Noise is one of the main sources of quality deterioration not only for visual inspection but also in computerized processing in brain magnetic resonance (MR) image analysis such as tissue classification, segmentation ...
详细信息
Noise is one of the main sources of quality deterioration not only for visual inspection but also in computerized processing in brain magnetic resonance (MR) image analysis such as tissue classification, segmentation and registration. Accordingly, noise removal in brain MR images is important for a wide variety of subsequent processingapplications. However, most existing denoising algorithms require laborious tuning of parameters that are often sensitive to specific image features and textures. Automation of these parameters through artificial intelligence techniques will be highly beneficial. In the present study, an artificialneural network associated with image texture feature analysis is proposed to establish a predictable parameter model and automate the denoising procedure. In the proposed approach, a total of 83 image attributes were extracted based on four categories: 1) Basic image statistics. 2) Gray-level co-occurrence matrix (GLCM). 3) Gray-level run-length matrix (GLRLM) and 4) Tamura texture features. To obtain the ranking of discrimination in these texture features, a paired-samples t-test was applied to each individual image feature computed in every image. Subsequently, the sequential forward selection (SFS) method was used to select the best texture features according to the ranking of discrimination. The selected optimal features were further incorporated into a back propagation neural network to establish a predictable parameter model. A wide variety of MR images with various scenarios were adopted to evaluate the performance of the proposed framework. Experimental results indicated that this new automation system accurately predicted the bilateral filtering parameters and effectively removed the noise in a number of MR images. Comparing to the manually tuned filtering process, our approach not only produced better denoised results but also saved significant processing time.
A Tongue Imaging and Analysis System (TIAS) is being developed to acquire digital color tongue images, and to automatically classify and quantify the tongue characteristics for traditional Chinese medical examinations...
详细信息
ISBN:
(纸本)0819435805
A Tongue Imaging and Analysis System (TIAS) is being developed to acquire digital color tongue images, and to automatically classify and quantify the tongue characteristics for traditional Chinese medical examinations. An important processing step is to segment the tongue pixels into two categories, the tongue body (no coating) and the coating. In this paper, we present a two-stage clustering algorithm that combines Fuzzy Kohonen Clustering networks (FKCN) and Genetic Algorithm (GA) for the segmentation, of which the major concern is to increase the interclass distance and at the same time decrease the intraclass distance. Experimental results confirm the effectiveness of this algorithm.
Biometric systems based on one-modal biometrics are often not able to meet the desired performance requirements for large user population applications, due to problems such as noisy data, intra-class variations, restr...
详细信息
ISBN:
(纸本)9788022728560
Biometric systems based on one-modal biometrics are often not able to meet the desired performance requirements for large user population applications, due to problems such as noisy data, intra-class variations, restricted degrees of freedom, non-university, spoof attacks, and unacceptable error rates. Therefore, multimodal biometrics refers to the use of a combination of two or more biometric modalities in a single recognition or identification system. In order to ensure that the performance of multibiometric systems such as fingerprint and iris will be powerful with respect to the quality of obtained fingerprint and iris images, these images are denoised and enhanced. In this study, curvelet transform is applied biometric images for enhancement. Obtained results after applied curvelet transform is compared to the other traditional image enhancement algorithms. Features obtained from enhanced fingerprints and iris images are selected by using Genetic Algorithms because of too huge dataset. Selected features are input to artificialneuralnetworks for biometric recognition. Thus, the recognition is achieved very fast without to reduce the performance.
The proceedings contains 13 papers from the conference on applications of artificialneuralnetworks in imageprocessing Vii. The topics discussed include: pornographic image detection with Gabor filters;classificatio...
详细信息
The proceedings contains 13 papers from the conference on applications of artificialneuralnetworks in imageprocessing Vii. The topics discussed include: pornographic image detection with Gabor filters;classification of interframe difference image blocks for video compression;configuring artificialneuralnetworks to implement function optimization;fusion of ATR classifiers and dual-band FLIR fusion for target detection.
This paper describes the design of an undersea mine detection system and compares the performance of various neural network models for classification of features extracted from side-scan sonar images. Techniques for r...
详细信息
ISBN:
(纸本)0819415472
This paper describes the design of an undersea mine detection system and compares the performance of various neural network models for classification of features extracted from side-scan sonar images. Techniques for region of interest and statistical feature extraction are described. Subsequent feature analysis verifies the need for neural network processing. Several different neural and conventional pattern classifiers are compared including: k-Nearest Neighbors, Backprop, Quickprop, and LVQ. Results using the Naval image Database from Coastal Systems Station (Panama City, FL) indicate neuralnetworks have consistently superior performance over conventional classifiers. Concepts for further performance improvements are also discussed including: alternative image preprocessing and classifier fusion.
