The constrained phase congruency feature detector: simultaneous localization, classification and scale determination

Abstract A novel feature detector — the Constrained Phase Congruency Transform (CPCT) is introduced. It simultaneously detects interest points together with their scale in various orientations. Each interest point is detected due to a (possibly imperfect) symmetry (or anti-symmetry) around it. The scale of the symmetry (or anti-symmetry) is associated wich each point. The symmetry (or anti-symmetry) type is used to classify the point. The CPCT is especially important in registration applications: the local transformation between interest points can be determined based on their orientational scales. Only points belonging to the same class should be compared. The CPCT detects the features in Mach bands and in sinusoidal waves. This cannot be done by simply looking for local maxima in intensity gradient nor by looking for local energy maxima. I conjecture that constraining the general phase congruency is sufficient for feature detection. The correct detection of features' location and of their scale is demonstrated.

[1]  Nicholas Ayache,et al.  3D-2D Projective Registration of Free-Form Curves and Surfaces , 1997, Comput. Vis. Image Underst..

[2]  E H Adelson,et al.  Spatiotemporal energy models for the perception of motion. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[3]  P Perona,et al.  Preattentive texture discrimination with early vision mechanisms. , 1990, Journal of the Optical Society of America. A, Optics and image science.

[4]  Robyn A. Owens,et al.  Feature detection from local energy , 1987, Pattern Recognit. Lett..

[5]  Carl-Johan Westelius,et al.  Focus of attention and gaze control for robot vision , 1995 .

[6]  M. Brady,et al.  Rejecting outliers and estimating errors in an orthogonal-regression framework , 1995, Philosophical Transactions of the Royal Society of London. Series A: Physical and Engineering Sciences.

[7]  Chuan Yi Tang,et al.  A 2.|E|-Bit Distributed Algorithm for the Directed Euler Trail Problem , 1993, Inf. Process. Lett..

[8]  Yehezkel Yeshurun,et al.  Detection of interest points using symmetry , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[9]  D. Burr,et al.  Mach bands are phase dependent , 1986, Nature.

[10]  Yehezkel Yeshurun,et al.  Robust detection of facial features by generalized symmetry , 1992, [1992] Proceedings. 11th IAPR International Conference on Pattern Recognition.

[11]  Jan-Olof Eklundh,et al.  Scale-space primal sketch: construction and experiments , 1992, Image Vis. Comput..

[12]  Nur Arad,et al.  Image Warping Using Few Anchor Points and Radial Functions , 1995, Comput. Graph. Forum.

[13]  Hans Knutsson,et al.  Signal processing for computer vision , 1994 .

[14]  Jitendra Malik,et al.  Detecting and localizing edges composed of steps, peaks and roofs , 1990, [1990] Proceedings Third International Conference on Computer Vision.

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

[16]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[17]  Rachid Deriche,et al.  A Robust Technique for Matching two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry , 1995, Artif. Intell..

[18]  Peter Kovesi,et al.  Image Features from Phase Congruency , 1995 .