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

Robust face recognition with partial occlusion, illumination variation and limited training data by optimal feature selection

引用

IET computer vision 2011年第1期5卷 23-32页

作者： Lin, J. Ming, J. Crookes, D. Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu 610054 Peoples R China Queens Univ Belfast Sch Elect Elect Engn & Comp Sci Belfast BT7 1NN Antrim North Ireland

This study investigates face recognition with partial occlusion, illumination variation and their combination, assuming no prior information about the mismatch, and limited training data for each person. The authors extend their previous posterior union model (PUM) to give a new method capable of dealing with all these problems. PUM is an approach for selecting the optimal local image features for recognition to improve robustness to partial occlusion. The extension is in two stages. First, authors extend PUM from a probability-based formulation to a similarity-based formulation, so that it operates with as little as one single training sample to offer robustness to partial occlusion. Second, they extend this new formulation to make it robust to illumination variation, and to combined illumination variation and partial occlusion, by a novel combination of multicondition relighting and optimal feature selection. To evaluate the new methods, a number of databases with various simulated and realistic occlusion/illumination mismatches have been used. The results have demonstrated the improved robustness of the new methods.

关键词： illumination variation Other topics in statistics face recognition image recognition robust face recognition probability-based formulation limited training data optimal feature selection similarity-based formulation probability computer vision and image processing techniques optimal local image features posterior union model partial occlusion

来源：评论

学校读者我要写书评

暂无评论

Elimination of gridlines by using non-linear filter in mammographic image

引用

IET image processing 2011年第5期5卷 457-465页

作者： Maruyama, T. Yamamoto, H. Okayama Univ Grad Sch Hlth Sci Kita Ku Okayama 7008558 Japan Kibikogen Rehabil Ctr Employment Injuries Kibichuou Okayama 7161241 Japan

Mammographic X-ray equipment uses a radiographic grid to remove the scatter radiation and improve image contrast. The grid causes striped lines to appear on the film and may degrade diagnostic information. This study deals with the mechanism of the gridline appearance, the gridline image on the mammographic film, and a method for eliminating the gridlines. In this study, the background noise caused by the radiographic grid is investigated by using a one-dimensional Fourier transform and the characteristics of the gridlines on the X-ray film are clarified. In addition, a new method that reduces the background noise caused by the radiographic grid on mammographic film is proposed by using non-linear image filtering. To eliminate gridlines effectively, the region of the filter is considered and V-filtering and median filtering are performed as methods of image filtering. In an experiment using a breast phantom, a signal-to-noise ratio (SNR) in the microcalcification region is calculated. The SNR of the image processed by median filtering after the V-filtering is increased. The value of the power spectrum at a frequency that represents the periodic noise made by the gridlines is decreased. The validity of image filtering is confirmed. This proposed image-filtering method is found to be useful for eliminating gridlines in the X-ray image.

关键词： mammography image SNR V-filtering phantoms Patient diagnostic methods and instrumentation microcalcification region nonlinear image filtering 1D Fourier transform Biology and medical computing computer vision and image processing techniques Digital filters signal-noise ratio diagnostic information degradation Optical, image and video signal processing diagnostic radiography background noise reduction median filters gridline image appearance mechanism mammographic X-ray equipment breast phantom nonlinear filter scatter radiation removal image contrast improvement Fourier transforms gridline elimination X-ray techniques: radiography and computed tomography (biomedical imaging/measurement) mammographic image medical image processing image denoising Integral transforms in numerical analysis X-rays and particle beams (medical uses) radiographic grid median filtering

来源：评论

学校读者我要写书评

暂无评论

Combined significance map coding for still image compression

引用

IET image processing 2011年第1期5卷 55-62页

作者： Wang, Y-L. Wang, J. -X. Su, A. W. Y. Natl Cheng Kung Univ Dept CSIE Tainan 70101 Taiwan

