作者：
Kurosh MadaniImage
Signals and Intelligent Systems Laboratory (LISSI / EA 3956) Val de Marne University Senart Institute of Technology Avenue Pierre Point Lieusaint France
The main goal of this paper is to present artificialneural network potential, through main ANN models and based techniques, to solve real world industrial problems dealing with imageprocessing and pattern recognitio...
详细信息
The main goal of this paper is to present artificialneural network potential, through main ANN models and based techniques, to solve real world industrial problems dealing with imageprocessing and pattern recognition fields.
applications of artificialneuralnetworks to in situ assessment of water quality are considered by means of an online optical scatter nephelometer. Light scattered by suspensions of oil in water is investigated for t...
详细信息
applications of artificialneuralnetworks to in situ assessment of water quality are considered by means of an online optical scatter nephelometer. Light scattered by suspensions of oil in water is investigated for three different oils in the concentration range 0-100 parts per million by,volume. An artificialneural network is designed to recognise the oil species and output its concentration to within an accuracy of 5.4%. applications of the technique to more general classes of suspensions are discussed.
This paper presents a new approach for extracting spatial features of images based on the theory of regionalized variables. These features can be effectively used for automatic recognition of logo images using neural ...
详细信息
ISBN:
(纸本)081944815X
This paper presents a new approach for extracting spatial features of images based on the theory of regionalized variables. These features can be effectively used for automatic recognition of logo images using neuralnetworks. Experimental results on a public-domain logo database show the effectiveness of the proposed approach.
The area of artificialneuralnetworks has recently seen an explosion of theoretical and practical results. In this paper, we present an artificialneural network that is algebraically distinct from the classical arti...
详细信息
The area of artificialneuralnetworks has recently seen an explosion of theoretical and practical results. In this paper, we present an artificialneural network that is algebraically distinct from the classical artificialneuralnetworks, and several applications which are different from the typical ones. In fact, this new class of networks, called morphology neuralnetworks, is a special case of a general theory of artificialneural nets, which includes the classical neural nets. The main difference between a classical neural net and a morphology neural net lies in the way each node algebraically combines the numerical information. Each node in a classical neural net combines information by multiplying output values and corresponding weights and summing, while in a morphology neural net, the combining operation consists of adding values and corresponding weights, and taking the maximum value. We lay a theoretical foundation for morphology neural nets, describe their roots, and give several applications in imageprocessing. In addition, theoretical results on the convergence issues for two networks are presented.
Systems for processing high resolution images need to be fast, compact, and efficient. imageprocessing systems that incorporate optics into its architecture can provide the speed and potentially the compactness to me...
详细信息
ISBN:
(纸本)081944815X
Systems for processing high resolution images need to be fast, compact, and efficient. imageprocessing systems that incorporate optics into its architecture can provide the speed and potentially the compactness to meet the demands of analyzing images. In this paper a hybrid approach to image analysis using Winner Take All neural network dynamics with optical and electronic implementation is discussed. Resulting images from the system simulations are explored for use in object and background discrimination for image segmentation tasks.
The proposed system for CT image reconstruction is structured with three layers of neurons. In our previous work, we used the resilient backpropagation(Rprop) instead of the straight, BP to modify the network weights....
详细信息
ISBN:
(纸本)0819444081
The proposed system for CT image reconstruction is structured with three layers of neurons. In our previous work, we used the resilient backpropagation(Rprop) instead of the straight, BP to modify the network weights. The basic idea is to minimize the error between the projections of the original image and of the reconstructed image. We noticed that the system performance depends oil the initial status of the network. Based on this observation, we propose a novel approach for choosing optimal values of the connection weights. The experimental results indicate that the new method can find a satisfactory solution despite that only a few projections are available.
This paper aims to exploit approximate computing units in imageprocessing systems and artificialneuralnetworks. For this purpose, a general design methodology is introduced, and approximation-oriented architectures...
详细信息
This paper aims to exploit approximate computing units in imageprocessing systems and artificialneuralnetworks. For this purpose, a general design methodology is introduced, and approximation-oriented architectures are developed for different applications. This paper proposes a method to compromise power/area efficiency of circuit-level design with accuracy supervision of system-level design. The proposed method selects approximate computational units that minimize the total computation cost, yet maintaining the ultimate performance. This is accomplished by formulating a linear programming problem, which can be solved by conventional linear programming solvers. Approximate computing units, such as multipliers, neurons, and convolution kernels, which are proposed by this paper, are suitable for power/area reduction through accuracy scaling. The formulation is demonstrated on applications in imageprocessing, digital filters, and artificialneuralnetworks. This way, the proposed technique and architectures are tested with different approximate computing units, as well as system-level requirement metrics, such as PSNR and classification performance.
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.
暂无评论