Junctions: Detection, Classification, and Reconstruction

Junctions are important features for image analysis and form a critical aspect of image understanding tasks such as object recognition. We present a unified approach to detecting, classifying, and reconstructing junctions in images. Our main contribution is a modeling of the junction which is complex enough to handle all these issues and yet simple enough to admit an effective dynamic programming solution. We use a template deformation framework along with a gradient criterium to detect radial partitions of the template. We use the minimum description length principle to obtain the optimal number of partitions that best describes the junction. The Kona detector presented by Parida et al. (1997) is an implementation of this model. We demonstrate the stability and robustness of the detector by analyzing its behavior in the presence of noise, using synthetic/controlled apparatus. We also present a qualitative study of its behavior on real images.

[1]  Adolfo Guzman,et al.  Decomposition of a visual scene into three-dimensional bodies , 1968 .

[2]  Manfred H. Hueckel.  An Operator Which Locates Edges in Digitized Pictures , 1971, J. ACM.

[3]  Manfred H. Hueckel.  A Local Visual Operator Which Recognizes Edges and Lines , 1973, JACM.

[4]  Robert A. Hummel,et al.  Feature detection using basis functions , 1979 .

[5]  E. Adelson,et al.  Phenomenal coherence of moving visual patterns , 1982, Nature.

[6]  J. Rissanen.  A UNIVERSAL PRIOR FOR INTEGERS AND ESTIMATION BY MINIMUM DESCRIPTION LENGTH , 1983 .

[7]  J. Rissanen.  Stochastic Complexity and Modeling , 1986 .

[8]  Yehezkel Lamdan,et al.  Geometric Hashing: A General And Efficient Model-based Recognition Scheme , 1988, [1988 Proceedings] Second International Conference on Computer Vision.

[9]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[10]  J. Bigun.  A structure feature for some image processing applications based on spiral functions , 1990 .

[11]  Rachid Deriche,et al.  On corner and vertex detection , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  David J. Beymer,et al.  Finding junctions using the image gradient , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[13]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[14]  Kjell Brunnström,et al.  Active Detection and Classsification of Junctions by Foveation with a Head-Eye System Guided by the Scale-Space Primal Sketch , 1992, ECCV.

[15]  J. Koenderink,et al.  Invariant Third Order Properties of Isophotes: T-Junction Detection , 1992 .

[16]  Rachid Deriche,et al.  Recovering and characterizing image features using an efficient model based approach , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[17]  David Mumford,et al.  Filtering, Segmentation and Depth , 1993, Lecture Notes in Computer Science.

[18]  Wolfgang Förstner,et al.  A Framework for Low Level Feature Extraction , 1994, ECCV.

[19]  Uwe Weidner,et al.  Parameterfree Information-Preserving Surface Restoration , 1994, ECCV.

[20]  Jean-Michel Morel,et al.  Variational methods in image segmentation , 1995 .

[21]  Eero P. Simoncelli,et al.  Steerable wedge filters for local orientation analysis , 1996, IEEE Trans. Image Process..

[22]  R. Shapley,et al.  “On the Visually Perceived Direction of Motion” by Hans Wallach: 60 Years Later , 1996 .

[23]  Jitendra Malik,et al.  On Binocularly Viewed Occlusion Junctions , 1996, ECCV.

[24]  Laxmi Parida,et al.  Visual organization for figure/ground separation , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[25]  Laxmi Parida,et al.  Kona: A Multi-junction Detector Using Minimum Description Length Principle , 1997, EMMCVPR.