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.
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.
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.
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 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.
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.
In this paper a learning algorithm of synergetic neural network based on selective attention parameters is proposed. According to the mechanism of the Human Visual System (HVS), the weight matrix of synergetic neural ...
详细信息
ISBN:
(纸本)081944815X
In this paper a learning algorithm of synergetic neural network based on selective attention parameters is proposed. According to the mechanism of the Human Visual System (HVS), the weight matrix of synergetic neural network can be obtained by multiplying the prototype matrix by selective attention parameters. Two selective attention models based on the human visual system are put forward in this paper. The comparative experiments between the traditional algorithm SCAP and the new method we proposed in the application of recognising the real gray images of numeric and alphabetic characters are done. And the results show that our method can improve the synergetic neural network's recognition performance and be more suitable to human visual system.
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.
A feedback neural network (FBNN) can be triggered by ANY input analog pattern vector. Then depending on the domain-of-convergence (or domain-of-attraction in the languages of nonlinear systems) that this triggering pa...
详细信息
ISBN:
(纸本)081944815X
A feedback neural network (FBNN) can be triggered by ANY input analog pattern vector. Then depending on the domain-of-convergence (or domain-of-attraction in the languages of nonlinear systems) that this triggering pattern falls into, the FBNN will go around and around the feedback loop and finally settle down at one of the few designated patterns associatively stored in the connection matrix. This recalled (or the settle-down) pattern will stay at the output even when the input triggering pattern is removed because of the self-sustained feedback action of the FBNN. The triggering pattern does not have to be the same as the stored pattern that it recalls. It can be a noise-affected pattern. But as long as it falls within the designated noise range (or the designated domain of convergence) of an accurately stored pattern, that accurate pattern will be recalled and permanently appear at the output even when the input triggering is removed.
暂无评论