Title :
Constrained phase congruency: simultaneous detection of interest points and of their scales
Author :
Reisfeld, Daniel
Author_Institution :
Inst. Nat. de Recherche en Inf. et Autom., Sophia Antipolis, France
Abstract :
A novel feature detector-the Constrained Phase Congruency Transform (CPCT) is introduced. It simultaneously detects interest points as well as their scale in various orientations. The CPCT is especially important in registration applications: the local transformation between interest points can be determined based on their orientational scales. The CPCT detects the features in Mach bands and in sinusoidal waves. This cannot be done simply by 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. The robustness of the CPCT is achieved by constraining the local phase. Only four easy-to-detect phases are used in the computations. They correspond to symmetry and anti-symmetry in their neighborhood. The scale at any location and orientation is determined by the scale of the channel that conforms to the constraints and maximizes energy
Keywords :
feature extraction; image registration; CPCT; Constrained Phase Congruency Transform; Mach bands; feature detection; feature detector; local transformation; phase congruency; registration; sinusoidal waves; Biomedical imaging; Computer vision; Detectors; Image matching; Image recognition; Personnel; Phase detection; Robots; Robustness; Stereo vision;
Conference_Titel :
Computer Vision and Pattern Recognition, 1996. Proceedings CVPR '96, 1996 IEEE Computer Society Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-8186-7259-5
DOI :
10.1109/CVPR.1996.517128