检索结果-内蒙古大学图书馆

Human perception-based image segmentation using optimising of colour quantisation

IET IMAGE PROCESSING 2014年第12期8卷 761-770页

作者： Cho, Sung In Kang, Suk-Ju Kim, Young Hwan Pohang Univ Sci & Technol POSTECH Dept Elect Engn Pohang 790784 South Korea Dong A Univ Dept Elect Engn Pusan 604714 South Korea

This study presents an advanced histogram-based image segmentation method that enhances image segmentation quality, while greatly reducing the computational complexity. Unlike existing histogram-based methods, the authors optimise the size of bins in the colour histogram by using human perception-based colour quantisation and the clustering centroids are selected effectively without using a complex process. Additionally, an over-segmentation removal technique based on connected-component labelling is employed. This improves the segmentation quality by connectivity analysis. A comparison between the experimental results on the berkeley segmentation dataset by the proposed method and the benchmark methods demonstrated that the proposed method enhanced the segmentation quality by improving the Probabilistic Rand Index and the segmentation Covering values compared with those of the benchmark methods. The computation time using the proposed method is reduced by up to 91.63% compared with the computation time using benchmark methods.

关键词： image segmentation image colour analysis quantisation (signal) computational complexity image enhancement pattern clustering probability human perception-based image segmentation colour quantisation optimization advanced histogram-based image segmentation method image segmentation quality enhancement computational complexity colour histogram clustering centroids over-segmentation removal technique connected-component labelling connectivity analysis berkeley segmentation dataset probabilistic rand index segmentation covering values

来源：评论

学校读者我要写书评

暂无评论

Matrix completion via capped nuclear norm

引用

IET IMAGE PROCESSING 2018年第6期12卷 959-966页

作者： Zhang, Fanlong Yang, Zhangjing Chen, Yu Yang, Jian Yang, Guowei Nanjing Audit Univ Sch Technol Nanjing Jiangsu Peoples R China Nanjing Univ Sci & Technol Dept Comp Sci & Technol Nanjing Jiangsu Peoples R China

Matrix completion is to recover a low-rank matrix from a subset of its entries. One of the solution strategies is based on nuclear norm minimisation. However, since the nuclear norm is defined as the sum of all singular values, each of which is treated equally, the rank function may not be well approximated in practice. To overcome this drawback, this study presents a matrix completion method based on capped nuclear norm (MC-CNN). The capped nuclear norm can reflect the rank function more directly and accurately than the nuclear norm, Schatten p-norm (to the power p) and truncated nuclear norm. The relation between the capped nuclear norm and the truncated nuclear norm is revealed for the first time. Difference of convex functions' programming is employed to solve MC-CNN. In the proposed algorithm, a key sub-problem, i.e. a matrix completion problem with linear regularisation term, is solved by using the active subspace selection method. In addition, the algorithm convergence is discussed. Experimental results show encouraging results of the proposed algorithm in comparison with the state-of-the-art matrix completion methods on both synthetic and real visual datasets.

关键词： image segmentation singular value decomposition convergence matrix completion capped nuclear norm low-rank matrix recovery nuclear norm minimisation singular values rank function MC-CNN Schatten p-norm truncated nuclear norm convex function programming linear regularisation term active subspace selection method algorithm convergence synthetic visual datasets real visual datasets berkeley segmentation dataset

来源：评论

学校读者我要写书评

暂无评论

Multi-nature hierarchical approach for natural image segmentation with pattern refinement feedback

引用

NEUROCOMPUTING 2013年 99卷 325-338页

作者： Diaz-Pernas, F. J. Anton-Rodriguez, M. Martinez-Zarzuela, M. Perozo-Rondon, F. J. Gonzalez-Ortega, D. Univ Valladolid Dept Signal Theory Commun & Telemat Engn Telecommun Engn Sch Valladolid Spain Univ Valladolid Dept Syst Engn & Automat Valladolid Spain Univ Valladolid Higher Sch Telecommun Engn Valladolid Spain Univ Carabobo Sch Sci & Technol Valencia Venezuela Univ Carabobo Comp Lab Grad Sch Engn Valencia Venezuela

A hierarchical learning method for segmenting natural images is proposed in this paper. This approach combines the perceptual information of three natures - colour, texture, and homogeneity - in order to segment natural colour images. These low-level features are extracted using a multiple scale neural architecture we previously proven in [1,20]. Present approach incorporates the human knowledge to a hierarchical categorisation process, where the features of the three natures are independently categorised. The final segmentation is achieved through pattern refinement cycles. The approach is compared to other two significant natural scene segmentation methods, achieving better results in a global evaluation. These comparisons are performed using the berkeley segmentation dataset. (c) 2012 Elsevier B.V. All rights reserved.

关键词： Natural image segmentation Hierarchical neural network Supervised categorisation ARTMAP models Pattern refinement berkeley segmentation dataset

来源：评论

学校读者我要写书评

暂无评论

A Spatially Variant Motion Blur Removal Technique for Single Image Deblurring 11

A Spatially Variant Motion Blur Removal Technique for Single...