Set partitioning in hierarchical trees (SPIHT) was known for its relatively simple implementation and flexible scalability when it is combined with discrete wavelet transform (DWT). The authors propose a method called combined significance map coding (CSMC) to improve the coding efficiency of SPIHT when used with block-based discrete cosine transform (DCT). CSMC groups some blocks and encodes the combined significance map of one to several blocks together. Lots of bits spent in significance map coding can be saved when the trees constructed with block DCT coefficients have similar locality. From our simulation results, CSMC improves significantly when in comparison with the original SPIHT coder using DWT and DCT. It also yields better performance than JPEG2000, and even outperforms the non-scalable H. 264 intra-mode coder for some test images. No coding table is required, and fine rate/quality scalability property of SPIHT is still preserved.

关键词： discrete cosine transforms SPIHT coder block-based discrete cosine transform discrete wavelet transform data compression computer vision and image processing techniques image and video coding still image compression image coding Integral transforms discrete wavelet transforms set partitioning JPEG2000 trees (mathematics) set theory Combinatorial mathematics hierarchical trees nonscalable H.264 intra-mode coder combined significance map coding

来源：评论

学校读者我要写书评

暂无评论

Fast encoding method for vector quantisation of images using subvector characteristics and Hadamard transform

引用

IET image processing 2011年第1期5卷 18-24页

作者： Chen, S. X. Li, F. W. Chongqing Univ Posts & Telecommun Commun & Informat Engn Coll Chongqing 400056 Peoples R China

In a framework of vector quantisation (VQ), the encoding speed is a key issue for its practical applications. To speed up the VQ encoding process, a fast encoding method in the Hadamard transform domain is presented. In the proposed method, a five-step test flow based on two characteristic values, the first element and variance of the transformed subvector, is introduced to reject a large number of unlikely codewords. In order to make full use of the energy-compaction property of an orthogonal transform, the partial distance search (PDS) method is used in its Steps 4 and 5. Experimental results show that the proposed algorithm outperforms most of the existing algorithms, especially in case of larger codebook size and high-detail images.

关键词： five-step test flow Codes high-detail images energy compaction property VQ encoding process orthogonal transform subvector variance image and video coding subvector characteristics computer vision and image processing techniques Hadamard transforms image coding Hadamard transform fast encoding method partial distance search method Integral transforms images quantisation vector quantisation

来源：评论

学校读者我要写书评

暂无评论

Efficient fusion for infrared and visible images based on compressive sensing principle

引用

IET image processing 2011年第2期5卷 141-147页

作者： Li, X. Qin, S. -Y. Beihang Univ Sch Automat Sci & Elect Engn Beijing 100191 Peoples R China

In this study, the potential application of compressive sensing (CS) principle in the image fusion for infrared (IR) and visible images is studied. First, the theory of CS is introduced briefly. Some comparative analyses of different reconstruction techniques are carried out in view of their performance in multisensor image recovery and the minimum number of sampling measurements one has to take to achieve perfectly reconstruction of images is investigated afterwards. Then, a novel self-adaptive weighted average fusion scheme based on standard deviation of measurements to merge IR and visible images is developed in the special domain of CS using the better recovery tool of total variation optimisation. Both the subjective visual effect and objective evaluation indicate that the presented method enhances the definition of fused results greatly, and it achieves a high level of fusion quality in human perception of global information. On the other hand, no structure priori information about the original images is required and only some concise fusion computation of compressive measurements is needed in the authors' proposed algorithm, thus it has superiority in saving computation resources and enhancing the fusion efficiency.

