A Technique for Facilitating Threshold Selection for Object Extraction from Digital Pictures

Abstract : TAL Pictures,Weszka,J. S. ;Nagel,R. N. ;Rosenfeld,A. ;F44620-72-C-0062AF-9769AFOSRTR-73-1263(*photographic images, *pattern recognition), photointerpretation, data processinghistograms, *digital pictures, edge detection, *feature extractionThreshold selection for picture segmentation is relatively easy when the frequency distribution of gray levels in the picture is strongly bimodal, with the two peaks comparable in size and separated by a deep valley. The report describes a method of handling cases in which the peaks are very unequal in size and the valley is broad. A Laplacian operation is applied to the picture to determine points that lie on or near the edges of objects. Threshold selection becomes easier when the frequency distribution of gray levels of these points is used. (Author)