Segmentation of Salient Closed Contours from Real Images

Using a saliency measure based on the global property of contour closure, we have developed a method that reliably segments out salient contours bounding unknown objects from real edge images. The measure also incorporates the Gestalt principles of proximity and smooth continuity that previous methods have exploited. Unlike previous measures, we incorporate contour closure by nding the eigen-solution associated with a stochastic process that models the distribution of contours passing through edges in the scene. The segmentation algorithm utilizes the saliency measure to identify multiple closed contours by nding stronglyconnected components on an induced graph. The determination of strongly-connected components is a direct consequence of the property of closure. We report for the rst time, results on large real images for which segmentation takes an average of about 10 secs per object on a general-purpose workstation. The segmentation is made e cient for such large images by exploiti...

• Type: Conference
• Year: 1999
• Where: ICCV
• Authors: Shyjan Mahamud, Karvel K. Thornber, Lance R. Williams
• Keywords: Computer Vision, Contour Closure, ICCV 1999, Large Real Images, Multiple Closed Contours, Salient Contours, Segmentation Algorithm