关键词： variation optimisation fusion quality compressive sensing principle image reconstruction techniques human perception image reconstruction standard deviation image sampling computer vision and image processing techniques infrared images image fusion self-adaptive weighted average fusion scheme Optical, image and video signal processing objective evaluation visible images sampling measurements subjective visual effect multisensor image recovery comparative analyses

来源：评论

学校读者我要写书评

暂无评论

Reversible and high-capacity data hiding in medical images

引用

IET image processing 2011年第2期5卷 190-197页

作者： Fallahpour, M. Megias, D. Ghanbari, M. Univ Oberta Catalunya Barcelona Spain Univ Essex Sch Comp Sci & Elect Engn Colchester CO4 3SQ Essex England

In this study, the authors introduce a highly efficient reversible data hiding system. It is based on dividing the image into tiles and shifting the histograms of each image tile between its minimum and maximum frequency. Data are then inserted at the pixel level with the largest frequency to maximise data hiding capacity. It exploits the special properties of medical images, where the histogram of their non-overlapping image tiles mostly peak around some grey values and the rest of the spectrum is mainly empty. The zeros (or minima) and peaks (maxima) of the histograms of the image tiles are then relocated to embed the data. The grey values of some pixels are therefore modified. High capacity, high fidelity, reversibility and multiple data insertions are the key requirements of data hiding in medical images. The authors show how histograms of image tiles of medical images can be exploited to achieve these requirements. Compared to the data hiding method applied to the whole image, the authors' scheme can result in 30-200% capacity improvement and still with better image quality, depending on the medical image content. Additional advantages of the proposed method include hiding data in the regions of non-interest and better exploitation of spatial masking.

关键词： health physics image quality Patient diagnostic methods and instrumentation medical image content spatial masking nonoverlapping image tiles Biology and medical computing computer vision and image processing techniques data encapsulation Data handling techniques Optical, image and video signal processing high-capacity data hiding grey values reversible data hiding medical image processing Biomedical measurement and imaging histograms Medical and biomedical uses of fields, radiations, and radioactivity grey systems

来源：评论

学校读者我要写书评

暂无评论

New method for generating site-specific clutter map for land-based radar by using multimodal remote-sensing images and digital terrain data

引用

IET RADAR SONAR AND NAVIGATION 2011年第3期5卷 374-388页

作者： Kurekin, A. Radford, D. Lever, K. Marshall, D. Shark, L. -K. Plymouth Marine Lab Plymouth PL1 3DH Devon England Gen Dynam UK Oakdale NP12 4AA Blackwood Wales Cardiff Univ Commun Res Ctr Cardiff CF24 0YF S Glam Wales Cardiff Univ Dept Comp Sci Cardiff CF24 3AA S Glam Wales Univ Cent Lancashire ADSIP Res Ctr Preston PR1 2HE Lancs England

By using multimodal remote-sensing images and digital terrain data of the environment, this study presents a new method for generating the clutter map specific to the selected land radar site and the radar's operating parameters. In the proposed method, the estimation of backscattering from the environment involves extrapolation of the airborne radar remote-sensing image to provide the baseline values, classification of multispectral remote-sensing satellite images to provide a detailed description of terrain types, use of digital terrain elevation data with the land radar position and height to provide local grazing angles and a terrain visibility map and use of the digital topographic map to provide the geometric reference for all data sets. Using actual remote-sensing images and digital terrain data acquired from a real environment with various terrain features, the clutter map generated by the proposed method for land-based radar is compared with that generated by the competitive modelling method. The accuracy of the proposed method is demonstrated based on the differences with respect to the actual clutter measurements using a different airborne radar-sensing configuration.

关键词： computer vision and image processing techniques Geophysical techniques and equipment Geography and cartography computing comprehensive modelling method site-specific clutter map Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research radar imaging local grazing angles backscattering estimation multimodal remote-sensing images Optical, image and video signal processing digital topographic map terrain mapping Radar equipment, systems and applications multispectral remote-sensing satellite image classification clutter measurements remote sensing by radar terrain visibility map backscatter land radar position land-based radar radar clutter digital terrain data airborne radar

来源：评论

学校读者我要写书评

暂无评论

Segmentation of noisy colour images using Cauchy distribution in the complex wavelet domain

