Unstructured Object Recognition using Morphological Learning
S. Kar, Sharat Chandran · Defence Science Journal · 2002
A techniaue of obiect recognition which can detect absence or presence of obiects of interest without making explicit use of theirunde&ing geometric struchlre is deemed suitable formany practical applications. In this work. a method of recoenisinz unstructured obiects bas been ~resented. wherein several arav-. patterns are input as examples to amorpkological rule-based learning algoiithm. The output of the algorithm are the corresponding &!ray structuring elements capable of recogniiing patterns in query images. The learning is carried out offline before recognition of the aueries. The technique has been tested to identify fuel peiet surface imperfections. ~obustnkss wrt intensky, orientation, andshape variations of the q u e j patterns is built into the method. Moreover, simplicity of the recognition process leading to reduced computational time makes the method attractive to solve many practical problems.