Model-Based Shape Recognition Using Recursive Mathematical Morphology

This paper introduces a size invariant method to recognize two-dimensional binary shapes using the recursive erosion transform. Using recursive morphology with multiple structuring elements, the method takes constant time per pixel regardless of the scale of the shape model, and also works on noisy images without requiring noise removal. Results from experiments on 100 noisy images show the methodology is able to detect every shape model's scale and position with 13 false alarms and five misdetections out of 254 total translated and scaled models. 1. Introduction The ultimate goal of binary shape recognition is to imitate the human ability to recognize a variety of different shapes in an image. A majority of the algorithms fall under the areas of boundary [2], feature [1], parts [6], and skeleton representations [7]. Many of the algorithms fail with the introduction of noise. Others are very complex, requiring large amounts of memory or processing time. The algorithm in this paper wor..