检索结果-内蒙古大学图书馆

Iris matching using multi-dimensional artificial neural network

IET computer vision 2011年第3期5卷 178-184页

作者： Farouk, R. M. Kumar, R. Riad, K. A. Zagazig Univ Fac Sci Dept Math Zagazig Egypt Natl Univ Singapore Dept Elect & Comp Engn Singapore 117548 Singapore

Iris recognition is one of the most widely used biometric technique for personal identification. This identification is achieved in this work by using the concept that, the iris patterns are statistically unique and suitable for biometric measurements. In this study, a novel method of recognition of these patterns of an iris is considered by using a multidimensional artificial neural network. The proposed technique has the distinct advantage of using the entire resized iris as an input at once. It is capable of excellent pattern recognition properties as the iris texture is unique for every person used for recognition. The system is trained and tested using two publicly available databases (CASIA and UBIRIS). The proposed approach shows significant promise and potential for improvements, compared with the other conventional matching techniques with regard to time and efficiency of results.

关键词： iris texture UBIRIS biometrics (access control) pattern recognition properties image texture personal identification image matching Graphics techniques Neural computing techniques multidimensional artificial neural network CASIA computer vision and image processing techniques iris recognition image recognition neural nets iris matching biometric technique

来源：评论

学校读者我要写书评

暂无评论

Metropolis Monte Carlo for tomographic reconstruction with prior smoothness information

引用

IET image processing 2011年第2期5卷 198-204页

作者： Barbuzza, R. Clausse, A. CNEA CONICET RA-7000 Tandil Argentina Univ Nacl Ctr RA-7000 Tandil Argentina

The Metropolis Monte Carlo algorithm was applied to produce tomographic reconstructions from scarce projection data supplemented by prior information about the smoothness of the object. The prior information is represented by means of local energy functions, which are added to the projection error. The proposed prior function is an extension of previous proposals of border filters, the novelty introduced here being an adaptive control of the filter during the reconstruction process. The method was tested on synthetic phantoms and the reconstructions of a real object from a small number of projections. The technique shows good results in images with piecewise homogeneous regions, and can be useful in certain applications, where the scanning views are within an angular range that is either limited or sparsely sampled, as the detection of material defects in non-destructive testing or special anatomical components in medical images. Finally, the method is applied to the reconstruction of an industrial application of a stainless-steel BNC elbow from very few projections.

关键词： local energy functions adaptive control stainless-steel BNC elbow computerised tomography Filtering methods in signal processing metropolis Monte Carlo algorithm image reconstruction prior smoothness information computer vision and image processing techniques production engineering computing Materials testing Optical, image and video signal processing stainless steel nondestructive testing steel industry scarce projection data Testing border filters Metallurgical industries object detection computerised instrumentation Monte Carlo methods tomographic reconstructions filtering theory Industrial applications of IT Statistics material defect detection Production engineering computing

来源：评论

学校读者我要写书评

暂无评论

Integral image compression based on optical characteristic

引用

IET computer vision 2011年第3期5卷 164-168页

作者： Yan, P. Xianyuan, Y. Chang Chun Univ Sci & Technol Changchun Peoples R China Univ Washington Dept Elect Engn Seattle WA 98195 USA

The large amount of image data from the captured three-dimensional integral image requires to be presented with adequate resolution. It is therefore necessary to develop compression algorithms that take advantage of the characteristics of the recorded integral image. In this study, the authors propose a new compression method that is adapted to integral imaging. According to the optical characteristics of integral imaging, most of the information of each elemental image is overlapped with that of its adjacent elemental images. Thus, the method is to achieve image compression by taking a sample from the elemental image sequence for every m elemental image to get image compression. Experimental results that are presented to illustrate the proposed compression technique prove that the proposed technique can improve the compression ratio of integral imaging.

关键词： image data image and video coding optical characteristic data compression image sequences elemental image sequence integral image compression computer vision and image processing techniques image coding

来源：评论

学校读者我要写书评

暂无评论

Iris segmentation for non-cooperative recognition systems

引用

IET image processing 2011年第5期5卷 448-456页

作者： Chen, R. Lin, X. R. Ding, T. H. Tsinghua Univ Grad Sch Shenzhen Shenzhen 518055 Peoples R China Tsinghua Univ State Key Lab Precis Measurement Technol & Instru Beijing 100084 Peoples R China

Segmenting iris texture from an input image is an important step for recognising iris pattern. It is still a difficult task to localise available texture regions from non-ideal iris images captured in non-cooperative situations such as lighting variations, on-the-move and off-angle view. To address this problem, this study presents a novel algorithm for accurate and fast iris segmentation. An adaptive mean shift procedure is built to find the rough position of the iris centre. According to the localisation result, a circle is set as the initial iris contour. After combining the statistical texture prior modelled as Markov random field, a merged active contour model is established in terms of level set theory. Under the MAC model, the initial contour is iteratively driven to real iris boundaries. During the curve evolving process, eyelids, eyelashes, reflections and shadows can be simultaneously detected and labelled in iris regions. The novelty of the proposed method mainly includes developing a new modified mean shift procedure for fast and robust iris localisation, and successfully incorporating the local probabilistic prior, boundary and region information into the designed active contour model for accurate texture segmentation. Extensive experimental results on various challenging iris images show that our method can effectively and accurately perform iris segmentation with low computational complexity and has very promising applications in non-cooperative recognition systems.

