Osher,et al.  Geometric Level Set Methods in Imaging, Vision, and Graphics , 2011, Springer New York.

[10]  Rachid Deriche,et al.  Geodesic Active Regions and Level Set Methods for Supervised Texture Segmentation , 2002, International Journal of Computer Vision.

[11]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[12]  Jitendra Malik,et al.  Contour and Texture Analysis for Image Segmentation , 2001, International Journal of Computer Vision.

[13]  Arnold W. M. Smeulders,et al.  Color-based object recognition , 1997, Pattern Recognit..

[14]  Allan D. Jepson,et al.  Quantitative evaluation of a novel image segmentation algorithm , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[15]  Zhuowen Tu,et al.  Image Parsing: Unifying Segmentation, Detection, and Recognition , 2005, International Journal of Computer Vision.

[16]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[17]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[18]  S. S. Wolfson,et al.  PII: S0042-6989(97)00153-3 , 2003 .

[19]  Jitendra Malik,et al.  Learning affinity functions for image segmentation: combining patch-based and gradient-based approaches , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..