检索结果-内蒙古大学图书馆

A multi-layer image operator learning based on sample structure for staff lines removal

APPLIED INTELLIGENCE 2023年第7期53卷 8436-8452页

作者： Xiao, Zhe Chen, Xin Zhou, Li China Univ Geosci Sch Automat Wuhan 430074 Peoples R China Hubei Key Lab Adv Control & Intelligent Automat C Wuhan 430074 Peoples R China China Univ Geosci Sch Arts & Commun Wuhan 430074 Peoples R China

The removal of staff lines is the most significant step to separate notes from the score images in optical music recognition (OMR). However, musical images are often affected by different deformations, and it is difficult to delete the staff lines completely without affecting the integrity of the notes. A novel multi-layer image operator learning algorithm based on sample structure is proposed in this paper to solve the problem of staff lines deletion. Our algorithm is dedicated to obtain the structural characteristics of staff lines via image operator learning. Firstly, an iterative strategy is proposed to update the distribution of the samples for learning multiple image operators with different sample structure features. Further, based on the learned image operators, a multi-layer image operators network is designed to obtain the optimal combination of multiple operators. Finally, we have verified the feasibility of our algorithm on the data set 2013 ICDAR/GREC staff lines removal competition. The experiment shows that the proposed algorithm is robust against many kinds of deformation. Moreover, our algorithm is more competitive by comparing with state-of-the-art algorithms.

关键词： Staff lines removal Optical music recognition image operators learning document image processing

来源：评论

学校读者我要写书评

暂无评论

Spatialising uncertainty in image segmentation using weakly supervised convolutional neural networks: a case study from historical map processing

引用

IET image processing 2018年第11期12卷 2084-2091页

作者： Uhl, Johannes H. Leyk, Stefan Chiang, Yao-Yi Duan, Weiwei Knoblock, Craig A. Univ Colorado Dept Geog Guggenheim 110260 UCB Boulder CO 80309 USA Univ Southern Calif Spatial Sci Inst 3616 Trousdale Pkwy Los Angeles CA USA Univ Southern Calif Informat Sci Inst 4676 Admiralty Way Marina Del Rey CA 90292 USA

Convolutional neural networks (CNNs) such as encoder-decoder CNNs have increasingly been employed for semantic image segmentation at the pixel-level requiring pixel-level training labels, which are rarely available in real-world scenarios. In practice, weakly annotated training data at the image patch level are often used for pixel-level segmentation tasks, requiring further processing to obtain accurate results, mainly because the translation invariance of the CNN-based inference can turn into an impeding property leading to segmentation results of coarser spatial granularity compared with the original image. However, the inherent uncertainty in the segmented image and its relationships to translation invariance, CNN architecture, and classification scheme has never been analysed from an explicitly spatial perspective. Therefore, the authors propose measures to spatially visualise and assess class decision confidence based on spatially dense CNN predictions, resulting in continuous decision confidence surfaces. They find that such a visual-analytical method contributes to a better understanding of the spatial variability of class score confidence derived from weakly supervised CNN-based classifiers. They exemplify this approach by incorporating decision confidence surfaces into a processing chain for the extraction of human settlement features from historical map documents based on weakly annotated training data using different CNN architectures and classification schemes.

关键词： image resolution data visualisation Neural computing techniques visual-analytical method image patch level encoder-decoder CNN class decision confidence document image processing feedforward neural nets historical map processing historical map documents image recognition weakly supervised CNN-based classifiers history Knowledge engineering techniques Computer vision and image processing techniques pixel-level training labels human settlement feature extraction translation invariance image segmentation image classification spatial granularity feature extraction document processing techniques weakly supervised convolutional neural networks spatialising uncertainty CNN-based inference inference mechanisms semantic image segmentation cartography Geography and cartography computing weakly annotated training data Graphics techniques continuous decision confidence surfaces class score confidence spatial variability pixel-level segmentation tasks classification scheme

来源：评论

学校读者我要写书评

暂无评论

AdOtsu: An adaptive and parameterless generalization of Otsu's method for document image binarization

引用

PATTERN RECOGNITION 2012年第6期45卷 2419-2431页

作者： Moghaddam, Reza Farrahi Cheriet, Mohamed Ecole Technol Super Synchromedia Lab Multimedia Commun Telepresence Montreal PQ H3C 1K3 Canada

Adaptive binarization methods play a central role in document image processing. In this work, an adaptive and parameterless generalization of Otsu's method is presented. The adaptiveness is obtained by combining grid-based modeling and the estimated background map. The parameterless behavior is achieved by automatically estimating the document parameters, such as the average stroke width and the average line height. The proposed method is extended using a multiscale framework, and has been applied on various datasets, including the DIBCO'09 dataset, with promising results. (C) 2011 Elsevier Ltd. All rights reserved.

关键词： document image processing Binarization Adaptive methods

来源：评论

学校读者我要写书评

暂无评论

Rigid image registration via column sparse optimisation for seal registration

引用

ELECTRONICS LETTERS 2013年第17期49卷 1069-1070页

作者： Guo, Quan Zhang, Lei Wang, Sheng Yi, Zhang Sichuan Univ Coll Comp Sci Machine Intelligence Lab Chengdu 610065 Peoples R China

image registration is an essential and important process in seal identification. Rigid image registration in seal identification is known to be more suitable than elastic registration. The registration process is quite sensitive to outliers in matched feature point pairs. A novel method to take the matching outliers as data corrupted by 'sample-specific' error which can be modelled by a column sparse matrix is proposed. An optimisation problem is developed to describe this model. By solving the optimisation problem, corruption can be eliminated and the transformation model can be recovered simultaneously. An efficient algorithm called column sparse registration is given via the augmented Lagrange multiplier method. Experiments on real-world seal registration data demonstrate that the proposed method is robust to outliers among matched pairs and outperforms the state-of-the-art methods.

