Incomplete Contour Representations and Shape Descriptors: ICR Test Studies

Inspired by psychophysical studies of the human cognitive abilities we propose a novel aspect and a method for performance evaluation of contour based shape recognition algorithms regarding their robustness to incompleteness of contours. We use complete contour representations of objects as a reference (training) set. Incomplete contour representations of the same objects are used as a test set. The performance of an algorithm is reported using the recognition rate as a function of the percentage of contour retained. We call this evaluation procedure the ICR test. We consider three types of contour incompleteness, viz. segment-wise contour deletion, occlusion and random pixel depletion. We illustrate the test procedure using two shape recognition algorithms. These algorithms use a shape context and a distance multiset as local shape descriptors. Both algorithms qualitatively mimic human visual perception in the sense that the recognition performance monotonously increases with the degr...

• Type: Conference
• Year: 2005
• Where: BVAI
• Authors: Anarta Ghosh, Nicolai Petkov
• Keywords: BVAI 2005, Contour, Contour Representations, Shape Recognition Algorithms