Region Detection and Matching for Object Recognition?

Detecting regions is important to provide semantically meaningful spatial cues in images. Matching establishes similarity between visual entities, which is crucial for recognition. My thesis starts by detecting regions in both local and object level. Then, I leverage color intensity cues of the detected regions to improve image matching for the ultimate goal of object recognition. More specifically, my thesis considers four key questions: 1) How can I extract distinctively-shaped local regions that also ensure repeatability for robust matching? 2) How can object-level shape inform bottom-up image segmentation? 3) How should the spatial layout imposed by segmented regions influence image matching for exemplar-based recognition? And 4) How can I exploit regions to improve the accuracy and speed of dense image matching? I propose an adaptive color quantization scheme to obtain a coarse image representation. The tiny regions are combined based on color information. The proposed energy transform function using extracted color map is used as a criterion for image segmentation. The motivation of the proposed method is to obtain the similar and significant objects in different images. I propose Kernel based fuzzy C-means Algorithm on color Quantized images using bacteria foraging Technique.