We describe hardware that has been built to compress video in real time using full-search vector quantization (VQ). This architecture implements a differential-vector-quantization (DVQ) algorithm which features entrop...
详细信息
ISBN:
(纸本)0819415472
We describe hardware that has been built to compress video in real time using full-search vector quantization (VQ). This architecture implements a differential-vector-quantization (DVQ) algorithm which features entropy-biased codebooks designed using an artificialneural network. A special-purpose digital associative memory, the VAMPIRE chip, performs the VQ processing. We describe the DVQ algorithm, its adaptations for sampled NTSC composite- color video, and details of its hardware implementation. We conclude by presenting results drawn from real-time operation of the DVQ hardware.
artificialneuralnetworks are an interesting solution for several real-time applications in the area of signal and imageprocessing, in particular since recent advances in VLSI integration technologies allow for effi...
详细信息
ISBN:
(纸本)0819416207
artificialneuralnetworks are an interesting solution for several real-time applications in the area of signal and imageprocessing, in particular since recent advances in VLSI integration technologies allow for efficient hardware realizations. The use of dedicated circuits implementing the neuralnetworks in mission-critical applications requires a high level of protection with respect to errors due to faults to guarantee output credibility and system availability. In this paper, the problem of concurrent error detection in dedicated neuralnetworks is discussed by adopting an algorithm-based approach to check the inner product, i.e., the most of the computation performed in the neural network. Effectiveness and efficiency of this technique is shown and evaluated for the widely-used classes of neural paradigms.
This paper presents an edge detection algorithm using Hopfield neural network. This algorithm brings up a new concept which is different from those conventional differentiation operators, such as Sobel and Laplacian. ...
详细信息
ISBN:
(纸本)0819415472
This paper presents an edge detection algorithm using Hopfield neural network. This algorithm brings up a new concept which is different from those conventional differentiation operators, such as Sobel and Laplacian. In this algorithm, an image is considered a dynamic system which is completely depicted by an energy function. In other words, an image is described by a set of interconnected neurons. Every pixel in the image is represented by a neuron which is connected to all other neurons but not to itself. The weight of connection between two neurons is described as being a function of contrast of gray-level values and the distance between pixels. The initial state of each neuron represents the normalized gray-level value of the corresponding pixel in the original image. As a result of Hopfield network analysis, output of neurons is modified until the convergence. Even though the outputs are analog, they are close to zero in all regions except edges where the corresponding neurons have near 1.0 output values. A robust threshold on the output level of the converged network can be easily set up at 0.5 level to extract edges. The experimental results are presented to show the effectiveness and capability of this algorithm.
The utility and robustness of wavelet features is demonstrated through three practical case studies of detecting objects in multispectral electro-optical imagery, sidescan sonar imagery, and acoustic backscatter. Atte...
详细信息
The utility and robustness of wavelet features is demonstrated through three practical case studies of detecting objects in multispectral electro-optical imagery, sidescan sonar imagery, and acoustic backscatter. Attention is given to choosing proper waveforms for particular applications. Using artificialneuralnetworks (ANNs), evidence is fused from multiple-waveform types that detect local features. The wavelet waveforms and their dilation and shift parameters are adaptively computed with ANNs to maximize classification accuracy. Emphasis is placed on the acoustic backscatter case study, involving detecting a metallic man-made object from natural and synthetic specular clutter with reverberation noise. The synthetic clutter is shown to be a good model for the natural clutter, which appears promising for avoiding huge data collection efforts for natural clutter and for better delineating the classification boundary. The classifier computes the locations, sizes, and weights of Gaussian patches in time-scale space that contain the most discriminatory information. This new approach is shown to give higher classification rates than an ANN with commonly used power spectral features. The new approach also reduces the number of free parameters in the classifier based on all wavelet features, which leads to simpler implementation for applications and to potentially better generalization to test data.
An intelligent artificial vision system is developed which employs biologically inspired techniques for imageprocessing and an artificialneural network for object recognition. Particular emphasis is placed on the id...
