检索结果-内蒙古大学图书馆

Multimodal biometric method based on vein and geometry of a single finger

IET computer vision 2010年第3期4卷 209-217页

作者： Kang, B. J. Park, K. R. Elect & Telecommun Res Inst Taejon 305606 South Korea Dongguk Univ Seoul Div Elect & Elect Engn Seoul 100715 South Korea

There are limits to a single biometric observation such as variation in an individual biometric feature due to the condition of a sensor, the health condition of a human, illumination variation and so on. To overcome such limitations, the authors propose a new multimodal biometric approach integrating finger vein recognition and finger geometry recognition at the score level. The method presents three advantages compared to previous works: (i) the proposed multimodal biometric system can be constructed as a tiny device, which uses a finger vein and finger geometry features acquired from a single finger;(ii) the proposed finger geometry recognition, based on Fourier descriptors, is robust to the translation and rotation of a finger;and (iii) the authors obtained better recognition accuracy using the score-level fusion method based on a support vector machine than by other score-level fusion methods such as the MAX, MIN and SUM rules. The results showed that the equal error rate of the proposed method decreased by as much as 1.089 and 1.627% compared with finger vein recognition and finger geometry recognition methods, respectively.

关键词： finger geometry recognition Fourier descriptors image recognition Combinatorial mathematics Computational geometry score level fusion method support vector machine biometrics (access control) Sensor fusion sensor fusion support vector machines multimodal biometric method computational geometry object recognition Fourier analysis Mathematical analysis computer vision and image processing techniques feature extraction finger vein recognition Knowledge engineering techniques

来源：评论

学校读者我要写书评

暂无评论

Visual inspection for transformer insulation defects by a patrol robot fish based on deep learning

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2021年第7期15卷 606-618页

作者： Ji, Hongxin Cui, Xiwang Ren, Weiyan Liu, Liqing Wang, Wei Tsinghua Univ Sch Aerosp Engn Beijing Peoples R China Beijing Informat Sci & Technol Univ Sch Instrument Sci & Optoelect Engn Beijing 100192 Peoples R China State Grid Tianjin Elect Power Res Inst Tianjin Peoples R China

In order to effectively detect the internal insulation defects of large transformers, a miniature patrol robot fish is designed and used to observe the pressboard inside the transformer, which can visually inspect the insulation condition of the pressboard. In the process of visual inspection by a patrol robot fish, insulation defects observed in the transformer (such as discharge carbon marks, pressboard cracks, etc.) are small size, indistinctive colour contrast and different shapes. The key purpose of the patrol robot fish is to identify the defect targets and defect types intelligently and quickly from the images taken by the camera on the fish. Considering that there are abundant insulation defects in transformers and a lack of samples for learning, a vision detection method based on deep learning network is proposed in this study. The proposed method integrates the variable autoencoder into the traditional Faster-RCNN target detection network and constructs an improved Faster-RCNN that enhances feature extraction. This method expands the small-scale training sample set and improves the generalisation performance of the model. In order to verify the effectiveness of the proposed method, the improved network is trained and tested, and the test results show that the improved network training model can accurately identify and mark the carbon marks on the pressboard surface.

关键词： Inspection and quality control Organic insulation image recognition computerised instrumentation computer vision and image processing techniques computerised instrumentation Power engineering computing Transformers and reactors Neural nets

来源：评论

学校读者我要写书评

暂无评论

Sprott chaos synchronisation classifier for diabetic foot peripheral vascular occlusive disease estimation

引用

IET SCIENCE MEASUREMENT & TECHNOLOGY 2012年第6期6卷 533-540页

作者： Wu, J. -X. Lin, C. -H. Du, Y. -C. Chen, T. Natl Cheng Kung Univ Dept Biomed Engn Tainan 70101 Taiwan Kao Yuan Univ Dept Elect Engn Kaohsiung Taiwan Taiwan CareTech Corp Kaohsiung Taiwan

