FUZZY PYRAMID-BASED INVARIANT OBJECT RECOGNITION

A new fuzzy-decision-based invariant pattern recognition method for ob ject recognition is presented. Blending the well-known image pyramid d ata structure with fuzzy mathematics, the new method sets out to show how fuzzy concepts, such as membership grade, are used in fuzzifying t he features and building up a fuzzy feature pyramid. This is supported by a new segmentation technique using annular and sector windows insp ired by the human visual system. A fuzzy pyramid technique is then nat urally introduced to make the recognition decision. This new fuzzy dec ision approach is shown to have all the essential invariant properties and robustness against noise and uncertainty. The recognition system was applied to the problem of tool recognition and good results were o btained. A comparative study reveals many important advantages of our method over other techniques.