检索结果-内蒙古大学图书馆

Texture segmentation in the joint photographic expert group 2000 domain

IET image processing 2011年第6期5卷 554-559页

作者： Hsin, H. -C. Natl United Univ Dept Comp Sci & Informat Engn Taipei Taiwan

image segmentation is an important task in many image processing systems. For efficient transmission over a band-limited channel, original images are often compressed before being stored in databases. In order to avoid the burden of decompressing an image, it is desirable to extract features directly from a code stream. This approach saves computational time significantly. The look up table used for the MQ coder defined in joint photographic expert group 2000 (JPEG2000) called the MQ table provides probability models for bit-plane coding of wavelet coefficients, the wavelet histogram information can be obtained directly from a JPEG2000 code stream. Thus, the MQ feature based on the MQ table is proposed to segment an image in the JPEG2000 domain directly. Experimental results of clustering these features by using the simple K-means algorithm show the potential of MQ feature.

关键词： texture segmentation band-limited channel data compression image processing systems code stream computer vision and image processing techniques image and video coding image coding MQ feature image segmentation pattern clustering wavelet coefficients feature extraction joint photographic expert group 2000 domain image compression image texture Computational complexity computational complexity /(-means algorithm computational time JPEG2000 code stream bit-plane coding wavelet histogram information

来源：评论

学校读者我要写书评

暂无评论

image denoising using 2-D separable oversampled DFT modulated filter banks

引用

IET image processing 2009年第3期3卷 163-173页

作者： Shui, P. -L. Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Peoples R China

The direction-frequency selectivity of two-dimensional (2-D) separable oversampled discrete Fourier transform (DFT) modulated filter banks, showing that such 2-D filter banks can provide. ne frequency tiling and efficient image representations with direction-frequency selectivity, is analysed. Moreover, the doubly local Wiener filtering is extended to the case using two 2-D separable oversampled DFT modulated filter banks, where the empirical subband energy distributions of the image are estimated by the two sets of directional windows matching the direction-frequency selectivity of the subband filters. The proposed algorithm is of low computational complexity and exhibits a great capability to preserve inhomogeneous textures, owing to the fact that 2-D separable DFT modulated bases are suited to represent oscillating patterns in images. The experimental results show that the proposed denoising algorithm is competitive with the existing algorithms with comparable computational complexity. Particularly, for images with abundant inhomogenous texture, it gives larger output peak signal-to-noise ratios (PSNRs) and achieves better visual effect in texture regions of images.

关键词： image representation direction-frequency selectivity scheme Filtering methods in signal processing image sampling computer vision and image processing techniques discrete Fourier transforms channel bank filters Optical, image and video signal processing Integral transforms Wiener filters directional window matching method discrete Fourier transform image texture 2D separable oversampled DFT modulated filter bank image denoising computational complexity Wiener filtering subband energy distribution scheme

来源：评论

学校读者我要写书评

暂无评论

Maximum likelihood approach to image texture and acoustic signal classification

引用

IEE PROCEEDINGS-vision image AND SIGNAL processing 1999年第1期146卷 34-39页

作者： Thyagarajan, KS Nguyen, T Persons, CE San Diego State Univ Dept Elect & Comp Engn San Diego CA 92182 USA RDTE NCCOSC San Diego CA 92152 USA

The authors describe a method of classifying natural textures based on the maximum likelihood parameter estimation technique. The novelty of the technique lies in the use of textural features that are derived from the subbands of a wavelet transformed image via the co-occurrence matrices. A maximum likelihood classifier is designed using a set of training texture samples. Ten different Brodotz textures have been classified using this procedure with an average classification accuracy of 99.7%. The main emphasis is to apply this technique to the classification of underwater acoustic signals. A time-frequency plot is obtained for each segment of the acoustic signal and then converted to an intensity pattern. The textural classification scheme is then applied to the intensity patterns of the acoustic signals. Eight different underwater acoustic signals have been classified by this procedure with an average accuracy of 99.99%.

