Conformal monogenic phase congruency model-based edge detection in color images

To enhance the precision of edge localization and noise suppression in a color image, we propose a conformal monogenic phase congruency model-based (CMPCM) edge detection algorithm that has a good analytical capability in a spatial domain for local structural features to exploit points of the maximum phase congruency in two-dimensional images, and employ Pratt’s Figure of Merit (PFOM) evaluation metrics to measure the performance of its edge detection. Comprehensive experiments were conducted on synthetic color images and natural color images from BSDS500 and LPAICI standard image datasets. The experimental results demonstrated that the proposed CMPCM algorithm outperforms other algorithms, such as viz. Canny, LOG, VPMM, PC and MPC, and has smaller computational time consumption as well.