This study proposes a method for lower limb peripheral vascular occlusive disease (PVOD) estimation using a Sprott chaos synchronisation (CS) classifier. Early PVOD estimation is important for the patients to prevent ischaemic chest pain and disabling claudication. Photoplethysmography (PPG) is a non-invasive technique to detect blood volume changes in peripheral arteries. The pulse transit time increases with disease severity, and normalised amplitudes decrease in vascular disease. Synchronous PPG pulses gradually become asynchronous producers at the right and left sites. A CS detector based on the Sprott system is used to track bilateral similarity or asymmetry of PPG signals, and to construct various butterfly motion patterns. An adaptive classifier with wolf pack search algorithm performs to estimate the grade of PVOD, including normal condition, lower-grade disease and higher-grade disease. For 21 subjects, the proposed method demonstrates greater efficiency and higher accuracy in PVOD estimation.

关键词： peripheral artery computer vision and image processing techniques chaos Biology and medical computing CS detector Optical and laser radiation (biomedical imaging/measurement) lower limb peripheral vascular occlusive disease estimation medical image processing non-invasive technique diseases pattern classification Optical, image and video signal processing butterfly motion pattern blood vessels lower-grade disease Sprott chaos synchronisation classifier higher-grade disease photoplethysmography Patient diagnostic methods and instrumentation Haemodynamics, pneumodynamics disease severity synchronous PPG pulse pulse transit time diabetic foot peripheral vascular occlusive disease estimation Sprott system synchronisation blood volume Optical and laser radiation (medical uses) adaptive classifier wolf pack search algorithm

来源：评论

学校读者我要写书评

暂无评论

Adaptive group-of-pictures and scene change detection methods based on existing H.264 advanced video coding information

引用

IET image processing 2008年第2期2卷 85-94页

作者： Ding, J. -R. Yang, J. -F Natl Cheng Kung Univ Dept Elect Engn Inst Comp & Commun Engn Tainan 70101 Taiwan

The H.264 advanced video coding (H.264/AVC) standard provides several advanced features such as improved coding efficiency and error robustness for video storage and transmission. In order to improve the coding performance of H.264/AVC, coding control parameters such as group-of-pictures (GOP) sizes should be adaptively adjusted according to different video content variations (VCVs), which can be extracted from temporal deviation between two consecutive frames. The authors present a simple VCV estimation to design adaptive GOP detection (AGD) and scene change detection (SCD) methods by using the obtained motion information, where the motion vectors and the sum of absolute transformed differences as VCV features are effectively used to design the AGD and SCD algorithms, respectively. In order to avoid unnecessary computation, the above VCV features are obtained only in the 4 x 4 inter-frame prediction mode. Simulation results show that the proposed AGD with SCD methods can increase the peak signal-to-noise ratio by 0.62 dB on average over the H.264/AVC operated with a fixed GOP size. Besides, the proposed SCID method can reach a scene change detection rate of 98%.

关键词： adaptive group-of-picture H.264 advanced video coding video coding computer vision and image processing techniques image and video coding scene change detection method feature extraction motion estimation adaptive GOP detection motion vector video storage/transmission video content variation Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Contribution of neural networks in image steganography, watermarking and encryption

引用

IET image processing 2023年第2期17卷 463-479页

作者： Rafidison, Maminiaina Alphonse Rafanantenana, Sabine Harisoa Jacques Rakotomihamina, Andry Harivony Toky, Rajaonarison Faniriharisoa Maxime Ramafiarisona, Hajasoa Malalatiana Univ Antananarivo Telecommun Automat Signal Image Res Lab Doctoral Sch Sci & Technol Engn & Innovat Antananarivo Madagascar

In front of information fishing, it is necessary to protect the information to be circulated over public channel. The goal of this paper is to propose an approach which inserts a logo inside of cover image and having three different possible results according to user's needs. The algorithm can perform steganography, watermarking or host encryption. This technique is based on singular value decomposition (SVD) and discrete wavelet transform (DWT) composed by three steps: pre-processing, embedding and extraction/decryption. Reference matrix and reference parameter are the two factors deciding the operation and the intervention of neural networks makes the choice of their parameters easier according to the desired result. For measuring the steganography performance, the authors adopt the structural similarity index measure (SSIM) which calculates the similarity between original and watermarked image and peak signal-to-noise ratio. For watermarking, the normalized correlation (NC) coefficient investigates the correlation between the original watermark and the extracted watermark. Attacking the watermarked image with common attacks used by previous publication searchers, the value of SSIM and NC coefficient are closed to one. Regarding peak signal-to-noise ratio, the overall score is around 61.73 dB. The performance score is not negligible also for the encryption method.

