Baek, Kyungim, author2007-01-032007-01-032002http://hdl.handle.net/10217/60538Understanding the mechanisms underlying visual object recognition has been an important subject in both human and machine vision since the early days of cognitive science. Current state-of-the-art machine vision systems can perform only rudimentary tasks in highly constrained situations compared to the powerful and flexible recognition abilities of the human visual system. In this work, we provide an algorithmic analysis of psychological and anatomical models of the ventral visual pathway, more specifically the pathway that is responsible for expert object recognition, using the current state of machine vision technology. As a result, we propose a biologically plausible expert object recognition system composed of a set of distinct component subsystems performing feature extraction and pattern matching. The proposed system is evaluated on four different multi-class data sets, comparing the performance of the system as a whole to the performance of its component subsystems alone. The results show that the system matches the performance of state-of-the-art machine vision techniques on uncompressed data, and performs better when the stored data is highly compressed. Our work on building an artificial vision system based on biological models and theories not only provides a baseline for building more complex, end-to-end vision systems, but also facilitates interactions between computational and biological vision studies by providing feedback to both communities.doctoral dissertationsengCopyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright.Computer visionPattern recognition systemsText