Partial contour processing using curvature function‐assembly of jigsaw puzzle and recognition of moving figures

This paper proposes a method of partial contour processing by a curvature function and an adaptive integral filter. The filter parameter is determined by the length of the zero‐crossing segment of the curvature function both to enhance the concavo‐convex parts of the contour and to eliminate the quantization noise of the raw curvature function. Partial matching of contours is performed precisely and efficiently using the filtered curvature function. Three tasks were accomplished by the abovementioned method: assembly of a jigsaw puzzle, discrimination of overlapping and rotating figures, and tracking of a moving object which overlaps the background figures.