Thresholded binary networks of the discrete Hopfield-type lead to the efficient retrieval of the regularized least-squares (LS) solution in certain inverse problem formulations. Partitions of these networks are identi...
详细信息
ISBN:
(纸本)0819444081
Thresholded binary networks of the discrete Hopfield-type lead to the efficient retrieval of the regularized least-squares (LS) solution in certain inverse problem formulations. Partitions of these networks are identified based on forms of representation of the data. The objective criterion is optimized using sequential and parallel updates on these partitions. The algorithms consist of minimizing a suboptimal objective criterion in the currently active partition. Once the local minima is attained, an inactive partition is chosen to continue the minimization. This strategy is especially effective when substantial data must be processed by resources which are constrained either in space or available bandwidth.
In this paper, we discuss to develop automatic classification system for true color Leukocyte image. In view of the deficiencies of traditional combination optimization method, a new method based on genetic algorithm ...
详细信息
ISBN:
(纸本)081944815X
In this paper, we discuss to develop automatic classification system for true color Leukocyte image. In view of the deficiencies of traditional combination optimization method, a new method based on genetic algorithm is proposed. Combining the specific situation of cell classification, we made some modification. Finally neural network with error back-propagation is training using the selected feature sets. The result shows this method optimize the classification performance.
Recent developments in Pulse-Coupled neuralnetworks (PCNN) techniques provide efficiency in edge and target extraction [ 1]. The detection of targets is facilitated by PCNN multi-scale image factorization. But noise ...
详细信息
ISBN:
(纸本)0819444081
Recent developments in Pulse-Coupled neuralnetworks (PCNN) techniques provide efficiency in edge and target extraction [ 1]. The detection of targets is facilitated by PCNN multi-scale image factorization. But noise is still the enemy of PCNN. An efficient new Pulse-Coupled neuralnetworks technique has been proposed in combination with the wavelet theory. The new Pulse-Couple Neuron Network Wavelet (PCNNW) is based on multi-resolution decomposition for extracting the main features of the images by eliminating the noise. In addition, the wavelet coefficients provide the Pulse-Couple Neuron Network (PCNN) supplemental discrimination and lead to characteristic sets of numbers useful in identifying image factors of interest. The efficiency of the method has been tested and compared with other PCNN denoising methods.
This chapter discusses the application of neuralnetworks in imageprocessing. Many researchers have attempted to apply artificialneuralnetworks (ANNs) to imageprocessing problems. It is an overview of what can now...
详细信息
ISBN:
(纸本)0120147688
This chapter discusses the application of neuralnetworks in imageprocessing. Many researchers have attempted to apply artificialneuralnetworks (ANNs) to imageprocessing problems. It is an overview of what can now perhaps be called the "neural network hype" in imageprocessing. In some of these applications the most interesting aspect of ANNs, the fact that they can be trained, was not (or only partly) used. This held especially for applications to the first few tasks in the imageprocessing chain: preprocessing and feature extraction. Another advantage of ANNs often used to justify their use is the ease of hardware implementation; however, in most publications, this did not seem to be the reason for application. The experiment on supervised classification, in handwritten digit recognition, showed that ANNs are quite capable of solving difficult object recognition problems. A number of ANN architectures were trained to mimic the Kuwahara filter, a nonlinear edge-preserving smoothing filter used in preprocessing. The experiments showed that careful construction of the training set is very important. ANNs seem to be most applicable for problems requiring a nonlinear solution, for which there is a clear, unequivocal performance criterion.
The analog CMOS circuit realization of cellular neuralnetworks with transconductance elements is presented. This realization can be easily adapted to various types of applications in imageprocessing just by choosing...
详细信息
The analog CMOS circuit realization of cellular neuralnetworks with transconductance elements is presented. This realization can be easily adapted to various types of applications in imageprocessing just by choosing the appropriate transconductance parameters according to the predetermined coefficients. The effectiveness of the designed circuits for connected component detection is shown by HSPICE simulations. For ''fixed function'' cellular neural network circuits the number of transistors are reduced further by using multi-input transconductance elements.
This paper presents classification of difference image blocks between the two successive image frames for video data compression. Difference blocks are classified to several activity categories according to the image ...
详细信息
ISBN:
(纸本)0819444081
This paper presents classification of difference image blocks between the two successive image frames for video data compression. Difference blocks are classified to several activity categories according to the image activity distribution. The classification procedure goes in two steps: activity classification and distribution classification. In the activity classification, each interframe difference image block is classified into active or not-active class according to the amount of motion contained in the block. Distribution classification further classifies active image blocks to four activity categories, vertical, horizontal, diagonal, and uniform activities, based on the activity distribution measured by the edge feature vector in the discrete cosine transform domain. A multiplayer feedforward neural network, trained with a small set of sample classification data, successfully classified difference image blocks according to edge feature distribution. The classification scheme improves the performance of video compression at a cost of small increase in the overhead associated with the quantizer switching.
A neural network based image enhancement method is introduced to improve the image resolution from a sequence of low resolution image frames. Most of the existing methods reconstruct a high-resolution image from a mul...
详细信息
ISBN:
(纸本)081944815X
A neural network based image enhancement method is introduced to improve the image resolution from a sequence of low resolution image frames. Most of the existing methods reconstruct a high-resolution image from a multiple of low-resolution image frames by minimizing some established cost function using a mathematical technique. This method, however, uses an integrated recurrent neural network (IRNN) that is particularly designed to be capable of learning an optimal mapping from a multiple of low-resolution image frames to a high-resolution image through training. The IRNN consists of four feed-forward sub-networks working collectively with the ability of having a feedback of information from its output to input. As such, it is capable of both learning and searching the optimal solution in the solution space leading to high resolution images. Simulation results demonstrate that the proposed IRNN has good potential in solving image resolution enhancement problem, as it can adapt itself to the various conditions of the reconstruction problem by learning.
A controversial issue in the research of mathematics of intelligence has been that of the roles of a priori knowledge versus adaptive learning, After discussing mathematical difficulties of combining a priority with a...
详细信息
A controversial issue in the research of mathematics of intelligence has been that of the roles of a priori knowledge versus adaptive learning, After discussing mathematical difficulties of combining a priority with adaptivity encountered in the past, we introduce a concept of a model-based neural network, whose adaptive learning is based on a priori models. applications to target detection in SAR images are discussed, We briefly overview the SAR principles, derive relatively simple physics-based models of SAR signals, and describe model-based neuralnetworks that utilize these models. A number of real-world application examples are presented.
artificialneuralnetworks (ANN) are increasingly used to solve many problems related to pattern recognition and object classification. In this paper, we report on a study using artificialneuralnetworks to classify ...
详细信息
artificialneuralnetworks (ANN) are increasingly used to solve many problems related to pattern recognition and object classification. In this paper, we report on a study using artificialneuralnetworks to classify two kinds of animal fibers: merino and mohair. We have developed two different models, one extracting nine scale parameters with imageprocessing, and the other using an unsupervised artificialneural network to extract features automatically, which are determined in accordance with the complexity of the scale structure and the accuracy of the model. Although the first model can achieve higher accuracy, it requires more effort for imageprocessing and more prior knowledge, since the accuracy of the ANN largely depends on the parameters selected. The second model is more robust than the first, since only raw images are used. Because only ordinary optical images taken with a microscope are employed, we can use the approach for many textile applications without expensive equipment such as scanning electron microscopy.
暂无评论