关键词： iris texture segmentation probability eyelids statistical analysis mean shift procedure off-angle view accurate texture segmentation adaptive mean shift procedure lighting variations eyelashes on-the-move view curve evolving process image recognition statistical texture prior modeling iris recognition active contour model iris pattern recognition robust iris localisation computer vision and image processing techniques reflections image segmentation noncooperative recognition systems iris contour Markov random field image texture computational complexity MAC model Markov processes level set theory Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

Gradient-based edge detection for motion estimation in H.264/AVC

引用

IET image processing 2011年第4期5卷 323-327页

作者： Paul, A. Wu, J. Yang, J. -F. Jeong, J. Hanyang Univ Dept Elect Engn Seoul 133791 South Korea Natl Cheng Kung Univ Dept Elect Engn Tainan 70101 Taiwan

This study introduces a block-based motion estimation algorithm based on projection with adaptive window-size selection. Using one-dimensional (1D) projection, the original 2D block-matching problem is translated to a simpler 1D matching problem which eliminates the majority of potential pixel participation. The authors propose an efficient fast-motion estimation method using an intensity gradient algorithm to reduce the encoding time. The proposed algorithm estimates the texture direction of the block, and then a horizontal or vertical projection is employed for the sum of absolute difference calculation. Experimental results show that the proposed algorithm achieves a greater than 60% time reduction with negligible peak signal to noise ratio (PSNR) loss and BR increments.

关键词： gradient-based edge detection potential pixel participation image recognition computer vision and image processing techniques image and video coding H.264-AVC adaptive window-size selection motion estimation block-based motion estimation algorithm 2D block-matching problem one-dimensional projection image matching 1D matching problem video coding Interpolation and function approximation (numerical analysis) Video signal processing edge detection intensity gradient algorithm gradient methods

来源：评论

学校读者我要写书评

暂无评论

Corner classification using Harris algorithm

引用

ELECTRONICS LETTERS 2011年第9期47卷 536-538页

作者： Ryu, J. -B. Park, H. -H. Park, J. Chung Ang Univ Coll Engn Seoul 156756 South Korea

An efficient corner type classification method derived from the general Harris corner detector is presented. The key idea is using the property that the gradient magnitudes of two isophotes in a second-order corner are the same but those in higher-order corners are different. A computational framework for post corner type classification led by the general Harris corner detector is devised. It can be implemented with a few additional computations.

关键词： corner type classification method gradient magnitudes corner classification second-order corner Harris corner detector algorithm edge detection object recognition image classification computer vision and image processing techniques image recognition

来源：评论

学校读者我要写书评

暂无评论

Error concealment for motion-compensated interpolation

引用

IET image processing 2010年第3期4卷 195-210页

作者： Wu, Y. Swamy, M. N. S. Ahmad, M. O. Concordia Univ Dept Elect & Comp Engn Ctr Commun & Signal Proc Montreal PQ H3G 1M8 Canada

Motion-compensated interpolation is usually employed at the receiver end in order to improve the quality of the video, when a low-bit-rate video is encoded in conjunction with frame dropping. The authors propose a scheme that can exploit the block-based motion vector field available at the decoder to avoid the complex motion estimation. The scheme is based on an iterative refinement technique that employs the finite-element method to efficiently conceal the interpolation errors caused by unfilled holes or overlapped pixels in the predicted frames. As a consequence, no pixel classification is needed in the proposed scheme, thus reducing substantially the computational complexity. The scheme is capable of concealing the errors in the homogeneous regions as well as in regions containing sharp edges. The proposed scheme is simulated with the original frames of a number of test sequences, as well as implemented with the H.264/AVC decoded frames. The results from these extensive simulations show that the proposed scheme results in reconstructed frames having a better visual quality and a lower computational complexity than the existing schemes.

