Unstructured Object Recognition using Morphological Learning

Defence Science Journal

S. Chandran¹  S. Kar² 

[1] Indian Institufe of Technology Bombay, Mumbai;Bhabha Atomic Research Centre, Mumbai

关键词: Object recognition;    learning algorithm;    morphological learning;    unstructured object;    gray structuring element;    geometric structure;    surface imperfections;   

DOI  :  

学科分类：社会科学、人文和艺术（综合）

来源: Defence Scientific Information & Documentation Centre

【 摘 要 】

A technique of object recognitionwhich can detect absence or presence of objects of interest withoutmaking explicit use of their underlying geometric structure is deemedsuitable for many practical applications. In this work, a method ofrecognising unstructured objects has been presented, wherein severalgray patterns are input as examples to a morphological rule-basedlearning algorithm. The output of the algorithm are the correspondinggray structuring elements capable of recognising patterns in queryimages. The learning is carried out offline before recognition of thequeries. The technique has been tested to identify fuel pellet surfaceimperfections. Robustness wrt intensity, orientation, and shapevariations of the query patterns is built into the method. Moreover,simplicity of the recognition process leading to reduced computationaltime makes the method attractive to solve many practical problems.

【 授权许可】

Unknown