Model based segmentation and detection of affine transformed shapes in cluttered images

This paper presents a novel approach for detection and segmentation of generic shapes in cluttered images. The underlying assumption is that man made objects frequently have surfaces which closely resemble standard model shapes such as rectangles, semicircles etc. Due to the transformation of optical imaging systems, a model shape can appear differently in the image with different orientations and aspect ratios. This set of possible appearances can be represented compactly by a few vectorial eigenbases that are derived from a small set of model shapes which are affine transformed in a wide range. The use of vectorial boundary information improves robustness to noise, background clutter and partial occlusion. The detection of generic shapes is realized by detecting local peaks of a similarity measure between the image edge map and an eigenspace combined set of the appearances. At each local maxima, a fast search approach based on a novel representation by angle space is employed to determine the best matching between models and the underlying subimage. Experiments are performed in various interfering distortions, and robust detection and recognition are achieved.