引用

IET image processing 2011年第2期5卷 159-170页

作者： Wan, T. Canagarajah, N. Achim, A. Beijing Normal Univ Sch Informat Sci & Technol Beijing 100875 Peoples R China Univ Bristol Dept Elect & Elect Engn CCR Bristol BS8 1UB Avon England

This study proposes a novel image segmentation technique for noisy colour images, in which the heavy-tailed characteristics of the image are modelled by Cauchy distributions. First, the RGB colour bands of the noisy image are decomposed into multiresolution representations using the dual-tree complex wavelet transform. For each wavelet subband, a model is built assuming that the input coefficients are contaminated with signal-independent additive white Gaussian noise. Hence, the authors derive an estimation rule in the wavelet domain to obtain the noise-free coefficients based on the bivariate Cauchy distribution. The bivariate model makes it possible to exploit the inter-scale dependencies of wavelet coefficients. Subsequently, the image is roughly segmented into textured and non-textured regions using the bivariate model parameters corresponding to the denoised coefficients. A multiscale segmentation is then applied to the resulting regions. Finally, a novel statistical region merging algorithm is introduced by measuring the Kullback-Leibler distance between the estimated Cauchy models for the neighbouring segments. The experiments demonstrate that the authors algorithm yields robust segmentation results for noisy images containing artificial or natural noise.

关键词： multiscale segmentation image colour analysis wavelet subband denoised coefficient wavelet coefficient multiresolution representation signal-independent additive white Gaussian noise noise-free coefficient computer vision and image processing techniques RGB colour bands statistical region merging algorithm bivariate Cauchy distribution Optical, image and video signal processing Integral transforms Cauchy model image segmentation complex wavelet domain noisy colour image segmentation wavelet transforms bivariate model parameter Kullback-Leibler distance robust segmentation dual-tree complex wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Blur identification with assumption validation for sensor-based video reconstruction and its implementation on field programmable gate array

引用

IET computerS AND DIGITAL techniques 2011年第4期5卷 271-286页

作者： Angelopoulou, M. E. Bouganis, C-S. Cheung, P. Y. K. Univ London Imperial Coll Sci Technol & Med Dept Elect & Elect Engn London SW7 2BT England

Restoration methods, such as super-resolution (SR), largely depend on the accuracy of the point spread function (PSF). PSF estimation is an ill-posed problem, and a linear and uniform motion is often assumed. In real-life systems, this may deviate significantly from the actual motion, impairing subsequent restoration. To address the above, this work proposes a dynamically configurable imaging system that combines algorithmic video enhancement, field programmable gate array (FPGA)-based video processing and adaptive image sensor technology. Specifically, a joint blur identification and validation (BIV) scheme is proposed, which validates the initial linear and uniform motion assumption. For the cases that significantly deviate from that assumption, the real-time reconfiguration property of an adaptive image sensor is utilised, and the sensor is locally reconfigured to larger pixels that produce higher frame-rate samples with reduced blur. Results demonstrate that once the sensor reconfiguration gives rise to a valid motion assumption, highly accurate PSFs are estimated, resulting in improved SR reconstruction quality. To enable real-time reconstruction, an FPGA-based BIV architecture is proposed. The system's throughput is significantly higher than 25 fps, for frame sizes up to 1024 x 1024, and its performance is robust to noise for signal-to-noise ratio (SNR) as low as 20 dB.

关键词： adaptive image sensor technology algorithmic video enhancement Video signal processing Logic and switching circuits point spread function imaging techniques autocorrelation-based blur identification framework Logic circuits image reconstruction sensor-based video reconstruction method field programmable gate arrays passive cameras Optical, image and video signal processing high-throughput hardware architecture computer vision and image processing techniques image enhancement field programmable gate array image motion analysis joint blur identification and validation scheme image sensors improved SR reconstruction quality image sensors system throughput signal-to-noise ratio

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：