ConGrap - Contour Detection based on Gradient Map of Images

In this paper, we present ConGrap, a novel contour detector that uses the Gradient Map and results in closed contours with semantic connections. In contrast to common edge and contour detections, ConGrap not only produces an edge image, but also provides additional information (e.g. the borderline pixel coordinates, the bounding box, etc.) about every contour. Additionally, the resulting contour image provides closed contours without discontinuities and merges regions with semantic connections together. Consequently, the ConGrap contour image can be seen as an enhanced edge image as well as a kind of segmentation and object recognition.