In early stages of vision, the images are processed to generate "maps" or point-by-point distributions of values of various quantities including the edge elements, fields of local motion, depth maps and color constancy, etc. These features are then refined and processed in visual cortex. The next stage is recognition which also leads to simple control of behaviors such as steering and obstacle avoidance, etc. In this paper we present a system for object shape recognition that utilizes the features extracted by use of human vision model. The first block of the system performs processing analogous to that in retina for edge feature extraction. The second block represents the processing in visual cortex, where features are refined and combined to form a stimulus to be presented to the recognition model. We use the normalized distances of the edge pixels from the mean to form a feature vector. The next block that accomplishes the task of recognition consists of a counterpropagation neural network model. We use gray scale images of 3D objects to train and test the performance of the system. The experiments show that the system can recognize the objects with some variations in rotation, scaling and translation.
In this paper, we describe a novel use of neural networks for extracting three-dimensional shape of the objects based on image focus. The conventional shape from focus methods are based on piece-wise constant, or piece-wise planar approximation of the focused image surface (FIS) of the object, so they fail to provide accurate shape estimation for objects with complex geometry. The proposed scheme is based on representation of three-dimensional shape of FIS in a window in terms of the neural network weights. The neural network is trained to learn the shape of the FIS that maximizes the focus measure. The SFF problem has thus been converted to an ordinary optimization problem in which a criterion function (focus measure) is to be optimized (maximized) with respect to the network weights. Gradient accent method has been used to optimize the focus measure over the three-dimensional FIS. Experiments were conducted on three different types of objects to compare the performance of the proposed algorithm with that of traditional SFF methods. Experimental results demonstrate that the method of SFF using neural networks provides more accurate depth estimates than those by the traditional methods.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.