关键词： Sonar and acoustic radar image classification Acoustic signal processing Simulation, modelling and identification maximum likelihood estimation transform coding acoustic signal processing average accuracy time-frequency plot intensity patterns maximum likelihood parameter estimation co-occurrence matrices training texture samples image representation image resolution computer vision and image processing techniques Brodotz textures multiresolution representation acoustic signal classification image coding underwater sound average classification accuracy subbands Integral transforms in numerical analysis Underwater sound textural features image texture image and video coding wavelet transformed image underwater acoustic signals image texture classification wavelet transforms maximum likelihood classifier wavelet transform

来源：评论

学校读者我要写书评

暂无评论

An image layered scrambling encryption algorithm based on a novel discrete chaotic map

引用

IET image processing 2023年第2期17卷 518-532页

作者： Tang, Jianeng Zhang, Zezong Chen, Peiyang Zhang, Feng Ni, Hui Huang, Zhongming Huaqiao Univ Coll Engn Quanzhou Peoples R China Huaqiao Univ Coll Informat Sci & Engn Xiamen Peoples R China Fujian MM Elect Co Ltd Quanzhou Peoples R China

At present, the image encryption algorithm based on the bit-plane has the problem that the encryption speed and the encryption effect cannot be well balanced. To address the problem, an image layered scrambling encryption algorithm is proposed in this paper. First, a new one-dimensional Cosine Logistic compound chaotic map (1DCLC) is proposed. Several characteristics of the new chaotic map are analyzed by using various measures, such as bifurcation diagram, Lyapunov exponent, sample entropy etc. And the results show that the novel chaotic map has a better chaotic performance. Second, based on the chaotic map, an image encryption algorithm is proposed. The algorithm first performs an XOR encryption operation on the image. Second, the layered scrambling is applied to the XOR encrypted image. Then the layered and scrambled image is recombined for the second XOR encryption operation. In particular, in the layered scrambling, not only can the position of the pixel be changed but also the value of the pixel can be modified, which improves the security of the algorithm. In addition, in order to defend against various plaintext attacks and increase the security of the overall algorithm, the Hash function is introduced to update the key of the proposed algorithm. Finally, the original algorithm is improved and the improved algorithm's ability to resist differential attacks is analyzed. The experimental simulation and security test results show that the proposed encryption algorithm has a comparable encryption effect and a faster encryption speed.

关键词： XOR encryption operation improved algorithm Cryptography image layered scrambling novel chaotic map chaotic performance image encryption algorithm Optical, image and video signal processing faster encryption speed computer vision and image processing techniques chaos image processing XOR encrypted image Data security entropy one-dimensional Cosine Logistic compound chaotic map novel discrete chaotic map comparable encryption effect bifurcation cryptography layered scrambled image

来源：评论

学校读者我要写书评

暂无评论

A modified 3D EfficientNet for the classification of Alzheimer's disease using structural magnetic resonance images

引用

IET image processing 2023年第1期17卷 77-87页

作者： Zheng, Bowen Gao, Ang Huang, Xiaona Li, Yuhan Liang, Dong Long, Xiaojing Chinese Acad Sci Shenzhen Inst Adv Technol Res Ctr Med AI Shenzhen Peoples R China Univ Chinese Acad Sci Beijing Peoples R China

Structural magnetic resonance imaging (MRI) provides useful information for biomarker exploration and intelligent classification of Alzheimer's disease (AD). Machine learning and deep learning methods have been used in feature extraction and computer-aided diagnosis or prediction of AD. In this research, a new deep learning model is developed to detect or predict AD in an effective manner. A modified 3D EfficientNet with a sequentially connected 3D mobile inverted bottleneck convolution (MBConv) block is proposed to explore the multiscale characteristics of brain MR images for AD classification. The 3D MBConv block consists of depthwise convolution and a squeeze-and-excitation module to transform the input features into more compact features with fewer parameters than those in standard convolution. The proposed method was evaluated considering four classification tasks: (1) NC versus AD, (2) NC versus all MCI, (3) NC versus pMCI, and (4) sMCI versus pMCI. The proposed model achieved accuracies of 95.00%, 86.67%, and 83.33% for the classification of NC versus AD, NC versus pMCI, and sMCI versus pMCI, respectively, and exhibited a high performance in comparison with the classical networks and several existing methods. Efficient deep learning networks are powerful tools for the early diagnosis and prediction of AD.

关键词： biomarker exploration Biology and medical computing feature extraction structural magnetic resonance imaging brain MR images diseases image classification AD classification biomedical MRI Medical magnetic resonance imaging and spectroscopy compact features deep learning networks Neural nets Alzheimer's disease standard convolution mild cognitive impairment computer vision and image processing techniques Biomedical magnetic resonance imaging and spectroscopy convolutional neural nets depthwise convolution structural magnetic resonance images machine learning intelligent classification deep learning (artificial intelligence) image recognition classification tasks sequentially connected 3D mobile inverted bottleneck convolution block early diagnosis computer-aided diagnosis brain Patient diagnostic methods and instrumentation 3D MBConv block squeeze-and-excitation module medical image processing modified 3D EfficientNet

来源：评论

学校读者我要写书评

暂无评论

Hard exudate segmentation in retinal image with attention mechanism

引用

IET image processing 2021年第3期15卷 587-597页

作者： Si, Ze Fu, Dongmei Liu, Yang Huang, Zhicheng Univ Sci & Technol Beijing Sch Automat & Elect Engn 30 Xueyuan Rd Beijing Peoples R China Univ Sci & Technol Beijing Beijing Engn Res Ctr Ind Spectrum Imaging Beijing Peoples R China

Diabetic retinopathy (DR) is the main reason that causes preventable blindness. Hard exudate is one of the earliest signs of diabetic retinopathy. Precise detection of hard exudate is helpful for the early diagnosis of diabetic retinopathy. Fully convolutional network (FCN) shows great performance on hard exudate segmentation task. However, there are limitations for fully convolutional network to build long-range dependencies in different regions of the image. Convolution operator extract features in local area, segmentation results based on local features are likely to be wrong in some cases. Another channel attention method was proposed, and two different attention modules are used in the segmentation model. In this way, long-range dependencies across different image regions are built efficiently in different stages of feature extraction. In addition, a new loss function is designed to deal with the data imbalance problem in hard exudate segmentation task. The proposed method was evaluated by two public datasets, and the comparative experiments show the effectiveness of the proposed method.

关键词： Patient diagnostic methods and instrumentation Optical, image and video signal processing computer vision and image processing techniques Biology and medical computing

来源：评论

学校读者我要写书评

暂无评论

Minimum-entropy phase adjustment for ISAR

引用

IEE PROCEEDINGS-RADAR SONAR AND NAVIGATION 2004年第4期151卷 203-209页

作者： Wang, J Liu, X Zhou, Z Shanghai Jiao Tong Univ Shanghai 200030 Peoples R China

A new technique is developed for phase adjustment in ISAR imaging. The adjustment phase is found by iteratively solving an equation, which is derived by minimising the entropy of the image. This technique can be used to estimate adjustment phases of any form. Moreover, the optimisation method used in this technique is computationally more efficient than trial-and-error methods.

关键词： minimum-entropy optimisation Radar theory Fourier transforms Optimisation techniques translation compensation Fourier transform optimisation method computer vision and image processing techniques Radar equipment, systems and applications Interpolation and function approximation (numerical analysis) ISAR imaging Integral transforms in numerical analysis Optical, image and video signal processing phase adjustment estimation radar imaging synthetic aperture radar iterative methods minimum entropy methods

来源：评论

学校读者我要写书评

暂无评论

Texture classification using invariant features of local textures

引用

IET image processing 2010年第3期4卷 158-171页

作者： Janney, P. Geers, G. Univ New S Wales Sch Engn & Comp Sci Sydney NSW 2032 Australia NICTA Sydney NSW 2032 Australia

In this paper, the authors present a texture descriptor algorithm called invariant features of local textures (IFLT). IFLT generates scale, rotation and (essentially) illumination invariant descriptors from a small neighbourhood of pixels around a centre pixel or a texture patch. Texture classification experiments were carried out on the Brodatz, Outex and KTH-TIPS2 databases. Demonstrated texture classification accuracy exceeds the previously published state of the art at a significantly lower computational cost. Experiments also suggests that IFLT descriptors are in a sense intuitive texture descriptors.

