The Link Between Image Segmentation and Image Recognition

A long standing debate in computer vision community concerns the link between segmentation and recognition. The question I am trying to answer here is, Does image segmentation as a preprocessing step help image recognition? In spite of a plethora of the literature to the contrary, some authors have suggested that recognition driven by high quality segmentation is the most promising approach in image recognition because the recognition system will see only the relevant features on the object and not see redundant features outside the object (Malisiewicz and Efros 2007; Rabinovich, Vedaldi, and Belongie 2007). This thesis explores the following question: If segmentation precedes recognition, and segments are directly fed to the recognition engine, will it help the recognition machinery? Another question I am trying to address in this thesis is of scalability of recognition systems. Any computer vision system, concept or an algorithm, without exception, if it is to stand the test of time, will have to address the issue of scalability. ii ACKNOWLEDGEMENTS Thanks to Prof. Melanie Mitchell for her patience, advising and support during the course of my research in the Learning and Adaptive Systems lab. Her comments and advice were extremely useful in shaping this thesis. Thanks to Dr. Bart Massey and Dr. Feng Liu for being the members of my committee and for providing invaluable support whenever necessary. Thanks to Mick Thomure for his HMAX implementation code and for his assistance in helping me conduct HMAX related experiments. Rabinovich, Google, for their stability based segmentation code. Thanks to Chris Goughnour, Math department, PSU for his exceptional system administration skills and the discussions that were very useful. Thanks to Tomasz Malisiewicz, MIT for his useful advice at the critical moments.