Object identification for computer vision using image segmentation

Object detection for computer vision is one of the key factors for scene understanding. It is still a challenge today to accurately determine an object from a background where similar shaped objects are present in a large number. In this paper we proposed a method for object detection from such chaotic background by using image segmentation and graph partitioning. We build a “feature set” from the original object and then we train the system using the “feature set” and graph partitioning on the chaotic image. Testing is done on computer manipulated images and real world images. In both the cases our system identified the search object among other similar objects successfully.

[1]  Vikas Singh,et al.  An efficient algorithm for Co-segmentation , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[2]  Allan D. Jepson,et al.  Spectral Embedding and Min Cut for Image Segmentation , 2004, BMVC.

[3]  Anat Levin,et al.  Learning to Combine Bottom-Up and Top-Down Segmentation , 2006, International Journal of Computer Vision.

[4]  Shimon Ullman,et al.  Class-Specific, Top-Down Segmentation , 2002, ECCV.

[5]  Jianbo Shi,et al.  Bottom-up Recognition and Parsing of the Human Body , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.