An efficient approach to automatic shape recognition

Automated shape recognition in two dimensions is analyzed, and an efficient approach is provided to reduce the redundancy of the matching process. Shape recognition is achieved through locating the objects to be recognized within the field of view. Two theorems are presented. The first theorem is applied to the shape-recognition problem and indicates a clear advantage in reducing the redundancy involved in the matching process when morphological operations are used. Experiments show that a large amount of computing time is saved as a consequence of this theorem. This theorem also offers advantages when performing automated shape recognition on images acquired in a noisy environment. The second theorem suggests that edges of shapes can be used as a structuring element, and all possible outcomes due to noisy environments need to be exhausted