关键词： Integral transforms previous publication searchers Cryptography neural networks normalized correlation coefficient watermarking image steganography performance score image and video coding encryption method singular value decomposition image watermarking computer vision and image processing techniques structural similarity index measure original watermark discrete wavelet transforms steganography performance reference parameter extracted watermark watermarked image Data security image coding information fishing host encryption steganography cover image public channel peak signal-to-noise ratio cryptography

来源：评论

学校读者我要写书评

暂无评论

Traffic congestion identification based on image processing

引用

IET INTELLIGENT TRANSPORT SYSTEMS 2012年第2期6卷 153-160页

作者： Jianming, H. Qiang, M. Qi, W. Jiajie, Z. Yi, Z. Tsinghua Univ Dept Automat Beijing 100084 Peoples R China

Accurate and real-time traffic information is the foundation of intelligent transportation systems (ITS). In general, density, velocity and flow are used to describe traffic status of certain road segment. However, these macroscopic parameters are not able to reflect detailed traffic scenarios. It is more valuable to detect traffic congestion, which can be the basis of dynamic control and real-time guidance. This study proposes a novel approach towards traffic congestion identification based on vehicle trajectories in intelligent vehicle infrastructure co-operation system (IVICS). Considering spatial-temporal trajectories as image, this study uses self-correlation to extract propagation speed of congestion wave. Based on this, this study constructs congestion template;by matching algorithm, congestion is further identified as well as its intensity. Simulations on next generation simulation (NGSim) dataset verify the effectiveness of the above methods.

关键词： traffic congestion detection Traffic engineering computing real-time systems ITS system extract propagation speed intelligent transportation systems road segment macroscopic parameters spatiotemporal phenomena traffic information systems computer vision and image processing techniques image processing dynamic control traffic status real-time traffic information Optical, image and video signal processing real-time guidance image matching next generation simulation spatial-temporal trajectories vehicle trajectories traffic congestion identification self-correlation matching algorithm correlation methods congestion wave intelligent vehicle infrastructure co-operation system automated highways

来源：评论

学校读者我要写书评

暂无评论

Human motion estimation with multiple frequency modulated continuous wave radars

引用

IET RADAR SONAR AND NAVIGATION 2010年第3期4卷 348-361页

作者： van Dorp, P. Groen, F. C. A. TNO NL-2509 JG The Hague Netherlands Univ Amsterdam Intelligent Autonomous Syst IAS Grp NL-1098 SJ Amsterdam Netherlands

Human motion estimation is an important issue in automotive, security or home automation applications. Radar systems are well suited for this because they are robust, are independent of day or night conditions and have accurate range and speed domain. The human response in a radar range-speed-time measurement behaves like an extended target where legs and arms coincide. A mutually non-coherent radar sensor network makes it possible to estimate additional information of the extended target response. To keep the system low cost the network uses commercial off-the-shelf (COTS) radar sensors without synchronisation of frequency or phase between the radar sensors. This article presents the results of human motion estimation with a mutually non-coherent radar sensor network. The calibration, radar processing, parameter estimation and classification of extended human objects are described. The swinging and rotating moving body parts give elliptical shapes in the differential range-speed responses. A model fit gives the legs and arms parameters on which classification is possible.

