作者: E.R. Davies , M. Bateman , D.R. Mason , J. Chambers , C. Ridgway
DOI: 10.1016/S0167-8655(02)00266-0
关键词: Shape analysis (digital geometry) 、 Document processing 、 Computer science 、 Template matching 、 Artificial intelligence 、 Computer vision 、 Line segment 、 Detector 、 False positive paradox
摘要: This paper shows how line segment detection can be achieved with a minimum of computation if two masks embodying vectorial design strategy are employed. To achieve the greatest combination accuracy and speed, two-stage procedure was used operator backed up by template matching technique. Experimental tests verified effectiveness this type detector for locating insects in cereal grain images: set 60 images containing 150 insects, there were no false positives only negative arose from which contact. The approach should useful good many other areas ranging industrial inspection to document processing remote sensing--and indeed, applications where segments have located or thin lines tracked.