SHAPE-RECOGNITION METHOD USING MORPHOLOGICAL HIT-OR-MISS TRANSFORM

We present a new shape recognition algorithm for binary images based o n the morphological approach. The standard algorithms based on the mor phological hit-or-miss transform use block structure patterns, but in many practical situations, this may cause problems because the size of the object is unknown. In the proposed method, we match the corners o f the object instead of the block structure pattern. Because most obje cts have different structure elements for the corners, our method give s a more reasonable approach and the size of the object plays a less s ignificant role in our recognition algorithm than in the standard algo rithms. Our method can be easily adapted to recognize the features of different types of objects.