A biologically plausible architecture for shape recognition

by (Sanketh Vittaldas), 1982- Shetty

SHETTY, SANKETH V. A Biologically Plausible Architecture for Shape Recognition. (Under the direction of Professor Wesley E. Snyder). This thesis develops an algorithm for shape representation and matching. The algorithm is an object centered, boundary-based method for shape recognition. Global features of the shape are utilized to define a frame of reference relative to which local shape features are characterized. The curvature of the boundary at a point is the local feature used. Curvature is computed by the Digital Straight Segments algorithm. Matching is done using the process of evidence accumulation similar in approach to the Generalized Hough Transform. The algorithm is tested for invariance to similarity transforms. Its robustness to noise and blurring is also tested. A multi-layer, feed-forward neural network architecture that implements the algorithm is proposed. A Biologically Plausible Architecture for Shape Recognition by Sanketh V. Shetty A thesis submitted to the Graduate Faculty of North Carolina State University in partial fulfillment of the requirements for the Degree of Master of Science Electrical Engineering Raleigh 2006 Approved By: Dr. Griff Bilbro Dr. David S Lalush Dr. Wesley E. Snyder Chair of Advisory Committee Dr. H Joel Trussell To Mom and Dad . . . ii iii Biography Sanketh Shetty was born in the south Indian port city of Mangalore on the 24th of August 1982. He did his primary schooling at Bishop Cottons Boys School, Bangalore and St.Dominics Savio College, Lucknow. He attended middle school at La Martiniere Boys Junior College, Lucknow. He completed his higher secondary education at DAV Boys Senior Secondary School in Chennai. In 2000, he enrolled into the Bachelor of Engineering program at Birla Institute of Technology and Science (BITS), Pilani, India. There he majored in Electrical and Electronics Engineering with an emphasis in Robotics. In his senior year he completed a six month internship at Hewlett Packard Laboratories in Bangalore, working in Speech Recognition. In Spring 2004 he graduated with distinction and the Fall of the same year he joined the Master’s program in Electrical and Computer Engineering at North Carolina State University, Raleigh. Since the summer of 2005 he has been a member of the Image Analysis Laboratory and worked under the guidance of Dr.Wesley Snyder. He has been accepted into the PhD program at the Department of Electrical and Computer Engineering, University of Illinois, Urbana-Champaign. He plans to enroll there in the fall semester of 2006. Sanketh’s interests are in Computer Vision, Visual Neuroscience, Cognitive Science and Artificial Intelligence. iv