Object Segmentation by an Automatic Edge Constrained Region Growing Technique

Region growing is a well known technique for image segmentation. However it suffers from certain limitations such as ambiguity regarding initial seed selection and threshold determination for region growing. In this paper we explore the possibility of using region growing technique for segmenting out the foreground object and propose to solve the imperfect results by incorporating the nearest edge information. The whole procedure is rendered automatic by defining a center window containing some part of the object. From this window the seed selection and threshold value for region growing is determined by simple computations. The results on the 'Car' category of the challenging PASCAL VOC 2005 dataset indicate a superior performance to Xavier Bresson's method for object segmentation.

[1]  M. Ghanbari,et al.  Nonlinear Gaussian filtering approach for object segmentation , 1999 .

[2]  Madasu Hanmandlu,et al.  A Simple Single Seeded Region Growing Algorithm for Color Image Segmentation using Adaptive Thresholding , 2011, 2011 International Conference on Communication Systems and Network Technologies.

[3]  Natan Peterfreund,et al.  Robust Tracking of Position and Velocity With Kalman Snakes , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Tieniu Tan,et al.  A multi-object tracking system for surveillance video analysis , 2004, ICPR 2004.

[5]  Josef Kittler,et al.  Region growing: a new approach , 1998, IEEE Trans. Image Process..

[6]  Jianhua Xuan,et al.  Segmentation of magnetic resonance brain image: integrating region growing and edge detection , 1995, Proceedings., International Conference on Image Processing.

[7]  Christof Koch,et al.  A Model of Saliency-Based Visual Attention for Rapid Scene Analysis , 2009 .

[8]  Tieniu Tan,et al.  A multi-object tracking system for surveillance video analysis , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[9]  Juliana Fernandes Camapum,et al.  Segmentation of clinical structures from images of the human pelvic area , 2004, Proceedings. 17th Brazilian Symposium on Computer Graphics and Image Processing.

[10]  Jitendra Malik,et al.  Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Xavier Bresson,et al.  A Variational Model for Object Segmentation Using Boundary Information and Shape Prior Driven by the Mumford-Shah Functional , 2006, International Journal of Computer Vision.

[12]  Ulrich Kressel,et al.  Tracking non-rigid, moving objects based on color cluster flow , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Rolf Adams,et al.  Seeded Region Growing , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Pietro Perona,et al.  Graph-Based Visual Saliency , 2006, NIPS.

[15]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Jun Tang,et al.  A color image segmentation algorithm based on region growing , 2010, 2010 2nd International Conference on Computer Engineering and Technology.

[17]  Chaobing Huang,et al.  Color image segmentation by seeded region growing and region merging , 2010, 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery.