检索结果-内蒙古大学图书馆

Efficient saliency detection based on Gaussian models

IET image processing 2011年第2期5卷 122-131页

作者： Liu, Z. Xue, Y. Yan, H. Zhang, Z. Shanghai Univ Sch Commun & Informat Engn Shanghai 200072 Peoples R China Shanghai Univ Minist Educ Key Lab Adv Display & Syst Applicat Shanghai 200072 Peoples R China

This study presents an efficient saliency model mainly aiming at content-based applications such as salient object segmentation. The input colour image is first pre-segmented into a set of regions using the mean shift algorithm. A set of Gaussian models are estimated on the basis of segmented regions, and then for each pixel, a set of normalised colour likelihood measures to different Gaussian models are calculated. The colour saliency measure and spatial saliency measure of each Gaussian model are evaluated based on its colour distinctiveness and the spatial distribution, respectively. Finally, the pixel-wise colour saliency map and spatial saliency map are generated by summing the colour and spatial saliency measures of Gaussian models weighted by the normalised colour likelihood measures, and they are further combined to obtain the final saliency map. Experimental results on a dataset with 1000 images and ground truths demonstrate the better saliency detection performance of our saliency model.

关键词： saliency detection Gaussian model spatial saliency map image colour analysis colour saliency measure colour distinctiveness computer vision and image processing techniques normalised colour likelihood measure spatial distribution colour image Gaussian processes Optical, image and video signal processing content-based application image segmentation spatial saliency measure salient object segmentation saliency model pixel-wise colour saliency map Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

Automated region-based hybrid compression for digital imaging and communications in medicine magnetic resonance imaging images for telemedicine applications

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2012年第4期6卷 247-253页

作者： Bairagi, V. K. Sapkal, A. M. Sinhgad Acad Engn Dept Elect & Telecom Engn Pune Maharashtra India Coll Engn Dept Elect & Telecom Engn Pune Maharashtra India

Many classes of images contains spatial regions which are more important than other regions. Compression methods which are capable of delivering higher reconstruction quality are attractive in this situation for the important parts. For the medical images, only a small portion of the image might be diagnostically useful, but the cost of a wrong interpretation is high. Hence, Region Based Coding (RBC) technique is significant for medical image compression and transmission. Lossless compression in these 'regions' and lossy compression for rest of image can helps to achieve high efficiency and performance in telemedicine applications. This paper proposes an automated, efficient and low complexity, lossless, scalable RBC for Digital Imaging and Communications in Medicine (DICOM) images. The advantages of RBC are exploited in this paper, segmenting the region into various regions of importance and subjecting varying bit-rates for optimal performance. Moreover, the combined effects of Integer Wavelet Transform (IWT) and bit-rate limiting compression technique for lesser important regions helps reconstruct the image, reversibly, up to a desired quality. The overall compression thus reaches a satisfactory level to be able to safely transmit the image in limited bandwidth over a telemedicine network and reconstruct diagnostic details for treatment, most faithfully.

关键词： computer vision and image processing techniques Biomedical magnetic resonance imaging and spectroscopy data compression image and video coding medical images Biology and medical computing wavelet transforms Biomedical communication automated region based hybrid compression digital imaging medicine magnetic resonance imaging image biomedical MRI telemedicine medical image compression image coding medical image processing lossless compression DICOM patient diagnosis integer wavelet transform Integral transforms in numerical analysis Patient diagnostic methods and instrumentation telemedicine applications region based coding technique image processing and restoration image transmission Function theory, analysis Medical magnetic resonance imaging and spectroscopy bit rate limiting compression technique

来源：评论

学校读者我要写书评

暂无评论

Automatic image segmentation based on label propagation

引用

IET image processing 2021年第11期15卷 2532-2547页

作者： Belizario, Ivar Vargas Linares, Oscar Cuadros Santo Batista Neto, Joao do Espirito Univ Sao Paulo Inst Math & Comp Sci ICMC Sao Carlos Brazil

This article introduces an automatic approach for the segmentation of coloured natural scene images based on graphs and the propagation of labels originally designed for communities detection in complex networks. images are initially pre-segmented with super-pixels, followed by feature extraction using colour information of each super-pixels. The resulting graph consists of vertices which represent super-pixels, whereas the edge weights are a measure of similarity between super-pixels. The resulting segmentation corresponds to the propagation of labels among the vertices. In this article, three strategies for propagating labels have been formulated: (i) iterative propagation (ILP), (ii) recursive propagation (RLP) and (iii) a weighted recursive propagation (WRLP). The experiments have shown that the proposed methods, when compared to other state-of-the-art methods, produce better results in terms of segmentation quality and processing time.

关键词： iterative methods coloured natural scene images weighted recursive propagation vertices ILP computer vision and image processing techniques iterative propagation label propagation Optical, image and video signal processing super pixels image segmentation natural scenes resulting segmentation corresponds graph theory feature extraction Interpolation and function approximation (numerical analysis) graphs colour information segmentation quality automatic image segmentation RLP Combinatorial mathematics

来源：评论

学校读者我要写书评

暂无评论

QUANTIFICATION OF RETINAL DAMAGE DURING CARDIOPULMONARY BYPASS - COMPARISON OF computer AND HUMAN ASSESSMENT

引用

IEE PROCEEDINGS-I COMMUNICATIONS SPEECH AND vision 1990年第3期137卷 170-175页

作者： JAGOE, JR BLAUTH, CI SMITH, PL ARNOLD, JV TAYLOR, KM WOOTTON, R HAMMERSMITH HOSP ROYAL POSTGRAD MED SCHDEPT SURGLONDON W12 0NNENGLAND

A comparison of retinal fluorescein angiograms taken before cardiopulmonary bypass with those taken just before the end of operation, has shown that microvascular occlusions can develop during operation. Quantification of the retinal damage in terms of the area of non-perfusion depends on careful examination by humans. Assessment of these areas is necessarily subjective and digital image analysis would be preferable to make the measurements more objective. Visual or automatic comparison of images is facilitated by prior geometrical alignment. A method for registering retinal images which has been used successfully on 65 image pairs is described. techniques for automatically detecting changes in the microvascular structure are illustrated. Using a subset of 40 good quality image pairs, good agreement between computer detected occlusions and human assessment of non-perfusing areas is reported.

关键词： retinal images registering geometrical alignment Radiation and radioactivity applications in biomedicine retinal damage quantification eye nonperfusing areas medical computing good quality image pairs cardiology computer detected occlusions Biology and medical computing Optical information, image and video signal processing computerised picture processing computer vision and image processing techniques automatic detection cardiopulmonary bypass human assessment microvascular structure changes surgery

来源：评论

学校读者我要写书评

暂无评论

Role of 3-D graphics in NDT data processing

引用

IEE PROCEEDINGS-SCIENCE MEASUREMENT AND TECHNOLOGY 2001年第4期148卷 149-158页

作者： McNab, A Reilly, D Potts, A Toft, M Univ Strathclyde Dept Elect & Elect Engn Ctr Ultrasonc Engn Glasgow G1 1XW Lanark Scotland BNFL Magnox Generat Berkeley GL13 9PB Glos England

Visualisation in 3-D can significantly improve the interpretation and understanding of imaged NDT data sets. The advantages of using 3-D graphics to assist in the interpretation of ultrasonic data are discussed in the context of an advanced software environment for the reconstruction, visualisation and analysis of 3-D images within a component CAD model. The software combines the analysis features of established 2-D packages with facilities for real-time data rotation, interactive orthogonal/oblique slicing and 'true' image reconstruction, where scanning-surface shape and reflection from component boundaries are accounted for through interaction with the full 3-D model of the component. A number of novel facilities exploit the graphics capability of the system. These include the overlay of 3-D images with individual control of image transparency;a floating tooltip window for interrogation of data point co-ordinates and amplitude;image annotation tools, including 3-D distance measurement;and automated defect sizing based on '6dB drop' and,maximum amplitude' methods. A graphical user interface has also been designed for a well established flaw response model, which allows the user to easily specify the flaw size, shape, orientation and location;probe parameters and scan pattern on the component. The output is presented as a simulated ultrasound image.

关键词： Graphical user interfaces scanning-surface reflection CAD Materials testing 3D graphics role graphical user interface real-time data rotation Testing flaw detection maximum amplitude method graphical user interfaces component CAD model simulated ultrasound image Graphics techniques ultrasonic materials testing computerised instrumentation Programming support scanning-surface shape floating tooltip window interactive orthogonal/oblique slicing computer vision and image processing techniques imaged NDT data sets ultrasonic data images overlay flaw response model inspection flaw location data point coordinates image transparency control 3D visualisation automated defect sizing Optical, image and video signal processing Instrumentation Inspection and quality control Design Measurement by acoustic techniques scan pattern flaw shape image annotation tools Engineering materials data visualisation probe parameters flaw size advanced software environment image reconstruction flaw orientation Nondestructive testing: acoustic methods Computing devices and techniques ultrasonic imaging software tools computerised instrumentation automatic test software NDT data processing Sonic and ultrasonic applications

来源：评论

学校读者我要写书评

暂无评论

Medical image segmentation using deep learning: A survey

引用

IET image processing 2022年第5期16卷 1243-1267页

作者： Wang, Risheng Lei, Tao Cui, Ruixia Zhang, Bingtao Meng, Hongying Nandi, Asoke K. Shaanxi Univ Sci & Technol Shaanxi Joint Lab Artificial Intelligence Xian 710021 Peoples R China Shaanxi Univ Sci & Technol Sch Elect Informat & Artificial Intelligence Xian Peoples R China Xi An Jiao Tong Univ Affiliated Hosp 1 Lab Hepatobiliary Surg Xian Peoples R China Xi An Jiao Tong Univ Natl Engn Lab Big Data Algorithm & Anal Technol R Xian Peoples R China Lanzhou Jiaotong Univ Sch Elect & Informat Engn Lanzhou Peoples R China Brunel Univ London Dept Elect & Elect Engn London England

Deep learning has been widely used for medical image segmentation and a large number of papers has been presented recording the success of deep learning in the field. A comprehensive thematic survey on medical image segmentation using deep learning techniques is presented. This paper makes two original contributions. Firstly, compared to traditional surveys that directly divide literatures of deep learning on medical image segmentation into many groups and introduce literatures in detail for each group, we classify currently popular literatures according to a multi-level structure from coarse to fine. Secondly, this paper focuses on supervised and weakly supervised learning approaches, without including unsupervised approaches since they have been introduced in many old surveys and they are not popular currently. For supervised learning approaches, we analyse literatures in three aspects: the selection of backbone networks, the design of network blocks, and the improvement of loss functions. For weakly supervised learning approaches, we investigate literature according to data augmentation, transfer learning, and interactive segmentation, separately. Compared to existing surveys, this survey classifies the literatures very differently from before and is more convenient for readers to understand the relevant rationale and will guide them to think of appropriate improvements in medical image segmentation based on deep learning approaches.

关键词： Neural nets Unsupervised learning supervised learning transfer learning computer vision and image processing techniques deep learning approaches deep learning (artificial intelligence) medical image segmentation unsupervised learning deep learning techniques Data handling techniques Biology and medical computing Supervised learning learning (artificial intelligence) literatures Optical, image and video signal processing weakly supervised learning approaches image segmentation data augmentation

来源：评论

学校读者我要写书评

暂无评论

Light field editing in the gradient domain

引用

IET image processing 2021年第5期15卷 1072-1082页

作者： Sevcenco, Ioana Agathoklis, Panajotis Univ Victoria Dept Elect & Comp Engn Victoria BC V8P 5C2 Canada

This paper presents a new method for light field applications such as content replacement and fusion in the gradient domain. This approach is inspired by successful gradient domain based image and video editing techniques. A necessary and important part of gradient-based solutions is recovering the signal of interest from artificially generated, and typically non-integrable, gradient data. As such, a new algorithm is developed to reconstruct a light field from a given gradient data set. In the algorithm, first, the 4D Haar wavelet decomposition of the light field is obtained from the given gradient data. Then, the light field is obtained from a wavelet synthesis step. This algorithm is intended as a building block for gradient-based light field editing methods, and as such, its performance is analysed on a set of benchmark light field data sets. The proposed reconstruction algorithm is an essential part in developing solutions for two light field problems: light field editing and light field fusion. Results show that processing light fields in the gradient domain offers significant advantages over processing in the intensity domain.

关键词： Optical, image and video signal processing computer vision and image processing techniques Video signal processing Graphics techniques

来源：评论

学校读者我要写书评

暂无评论

Power line detection in millimetre-wave radar images applying convolutional neural networks

引用

IET RADAR SONAR AND NAVIGATION 2021年第9期15卷 1083-1095页

作者： Xiong, Wei Luo, Jingsheng Yu, Chaopeng Aviat Ind Corp China Leihua Elect Technol Res Inst Wuxi 214063 Jiangsu Peoples R China Aviat Key Lab Sci & Technol AISSS Wuxi Jiangsu Peoples R China

High-voltage power lines and their supporting towers create hazardous low-altitude flight conditions for helicopters. Herein, a novel power line detection and classification is proposed for millimetre-wave (MMW) radars applying Hough transform (HT) and convolutional neural network (CNN). HT is implemented to detect candidate lines in MMW radar images. Unfortunately, in the presence of background clutter and manmade structures, some false power lines are also brought in, thus it is vital to differentiate the actual power lines. Moreover, it is important to classify the power lines with and without Bragg pattern, and offer different threat levels. The authors firstly introduce the incidence angle and azimuth angle vectors of candidate lines as a supplement to power vectors, and propose a new CNN architecture for classification that uses powerful dense blocks and defined index pooling. With the trick of index pooling, the incidence angle and azimuth angle vectors can be merged with the corresponding power vectors together to mine the features, including those of Bragg pattern. Taking advantage of scale transformation, the proposed network adapts to different input scales. Extensive experiments demonstrate that the proposed method achieves state-of-the-art results and is not sensitive to the input scales and noise levels.

关键词： computer vision and image processing techniques candidate lines poles and towers millimetre-wave radar images radar imaging Hough transforms CNN architecture hazardous low-altitude flight conditions high-voltage power lines incidence angle power cables false power lines Bragg pattern Optical, image and video signal processing radar computing azimuth angle vectors Radar equipment, systems and applications classification helicopters convolutional neural network power line detection power vectors MMW radar images convolutional neural nets Integral transforms hazards object detection Power cables millimetre wave imaging image classification

来源：评论

学校读者我要写书评

暂无评论

COMPLEX NUMBER MULTIPLIERS

引用

IEE PROCEEDINGS-E computerS AND DIGITAL techniques 1989年第1期136卷 70-75页

作者： PEKMESTZI, KZ Division of Computer Science Department of Electrical Engineering National Technical University of Athens Athens Greece

The direct digital multiplication of complex numbers is examined. The proposed technique bypasses the classical method based on the identity (A+Bj)(C+Dj) =AC−BD+ (AD+BC)j. The complex multiplication is considered as one operation and is examined in the bit-level. Various multipliers, such as the parallel or serial-parallel types and the realisation through microprogramming on an arithmetic unit, are presented, all of which are based on the above technique.

关键词： direct digital multiplication Digital arithmetic methods digital arithmetic computerised signal processing microprogramming complex numbers computer vision and image processing techniques bit-level

来源：评论

学校读者我要写书评

暂无评论

End-to-end feature fusion Siamese network for adaptive visual tracking

引用

IET image processing 2021年第1期15卷 91-100页

作者： Guo, Dongyan Wang, Jun Zhao, Weixuan Cui, Ying Wang, Zhenhua Chen, Shengyong Zhejiang Univ Technol Coll Comp Sci & Technol 288 Liuhe Rd Hangzhou 310023 Zhejiang Peoples R China Tianjin Univ Technol Sch Comp Sci & Engn Tianjin Peoples R China

According to observations, different visual objects have different salient features in different scenarios. Even for the same object, its salient shape and appearance features may change greatly from time to time in a long-term tracking task. Motivated by them, an end-to-end feature fusion framework was proposed based on the Siamese network, named FF-Siam, which can effectively fuse different features for adaptive visual tracking. The framework consists of four layers. A feature extraction layer is designed to extract the different features of the target region and search region. The extracted features are then put into a weight generation layer to obtain the channel weights, which indicate the importance of different feature channels. Both features and the channel weights are utilised in a template generation layer to generate a discriminative template. Finally, the corresponding response maps created by the convolution of the search region features and the template are applied with a fusion layer to obtain the final response map for locating the target. Experimental results demonstrate that the proposed framework achieves state-of-the-art performance on the popular Temple-Colour, OTB50 and UAV123 benchmarks.

关键词： image recognition computer vision and image processing techniques Neural nets

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：