关键词： computer vision and image processing techniques radar range-speed-time measurement multiple frequency modulation sensors calibration parameter estimation commercial off-the-shelf radar sensors human motion estimation motion estimation Modulation and coding methods Optical, image and video signal processing noncoherent radar sensor Radar equipment, systems and applications frequency modulation object classification continuous wave radar object detection CW radar extended target

来源：评论

学校读者我要写书评

暂无评论

Structural sub-band decomposition of sequences and its applications in signal processing

引用

IEE PROCEEDINGS-vision image AND SIGNAL processing 1999年第3期146卷 109-123页

作者： Mitra, SK Heute, U Univ Calif Santa Barbara Dept Elect & Comp Engn Santa Barbara CA 93106 USA Univ Kiel Fac Engn Inst Syst Theory D-24143 Kiel Germany

The authors present a tutorial paper in which they review the concept of structural sub-band decomposition of sequences, a generalisation of polyphase decomposition. The idea of using a very simple analysis-synthesis structure allows for computational efficiency. It is applicable both for signals and for systems, which may thus be designed and realised advantageously. The use of such decomposition is shown, in terms of theory and applications, for transform-based spectral analysis, FIR filter design and implementation, and adaptive filtering. Advantages are demonstrated for cases of narrow-band signals and systems.

关键词： signal processing adaptive filters signal synthesis adaptive signal processing narrow-band systems FIR filter implementation FIR filters Filtering methods in signal processing computer vision and image processing techniques spectral analysis transform-based spectral analysis Integral transforms in numerical analysis adaptive filtering Optical, image and video signal processing sequences image processing transforms tutorial filtering theory FIR filter design structural sub-band decomposition narrow-band signals polyphase decomposition computational efficiency Signal processing theory analysis-synthesis structure

来源：评论

学校读者我要写书评

暂无评论

Dense spatio-temporal stereo matching for intelligent driving systems

引用

IET image processing 2021年第3期15卷 715-723页

作者： Kerkaou, Zakaria El Ansari, Mohamed Masmoudi, Lhoussaine Lahmyed, Redouan Ibn Zohr Univ Fac Sci Dept Comp Sci LabSIV BP 8106 Agadir 80000 Morocco Mohammed V Univ Rabat Fac Sci Dept Phys Rabat Morocco

This paper addresses the problem of matching stereo images acquired by a stereo system mounted aboard an intelligent vehicle. The main idea behind the new method consists in involving temporal matching between a current stereo pair and its preceding one to achieve the spatial matching of the former stereo by involving the matching results obtained at the last frame. The proposed method is achieved in three main steps. First, an edge based disparity map is derived from the disparity map of the preceding frame, we call it the assisting disparity map (ADM). Second, for each scan-line, a set of local ranges and global ranges are deduced from the ADM to keep only potential matching candidates. Third, the matching is done on the basis of dynamic programming algorithm by involving in the resulting local and global ranges we get from the last step. The proposed approach has been tested on both real and synthetic stereo sequences and the results demonstrate its effectiveness.

关键词： Optical, image and video signal processing image recognition Optimisation techniques computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Remote sensing image super-resolution based on convolutional blind denoising adaptive dense connection

引用

IET image processing 2021年第11期15卷 2508-2520页

作者： Yang, Xin Xie, Tangxin Guo, Yingqing Zhou, Dake Nanjing Univ Aeronaut & Astronaut Coll Automat Engn Nanjing Peoples R China

The current super-resolution (SR) deep network is mainly applied to the common image and pays little attention to the image with noise. The remote sensing image contains much noise, so that the SR reconstruction effect is not satisfactory. Therefore, a convolution blind denoising adaptive dense connection SR (CBD-ADCSR) network for the remote sensing image is proposed in this paper. The whole model is divided into a convolution blind denoising (CBD) network for denoising and an ADCSR network for reconstruction. Firstly, the components of the network are given in detail and are analysed. Secondly, a data set making method is designed combining motion blur, defocusing blur and Gaussian noise, which is used to generate low-resolution image data sets with complex degradation for the model training. Finally, through the detailed comparative experiment, it is proved that the reconstruction effect of the CBD-ADCSR model is better than that of the most state-of-the-art algorithms in objective criteria. In addition, compared with the original ADCSR network, CBD-ADCSR has a stronger ability for noise suppression.

关键词： Optical, image and video signal processing computer vision and image processing techniques Other topics in statistics Other topics in statistics

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：