关键词： pixel classification finite element method motion compensation complex motion estimation computer vision and image processing techniques image and video coding decoder frame dropping block-based motion vector field visual quality motion-compensated interpolation video coding error handling H.264/AVC decoded frames low bit rate video error concealment Video signal processing iterative refinement technique computational complexity video quality interpolation errors

来源：评论

学校读者我要写书评

暂无评论

Design and realisation of a microwave three-dimensional imaging system with application to breast-cancer detection

引用

IET MICROWAVES ANTENNAS & PROPAGATION 2010年第12期4卷 2200-2211页

作者： Zhurbenko, V. Rubaek, T. Krozer, V. Meincke, P. Tech Univ Denmark DK-2800 Lyngby Denmark Chalmers Univ Technol Dept Signals & Syst SE-412 Gothenburg Sweden Goethe Univ Frankfurt D-60438 Frankfurt Germany TICRA DK-1201 Copenhagen K Denmark

An active microwave-imaging system for non-invasive detection of breast cancer based on dedicated hardware is described. Thirty-two transceiving channels are used to measure the amplitude and phase of the scattered fields in the three-dimensional (3D) imaging domain using electronic scanning. The 3D inverse electromagnetic scattering problem is then solved in order to reconstruct the distribution of the complex permittivity in the imaging domain. The dedicated hardware is based on an array architecture allowing for a short acquisition time while maintaining a high sensitivity, which is important for measurement accuracy and reproducibility as well as for patient comfort. The dedicated hardware achieves a receiver noise figure of 2.3 dB at a gain of 97 dB. The operating frequency range is from 0.3 to 3 GHz. The image acquisition time at one frequency is approximately 50 s and an image is created within 2 h using the single-frequency reconstruction algorithm. The performance of the system is illustrated by an analysis of the standard deviations in amplitude and phase of a series of measurements as well as by a simple image reconstruction example.

关键词： computer vision and image processing techniques noninvasive breast-cancer detection Microwaves and other electromagnetic waves (medical uses) Biology and medical computing medical image processing Optical, image and video signal processing image reconstruction transceiving channels noise figure 2.3 dB Patient diagnostic methods and instrumentation single-frequency reconstruction algorithm electromagnetic wave scattering microwave imaging electronic scanning 3D inverse electromagnetic scattering problem cancer Microwaves and other electromagnetic waves (biomedical imaging/measurement) frequency 0.3 GHz to 3 GHz Electromagnetic wave propagation object detection microwave three-dimensional imaging system gain 97 dB

来源：评论

学校读者我要写书评

暂无评论

Computationally efficient algorithm for face super-resolution using (2D)²-PCA based prior

引用

IET image processing 2010年第2期4卷 61-69页

作者： Kumar, B. G. Vijay Aravind, R. Indian Inst Technol Dept Elect Engn Madras 600036 Tamil Nadu India

Super-resolution algorithms typically transform images into 1D vectors and operate on these vectors to obtain a high-resolution image. In this study, the authors first propose a 2D method for super-resolution using a 2D model that treats images as matrices. We then apply this 2D model to the super-resolution of face images. Two-directional two-dimensional principal component analysis (PCA) [(2D)(2)-PCA] is an efficient face representation technique where the images are treated as matrices instead of vectors. We use (2D)(2)-PCA to learn the face subspace and use it as a prior to super-resolve face images. Experimental results show that our approach can reconstruct high quality face images with low computational cost.

关键词： image resolution image representation image recognition face representation technique PCA face recognition image transformation computer vision and image processing techniques principal component analysis face super-resolution image Other topics in statistics

来源：评论

学校读者我要写书评

暂无评论

Frequency-domain weighted-least-squares design of quadratic interpolators

引用

IET SIGNAL processing 2010年第1期4卷 102-111页

作者： Deng, T. -B. Toho Univ Dept Informat Sci Fac Sci Chiba 2748510 Japan

Existing finite-support interpolators are derived from continuities in the time-domain. In this study, the authors optimally design a quadratic interpolator using two second-degree piecewise polynomials in the frequency-domain. The optimal coefficients of the piecewise polynomials are found by minimising the weighted least-squares error between the ideal and actual frequency responses of the quadratic interpolator subject to a few constraints. Adjusting the weighting functions in different frequency bands can yield accurate frequency response in a specified passband and even can ignore 'don't care' bands so that various quadratic interpolators can be designed for interpolating various discrete signals containing different frequency components. One-dimensional and two-dimensional examples have shown that the quadratic interpolator can achieve much higher interpolation accuracy than the existing interpolators for wide-band signals, and various images have been tested to verify that the quadratic interpolator can achieve comparable interpolation accuracy as the Catmull-Rom cubic for narrow-band signals (images), but the computational complexity can be reduced to about 70%. Therefore both narrow-band and wide-band signals can be interpolated with high accuracy.

关键词： piecewise polynomials computer vision and image processing techniques interpolation wideband signals frequency-domain weighted-least-squares design quadratic interpolators Interpolation and function approximation (numerical analysis) second-degree piecewise polynomials computational complexity Optical, image and video signal processing least squares approximations discrete signals finite-support interpolators image processing Catmull-Rom cubic

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：