2016/09/12 by Muhammet Baştan, Bastan, Muhammet, Syed Sohail Bukhari +3
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · #Cell Image Analysis Techniques #Computer Vision and Pattern Recognition (cs.CV) #Enhanced Oil Recovery Techniques #FOS: Computer and information sciences #Image and Object Detection Techniques #Medical Image Segmentation Techniques #Multimedia (cs.MM)
paper · pdf · doi:10.48550/arxiv.1609.03415
openalex publication_date 2016/09/12 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28
We introduce an edge detection and recovery framework based on open active\ncontour models (snakelets). This is motivated by the noisy or broken edges\noutput by standard edge detection algorithms, like Canny. The idea is to\nutilize the local continuity and smoothness cues provided by strong edges and\ngrow them to recover the missing edges. This way, the strong edges are used to\nrecover weak or missing edges by considering the local edge structures, instead\nof blindly linking them if gradient magnitudes are above some threshold. We\ninitialize short snakelets on the gradient magnitudes or binary edges\nautomatically and then deform and grow them under the influence of gradient\nvector flow. The output snakelets are able to recover most of the breaks or\nweak edges, and they provide a smooth edge representation of the image; they\ncan also be used for higher level analysis, like contour segmentation.\n