Polygonal approximation plays an important role in pattern recognition and computer vision. In this paper, a parallel method using a Competitive Hopfield Neural Network (CHNN) is proposed for polygonal approximation. ...
详细信息
Polygonal approximation plays an important role in pattern recognition and computer vision. In this paper, a parallel method using a Competitive Hopfield Neural Network (CHNN) is proposed for polygonal approximation. Based on the CHNN, the polygonal approximation is regarded as a minimization of a criterion function which is defined as the arc-to-chord deviation between the curve and the polygon. The CHNN differs from the original Hopfield network in that a competitive winner-take-all mechanism is imposed. The winner-take-all mechanism adeptly precludes the necessity of determining the values for the weighting factors in the energy function in maintaining a feasible result. The proposed method is compared to several existing methods by the approximation error norms L2 and L(infinity) with the result that promising approximation polygons are obtained.
Active contour models (snakes) are commonly used for locating the boundary of an object in computer vision applications. The minimisation procedure is the key problem to solve in the technique of active contour models...
详细信息
Active contour models (snakes) are commonly used for locating the boundary of an object in computer vision applications. The minimisation procedure is the key problem to solve in the technique of active contour models. In this paper, a minimisation method for an active contour model using Hopfield networks is proposed. Due to its network structure, it lends itself admirably to parallel implementation and is potentially faster than conventional methods. In addition, it retains the stability of the snake model and the possibility for inclusion of hard constraints. Experimental results are given to demonstrate the feasibility of the proposed method in applications of industrial pattern recognition and medical imageprocessing.
A parallel procedure for locating and representing 2D contours is discussed. At first, circular templates are used to determine the edge pixels and the dominant points with high local curvatures. Then arcs are acquire...
详细信息
A parallel procedure for locating and representing 2D contours is discussed. At first, circular templates are used to determine the edge pixels and the dominant points with high local curvatures. Then arcs are acquired from the edge pixels and the dominant points. The arcs are used to examine the validity of the dominant points and to represent the contours of surfaces. The method is mainly based on template-matching procedures and a modified Hough transform.
作者:
LAU, ASKImage Processing Group
Department of Physics and Astronomy University College London Gower St. London WC1E 6BT United Kingdom
A classification system in which both knowledge based and statistical analysis techniques are embedded is presented here. Textural features used are extracted efficiently by the CLIP4 (Cellular Logic image Processor) ...
详细信息
A classification system in which both knowledge based and statistical analysis techniques are embedded is presented here. Textural features used are extracted efficiently by the CLIP4 (Cellular Logic image Processor) machine because of its inherent parallelism.
Overall architecture of a local computer network, Star, is described. The objective is to accomplish a cost-effective system which provides multiple users a real-time service of manipulating very large volume imagery ...
详细信息
Overall architecture of a local computer network, Star, is described. The objective is to accomplish a cost-effective system which provides multiple users a real-time service of manipulating very large volume imagery information and data. Star consists of a reconfigurable communication subnet (Starnet), heterogeneous resource units, and distributed-control software entities. Architectural aspects of a fault-tolerant communication subnet, distributed database management, and a distributed scheduling strategy for configuring desirable computation topology are exploited. A model for comparing cost-effectiveness among Starnet, crossbar, and multiple buses is included. It is concluded that Starnet outperforms the other two when the number of units to be connected is larger than 64. This project serves as a research tool for using current and projected technology to innovate better schemes for parallel image processing.
A compact parallel image processing system concept has been developed. The main features of this system is the use of off-axis paraboloidal mirror segments as collimating, Fourier transforming and image reconstructing...
详细信息
A compact parallel image processing system concept has been developed. The main features of this system is the use of off-axis paraboloidal mirror segments as collimating, Fourier transforming and image reconstructing elements, and the use of a GaAs laser diode as the coherent radiation source. Preliminary experiments to demonstrate the usefulness of this system have been performed.
暂无评论