引用

11th Annual IEEE India Conference (INDICON)

作者： Deshpande, Ashwini M. Patnaik, Suprava Sardar Vallabhbhai Natl Inst Technol Dept Elect Engn Surat Gujarat India Xavier Inst Engn Dept Elect & Telecommun Engn Mumbai MS India

ISBN: (纸本)9781479953646

This paper presents an effective single image spatially variant motion blur removal technique. Motion blur during the image capture occurs due to the relative motion between the capturing device and image being captured. This blur becomes spatially variant if it varies with position in an image. Removal of such space/shift variant blur from a single image is a challenging problem. To solve this problem, the blurred image is divided into smaller subimages assuming that each subimage is uniformly blurred. In the proposed technique each subimage is transformed into frequency domain for estimating motion blur parameters. Proposed blur parameter estimation implies dual Fourier spectrum computation and Radon transformation steps to obtain estimated values of blur length and blur angle respectively. These estimated motion blur parameters are used to prepare a local parametric blur model. These local parametric blur models are deconvolved with the blurry subimages and thus restores the original image. Restoration step is performed using parametric Wiener filtering. However, due to piecewise uniform consideration, proposed technique introduces some blocking artifacts which are later removed by applying post processing steps on the restored image. To demonstrate the usefulness of this technique for natural scenes and real blurred images it is tested on berkeley segmentation dataset and standard test images. The proposed technique shows effective deblurring of images under spatial variance conditions.

关键词： Radon transforms Wiener filters image restoration motion estimation berkeley segmentation dataset Radon transformation blocking artifacts blur angle blur length blurry subimages dual Fourier spectrum computation image deblurring local parametric blur model motion blur parameter estimation parametric Wiener filtering piecewise uniform consideration single image deblurring spatially variant motion blur removal technique Deconvolution Estimation Frequency-domain analysis Image edge detection Image restoration Kernel Transforms

来源：评论

学校读者我要写书评

暂无评论

Image segmentation Using Linked Mean-Shift Vectors for SIMD Architecture

Image Segmentation Using Linked Mean-Shift Vectors for SIMD ...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Cho, HanJoo Cho, Sung In Kim, Young Hwan POSTECH Dept Elect Engn Pohang South Korea

ISBN: (纸本)9781479912919

This paper presents a new mean-shift based segmentation algorithm for single instruction multiple data (SIMD) architecture. A standard mean-shift algorithm has different number of computations for each pixel because the end-points of each pixel's iteration process are different, thus a standard mean-shift algorithm is hard to be accelerated using SIMD architecture. The proposed algorithm, however, equalizes the number of computations for each pixel by constructing links between pixels using their first mean-shift vectors without iteration process. It makes the proposed algorithm more suitable for the SIMD architecture without a complicated scheduling module. Experimental results using the berkeley segmentation dataset show the proposed algorithm successfully equalizes the number of computations with reasonable segmentation quality.

关键词： image segmentation parallel processing berkeley segmentation dataset SIMD architecture image segmentation iteration process linked mean shift vectors single instruction multiple data architecture Acceleration Bandwidth Clustering algorithms Computer architecture Image segmentation Standards Vectors

来源：评论

学校读者我要写书评

暂无评论

INCORPORATING TEXTURE INFORMATION INTO REGION-BASED UNSUPERVISED IMAGE segmentation USING TEXTURAL SUPERPIXELS

INCORPORATING TEXTURE INFORMATION INTO REGION-BASED UNSUPERV...

引用

IEEE International Conference on Image Processing

作者： Chih-Yu Hsu Yi-Yu Hsieh Kuo-Hua Lo Jen-Hui Chuang Inst. of Comput. Sci. & Eng. Nat. Chiao Tung Univ. Hsinchu Taiwan

ISBN: (纸本)9781479957521

Recently, an unsupervised image segmentation framework, segmentation by Aggregating Superpixels (SAS) is proposed and shown to be very promising. However, the texture cues, which have been shown to be very effective in many researches, are not used. In this paper, we propose an effective method for incorporating texture information into the SAS framework, using superpixels. To extract texture information, our algorithm first uses texture filtering and subsequently GMM clustering. Then, we develop an edge-aware low-pass filtering to generate multiple-scale textural superpixels (TXSPs) from the clustering results. Finally, by joining TXSPs with the superpixel set originally used in SAS, the incorporation of texture information is accomplished. Our method achieves superior performance on the berkeley segmentation dataset (BSDS300) under several evaluation criteria when compared to other benchmark algorithms.

关键词： Gaussian processes feature extraction filtering theory image resolution image segmentation image texture low-pass filters pattern clustering unsupervised learning BSDS300 berkeley segmentation dataset GMM clustering SAS framework edge-aware low-pass filtering multiple-scale textural superpixel generation region-based unsupervised image segmentation framework segmentation-by-aggregating superpixels texture cues texture filtering texture information extraction Benchmark testing Computer vision Filter banks Image segmentation Pattern recognition Synthetic aperture sonar Superpixel Texture Unsupervised image segmentation

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：