Use of the Magneto-Optic Spatial Light Modulator (MOSLM) in the filter plane of optical correlators is attractive because it is capable of high frame rates. This has led to the design of several different types of Bin...
详细信息
We describe a high-speed acousto-optic Hough-transform mapping modulator. This mapping modulator generates any theta slice of the straight line Hough-transform and one-dimensional slices of generalized Hough transform...
详细信息
We describe a high-speed acousto-optic Hough-transform mapping modulator. This mapping modulator generates any theta slice of the straight line Hough-transform and one-dimensional slices of generalized Hough transforms (e.g., for circles and ellipses). We derive the mapping functions for the acousto-optic modulator for both circle and ellipse Hough transforms and show simulations of generalized Hough transforms using both functions. We also describe how the mapping modulators can compute Hough transforms for nonanalytically describable inputs.
The original minimum average correlation energy (MACE) filter is addressed by using a new database (strategic relocatable objects, missile launchers) and including noise performance, depression angle, and resolution e...
详细信息
The original minimum average correlation energy (MACE) filter is addressed by using a new database (strategic relocatable objects, missile launchers) and including noise performance, depression angle, and resolution effects on the number of training set images that are required. Major attention is given to our new MACE filter algorithms for distortion-invariant pattern recognition: shifted-MACE filters (to suppress large false correlation peaks), minimum variance-MACE filters (for improved noise performance), multiple symbolic encoded filters (to reduce the effect of false correlation peaks), and Gaussian-MACE filters (to improve noise performance and intraclass recognition and reduce the training set size).
A neural network pattern classifier is presented. Its decision boundaries are formed from segments of conic sections which allows it to achieve improved performance over piecewise linear neural network classifiers, su...
详细信息
There is much present work concerning morphological image processing, both binary and gray scale. Almost all implementations to date are performed electronically on standard computers, specialized processors, or speci...
详细信息
作者：
Gasasene, DavidCarnegie Mellon University
Center for Excellence in Optical Data Processing Department of Electrical and Compute Engineering PittsburghPA15213 United States
Various error sources (including analog accuracy, nonlinearities, and noise) are present in all neural nets. We consido- their effects in training and testing on two diffirent pattern recognition neural nets. We show ...
详细信息
We discuss how one optical processor (a correlator) can be used for all levels of scene analysis (low, medium, and high-level computer vision). This is achieved by the use of different filter functions for the differe...
详细信息
作者：
Casasent, DavidCarnegie Mellon University
Center for Excellence in Optical Data Processing Department of Electrical and Computer Engineering PittsburghPA15213 United States
Several recent advances are described that use neural net methods to produce the higher-order decision surfaces required for difficult pattern recognition discrimination problems. Work at Carnegie Mellon University is...
详细信息
作者：
Casasent, DavidCarnegie Mellon University
Center for Excellence in Optical Data Processing Department of Electrical and Computer Engineering PittsburghPA15213 United States
optical processors can perform the required operations for the various levels of a hierarchical/inference computer vision system for scene analysis (detection, enhancement, recognition, feature extraction, and classif...
详细信息
A multifunctional optical imagc processor capable of morphological,feature extraction and correlation operations for low,medium and high-level computervision is described,A morphological processor achieves detection a...
详细信息
A multifunctional optical imagc processor capable of morphological,feature extraction and correlation operations for low,medium and high-level computervision is described,A morphological processor achieves detection and image enhance-ment. A correlator achieves recognition(and can also achieve detection and identi-fication). A feature extractor is useful for identification in large class problemsin scene analys *** optical processors can be realized on the same programmableoptical processor.
暂无评论