关键词： image resolution texture patch computer vision and image processing techniques image classification invariant features of local textures feature extraction texture descriptor algorithm texture classification image texture Optical, image and video signal processing illumination invariant descriptors KTH-TIPS2 databases

来源：评论

学校读者我要写书评

暂无评论

Salient object detection based on edge-interior feature fusion

引用

IET image processing 2023年第2期17卷 337-348页

作者： Shi, Yadi Qin, Guihe Liang, Yanhua Wang, Xinchao Yan, Jie Zhang, Zhonghan Jilin Univ Coll Software Changchun Peoples R China Jilin Univ Coll Comp Sci & Technol Changchun 130012 Peoples R China Jilin Univ Minist Educ Key Lab Symbol Computat & Knowledge Engn Changchun Peoples R China

Recently, existing FCNs-based methods have shown their advantages in processing object boundaries. However, these methods still suffer from false object interference, which appears in saliency predictions. To solve this problem, an edge-interior feature fusion (EIFF) framework is proposed, which consists of an internal-boundary decoupled generation structure with receptive field enlargement and attention mechanism enhancement, and a salient feature refinement module. Specifically, the framework first learns edge features and interior features through an internal-boundary decoupling generation network, which is supervised by labels obtained by decoupling ground-truth through an image erosion algorithm. Then, feature refinement module (FRM) is designed to purify the coarse prediction by focusing on the ambiguous regions through a mining strategy to generate the final saliency map. To compensate for shortcomings of the BCE and IU loss, we also introduce a weighted loss to guide our model to focus more on the error-prone parts. Experimental results on five benchmark datasets demonstrate that the proposed method performs favorably against 19 state-of-the-art approaches under four standard metrics.

关键词： image segmentation feature extraction salient object detection learning (artificial intelligence) edge-interior feature fusion framework Machine learning (artificial intelligence) FCN-based methods saliency predictions EIFF image fusion computer vision and image processing techniques FRM interior features BCE data mining coarse prediction internal-boundary decoupled generation structure internal-boundary decoupling generation network object detection image recognition salient feature refinement module Data mining false object interference image erosion algorithm edge detection receptive field enlargement IU loss attention mechanism enhancement object boundaries

来源：评论

学校读者我要写书评

暂无评论

REVIEW OF MOTION ANALYSIS techniques

引用

IEE PROCEEDINGS-I COMMUNICATIONS SPEECH AND vision 1989年第6期136卷 397-404页

作者： VEGARIVEROS, JF JABBOUR, K Department of Electrical and Computer Engineering Syracuse University Syracuse USA

Motion analysis is an important component of computer vision, dealing with the measurement of motion information from a time varying image sequence. The analysis of dynamic image sequences finds a wide range of applications, including robot navigation, target tracking, traffic monitoring, motion of biological cells, cloud and weather systems tracking, image coding, etc. The paper reviews the various techniques used in motion analysis from image sequences. The approaches are classified according to the methodology in two main groups: methods based on the optical flow constraint equation, and matching. The advantages and disadvantages of both methodologies are also discussed.

关键词： optical information processing Pattern recognition optical flow constraint equation motion analysis techniques computer vision review motion of biological cells target tracking picture processing weather systems tracking image coding advantages robot navigation reviews time varying image sequence Optical information, image and video signal processing computer vision and image processing techniques traffic monitoring block matching disadvantages

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：