Finding Stable Extremal Region Boundaries

This paper introduces a novel boundary detection framework finding the most stable region boundaries in grayscale images. In contrast to common detection algorithms as Canny, which only analyze local discontinuities in image brightness our method also integrates mid-level information by analyzing regions that support the local gradient magnitudes. We build a component tree where every node contains a single connected region obtained from thresholding the input image and edges define the spatial relations between the nodes. Then connected nodes at different levels in the tree are compared by a simplified chamfer matching method. Matching regions have boundaries that stay similar over several image intensities, and thus contribute as stable edges to the final result. Since the component tree can be calculated in linear time and chamfer matching between nodes in the component tree is reduced to an analysis of the distance transformation, results are obtained in a very efficient manner. Furthermore, the proposed detection algorithm automatically labels all identified boundaries during calculation avoiding the required post-processing of connecting and labeling edge responses for usage in a detection framework. We compare our method against standard Canny and the Berkeley edge detector on the ETHZ shape classes and the Weizmann horses dataset, which both demonstrate better performance in reducing clutter.

[1]  Gilles Bertrand,et al.  Quasi-Linear Algorithms for the Topological Watershed , 2005, Journal of Mathematical Imaging and Vision.

[2]  J. Hartigan.  Statistical theory in clustering , 1985 .

[3]  Jiri Matas,et al.  Robust wide-baseline stereo from maximally stable extremal regions , 2004, Image Vis. Comput..

[4]  Andrew Blake,et al.  Multiscale Categorical Object Recognition Using Contour Fragments , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Robert E. Tarjan,et al.  Efficiency of a Good But Not Linear Set Union Algorithm , 1972, JACM.

[6]  Richard Jones.  Component trees for image filtering and seg - mentation , 1997 .

[7]  Frédéric Jurie,et al.  Groups of Adjacent Contour Segments for Object Detection , 2008, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  V. Mosorov,et al.  The development of component tree structure for grayscale image segmentation , 2002, Modern Problems of Radio Engineering, Telecommunications and Computer Science (IEEE Cat. No.02EX542).

[9]  Ronald Jones,et al.  Connected Filtering and Segmentation Using Component Trees , 1999, Comput. Vis. Image Underst..

[10]  Shimon Ullman,et al.  Learning to Segment , 2004, ECCV.

[11]  David Nistér,et al.  Linear Time Maximally Stable Extremal Regions , 2008, ECCV.

[12]  Michel Couprie,et al.  Quasilinear algorithm for the component tree , 2004, IS&T/SPIE Electronic Imaging.

[13]  Andrew Blake,et al.  Contour-based learning for object detection , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[14]  Andrew Zisserman,et al.  A Boundary-Fragment-Model for Object Detection , 2006, ECCV.

[15]  Zhuowen Tu,et al.  Detecting Object Boundaries Using Low-, Mid-, and High-level Information , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Alan L. Yuille,et al.  Statistical Edge Detection: Learning and Evaluating Edge Cues , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  Luc Van Gool,et al.  Object Detection by Contour Segment Networks , 2006, ECCV.

[18]  R. K. Shyamasundar,et al.  Introduction to algorithms , 1996 .

[19]  Philippe Salembier,et al.  Antiextensive connected operators for image and sequence processing , 1998, IEEE Trans. Image Process..

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

[21]  Per-Erik Forssén,et al.  Maximally Stable Colour Regions for Recognition and Matching , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[22]  Michel Couprie,et al.  Building the Component Tree in Quasi-Linear Time , 2006, IEEE Transactions on Image Processing.

[23]  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.

[24]  Zhuowen Tu,et al.  Supervised Learning of Edges and Object Boundaries , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).