PointFlow: A Model for Automatically Tracing Object Boundaries and Inferring Illusory Contours

In this paper, we propose a novel method for tracing object boundaries automatically based on a method called “PointFlow” in image induced vector fields. The PointFlow method comprises two steps: edge detection and edge integration. Basically, it uses an ordinary differential equation for describing the movement of points under the action of an image-induced vector field and generates induced trajectories. The trajectories of the flows allow to find and integrate edges and determine object boundaries. We also extend the original PointFlow method to make it adaptable to images with complicated scenes. In addition, the PointFlow method can be applied to infer certain illusory contours.

[1]  Zheru Chi,et al.  Geometric Analysis of Particle Motion in a Vector Image Field , 2006, Journal of Mathematical Imaging and Vision.

[2]  Alfred M. Bruckstein,et al.  Regularized Laplacian Zero Crossings as Optimal Edge Integrators , 2003, International Journal of Computer Vision.

[3]  Nawapak Eua-anant,et al.  Boundary detection using simulation of particle motion in a vector image field , 1999, IEEE Trans. Image Process..

[4]  Alfred M. Bruckstein,et al.  Image Flows and One‐Liner Graphical Image Representation , 2002 .

[5]  C. Tomasi.  Coalescing Texture Descriptors , 1996 .

[6]  Djemel Ziou,et al.  Edge Detection Techniques-An Overview , 1998 .

[7]  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.

[8]  Charless C. Fowlkes,et al.  Contour Detection and Hierarchical Image Segmentation , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  J. Butcher.  Numerical methods for ordinary differential equations in the 20th century , 2000 .

[10]  R. von der Heydt,et al.  Illusory contours and cortical neuron responses. , 1984, Science.

[11]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[12]  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.