The traditional artificialneuralnetworks encode information through the spike firing rate. Spiking neuralnetworks fall into the third-generation artificialneural network models, which use the precisely timed spike...
详细信息
The traditional artificialneuralnetworks encode information through the spike firing rate. Spiking neuralnetworks fall into the third-generation artificialneural network models, which use the precisely timed spike trains to encode neural information. The computational models can accurately simulate the neural network activities of human brain, and provide powerful capabilities of signal processing to solve the complex problem. In this paper, we propose a supervised learning algorithm for single-layer spiking neuralnetworks based on the spike train kernel function, which can implement the complex spatio-temporal pattern learning of spike trains. Furthermore, a pattern classifier based on single-layer spiking neuralnetworks is constructed for image recognition problem. We test the learning performance of the proposed algorithm by the image classification task on the LabelMe dataset. The experimental results show that the proposed algorithm has got good image classification accuracy for the test dataset, and the different sizes of receptive fields influence classification accuracies significantly.
UAVs offer many advantages over manned vehicles and their application area expands in time passes. Particularly, interest in UAVs with rotary wing types is increasing. Increasing interest in these vehicles has spawned...
详细信息
ISBN:
(纸本)9781665436496
UAVs offer many advantages over manned vehicles and their application area expands in time passes. Particularly, interest in UAVs with rotary wing types is increasing. Increasing interest in these vehicles has spawned many different controller designs. In this study, estimating the pose of the vehicle according to the image features with the help of a single camera mounted on the quadrotor and then position-based visual servoing, a technique that allows the vehicle to be controlled by using the image features, was used. In this study position-based visual servoing (PBVS);3D parameter estimates of the vehicle pose were implemented with artificialneuralnetworks.
Convolution neuralnetworks (CNN) are artificialnetworks able to extract features from large dataset by spatial filtering. Here we propose an optical coprocessor able to perform large image filtering and convolutions...
详细信息
ISBN:
(纸本)9781728106021
Convolution neuralnetworks (CNN) are artificialnetworks able to extract features from large dataset by spatial filtering. Here we propose an optical coprocessor able to perform large image filtering and convolutions, outperforming current architectures.
This paper presents entropy constrained fuzzy clustering and learning vector quantization algorithms and their application in image compression, Entropy constrained fuzzy clustering (ECFC) algorithms were developed by...
详细信息
ISBN:
(纸本)0819424412
This paper presents entropy constrained fuzzy clustering and learning vector quantization algorithms and their application in image compression, Entropy constrained fuzzy clustering (ECFC) algorithms were developed by minimizing an objective function incorporating the fuzzy partition entropy and the average distortion between the feature vectors, which represent the image data, and the prototypes, which represent the codevectors or codewords, The reformulation of fuzzy c-means (FCM) algorithms provided the basis for the development of fuzzy learning vector quantization (FLVQ) algorithms and essentially established a link between clustering and learning vector quantization. Minimization of the reformulation function that corresponds to ECFC algorithms using gradient descent results in entropy constrained learning vector quantization (ECLVQ) algorithms, These algorithms allow the gradual transition from a maximally fuzzy partition to a nearly crisp partition of the feature vectors during the learning process. This paper presents two alternative implementations of the proposed algorithms, which differ in terms of the strategy employed for updating the prototypes during learning, The proposed algorithms are tested and evaluated on the design of codebooks used for image data compression.
The fractal transform is a recently developed tool for image analysis and pattern recognition. Problems relating to pixel based image resolution are highlighted. The fractal transform is outlined and shown to be a sol...
详细信息
ISBN:
(纸本)0819418455
The fractal transform is a recently developed tool for image analysis and pattern recognition. Problems relating to pixel based image resolution are highlighted. The fractal transform is outlined and shown to be a solution to pixel based image resolution related problems. MatchMaker, a technique based on fractal transform analysis is analyzed and its ability to find objects in complex scenes is confirmed. A new neural network paradigm, called the fractal transform network, is described. Built from neural network elements commonly described in the classic neural network literature, it is shown that this new paradigm can implement the MatchMaker technique and other fractal transform processes as highly parallel networks.
暂无评论