An intelligent artificial vision system is developed which employs biologically inspired techniques for imageprocessing and an artificialneural network for object recognition. Particular emphasis is placed on the identification and classification of objects and visual features in manufacturing environments. Past and current research into the physiological structure and function of the mammalian vision system are reviewed, and relationships between this research and neural-network based models of visual processing are developed. The psychological research on the subject of human visual cognition is also reviewed, with the goal of shedding some light on the processes that humans use to identify and classify features and objects. Several vision system models are also reviewed, with emphasis on recently developed models based on artificialneuralnetworks. A new neural network based vision model is developed based on this research, and this model is implemented as part of an artificial vision system. The system is designed to be robust, practical, and fast. The performance of the system is evaluated on a variety of objects. The ability of neuralnetworks to learn is exploited, with the emphasis being placed on learning from examples and experience rather than on programming based on a priori knowledge or object models. The system is shown to be capable of learning and later recognizing two-dimensional and three-dimensional objects under varying conditions. Potential applications for this system include the sorting of three-dimensional manufactured objects and the identification and classification of surface defects in manufactured materials.
Analog VLSI Implementation of artificialneuralnetworks for vision applications is studied in this paper. A locally connected, regular structure for 2D convolution is proposed for high speed imageprocessing. First, ...
详细信息
ISBN:
(纸本)0819415472
Analog VLSI Implementation of artificialneuralnetworks for vision applications is studied in this paper. A locally connected, regular structure for 2D convolution is proposed for high speed imageprocessing. First, a mathematical formulation is given to map the convolution to analog computing domain. Then a system level design is performed together with the design and the testing of the basic building blocks. Experiments using real laboratory images are conducted.
An intelligent artificial vision system is developed which employs biologically inspired techniques for imageprocessing and an artificialneural network for object recognition. Particular emphasis is placed on the id...
An intelligent artificial vision system is developed which employs biologically inspired techniques for imageprocessing and an artificialneural network for object recognition. Particular emphasis is placed on the identification and classification of objects and visual features in manufacturing environments.;Past and current research into the physiological structure and function of the mammalian vision system are reviewed, and relationships between this research and neural-network based models of visual processing are developed. The psychological research on the subject of human visual cognition is also reviewed, with the goal of shedding some light on the processes that humans use to identify and classify features and objects. Several vision system models are also reviewed, with emphasis on recently developed models based on artificialneuralnetworks.;A new neural network based vision model is developed based on this research, and this model is implemented as part of an artificial vision system. The system is designed to be robust, practical, and fast. The performance of the system is evaluated on a variety of objects. The ability of neuralnetworks to learn is exploited, with the emphasis being placed on learning from examples and experience rather than on programming based on a priori knowledge or object models. The system is shown to be capable of learning and later recognizing two-dimensional and three-dimensional objects under varying conditions. Potential applications for this system include the sorting of three-dimensional manufactured objects and the identification and classification of surface defects in manufactured materials.
This paper summarizes a research effort in finding the locations and sizes of faces in color images (photographs, video stills, etc.) if, in fact, faces are present1. Scenarios for using such a system include serving ...
详细信息
A serious degradation in detection probability of conventional Constant False Alarm Rate (CFAR) processors used in the automatic detection of radar targets results from a reduction in the number of available reference...
详细信息
ISBN:
(纸本)0819415472
A serious degradation in detection probability of conventional Constant False Alarm Rate (CFAR) processors used in the automatic detection of radar targets results from a reduction in the number of available reference cells. Several factors such as any constraints on the radar system used (in terms of resolution and sampling time), presence of interfering targets and nonstationary clutter may contribute to the reduction in the number of reference cells. This paper presents a novel neural network-based CFAR detection scheme (referred to as NN- CFAR scheme) that offers robust performance in the face of loss of reference cells. This scheme employs a multilayer feedforward neural network trained by error backpropagation approach using the optimal detector as the teacher. The excellent pattern classification capabilities of trained neuralnetworks are exploited in this application to effectively counter performance degradations due to reduced reference window sizes. In particular it is demonstrated that a neural network implementation of the CFAR detection scheme provides an efficient approach for accommodating more input parameters without increasing design complexity for countering the information loss due to reduced reference window size. Precise quantitative performance evaluation of the NN-CFAR scheme are conducted in a variety of situations that include both homogeneous and nonhomogeneous clutter backgrounds and the target detection performance is compared with that of the traditional CA-CFAR scheme to highlight the benefits.
These proceedings present the state of the art in Spanish research on pattern recognition, imageprocessing, speech recognition, and artificialneuralnetworks and applications to medicine, geology, control etc.
ISBN:
(数字)9789814533928
ISBN:
(纸本)9789810218720
These proceedings present the state of the art in Spanish research on pattern recognition, imageprocessing, speech recognition, and artificialneuralnetworks and applications to medicine, geology, control etc.
暂无评论