关键词： column sparse registration ALM method rigid image registration sparse matrices Algebra image matching document processing techniques document image processing transformation model corruption elimination optimisation column sparse optimisation seal registration feature extraction sample-specific error Computer vision and image processing techniques feature point pair matching column sparse matrix augmented Lagrange multiplier method image registration seal identification Optimisation techniques image recognition

来源：评论

学校读者我要写书评

暂无评论

Partitioning of feature space by iterative classification for degraded document image binarisation

引用

IET image processing 2012年第6期6卷 804-812页

作者： Valizadeh, M. Kabir, E. Tarbiat Modares Univ Dept Elect & Comp Engn Tehran Iran

Proper partitioning of feature space into text and background regions is very important in document image binarisation. This study presents an iterative classification algorithm that efficiently partitions a two-dimensional feature space into text and background regions. It uses the result of Niblack's binarisation algorithm as training data and employs its characteristics to define classification rules. In each iteration, it labels only some points of the feature space, which can be classified reliably and leaves the classification of other points to the next iterations. The classification result of a point in current iteration affects the classification of its neighbours in the next iterations and makes them more probable to be classified correctly. After a few iterations, it partitions the feature space into two regions associated with the text and background pixels. After partitioning, two global thresholding methods were used as an extra text class refinement to make the proposed algorithm robust against bleeding-through and shadow-through degradations. Finally, each pixel is labelled as either text or background according to its corresponding region in the feature space. The authors' binarisation algorithm demonstrated superior performance against six well-known algorithms on three datasets. It is appropriate for various types of degraded images.

关键词： iterative classification text class refinement Pattern recognition feature space partitioning degraded document image binarisation Computer vision and image processing techniques shadow-through degradation bleeding-through degradation feature extraction iterative methods Interpolation and function approximation (numerical analysis) document processing techniques Optical, image and video signal processing document image processing pattern classification global thresholding methods Niblack binarisation algorithm

来源：评论

学校读者我要写书评

暂无评论

Automatic logo detection from document image using HOG features

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第1期82卷 863-878页

作者： Dixit, Umesh D. Shirdhonkar, M. S. Sinha, G. R. BLDEAs VP Dr PG Halakatti Coll Engn & Technol Dept Elect & Commun Engn Vijayapur 586103 Karnataka India BLDEAs VP Dr PG Halakatti Coll Engn & Technol Dept Comp Sci & Engn Vijayapur 586103 Karnataka India Myanmar Inst Informat Technol MIIT Mandalay Myanmar

document image analysis and processing has drawn the attention of many researchers due to its real-time applications in day-to-day life. document database comprising of logo provides a good opportunity for an easier way of indexing, searching and retrieval of the documents. Logo detection is an essential need for the implementation of any logo-based document indexing or retrieval techniques. This paper aims to develop an efficient logo detection method for document images. The major steps employed in the developed system include preprocessing of the input document, finding the connected components and classification of these components into the logo and non-logo candidates. The preprocessing step employs a median filter and a unique procedure for the removal of clutter noise to reduce the false detection rate. Histogram of Oriented Gradient (HOG) features and an SVM classifier are used to identify the logo and non-logo candidates of the document. The presented system is evaluated using Tobacco 800 dataset and the results are compared with existing techniques. The results show an improvement of 5% in average logo detection rate with the proposed work.

关键词： Connected components Logo detection document image processing HOG SVM Logo detection rate

来源：评论

学校读者我要写书评

暂无评论

Weighting scheme for image retrieval based on bag-of-visual-words

引用

IET image processing 2014年第9期8卷 509-518页

作者： Zhu, Lei Jin, Hai Zheng, Ran Feng, Xiaowen Huazhong Univ Sci & Technol Sch Comp Sci & Technol Cluster & Grid Comp Lab Serv Comp Technol & Syst Lab Wuhan 430074 Peoples R China

Inspired by the success of bag-of-words in text retrieval, bag-of-visual-words and its variants are widely used in content-based image retrieval to describe visual content. Various weighting schemes have also been proposed to integrate different yet complementary visual-words. However, most of these weighting schemes tend to use fixed weight for every visual-word extracted from the query image, which may lose the discriminative information. This study presents a novel combining method which captures query-specific weights for visual-words in query image. The method mainly contains two stages. Firstly, in offline weight learning, the authors introduce a linear classifier to build a query-category mapping table, and max-margin learning to build category-weight mapping table. Query-category mapping table is used to map the query image to the most likely image class, and category-weight mapping table is used to map image class to the weights of visual-words. Secondly, in online weight mapping, the weights of visual-words are determined efficiently by looking into the prelearned mapping tables. Experimental results on WANG database and Caltech 101 demonstrate that the proposed weighting scheme can effectively weight visual-words of query image according to their discriminative information. In addition, comparative experiments demonstrate the proposed weighting scheme can obtain higher retrieval performance than other weighting schemes.

关键词： weight mapping bag-of-visual-words word processing weight learning text analysis document image processing visual word extraction visual content category weight mapping table content-based image retrieval query image linear classifler weighting scheme Computer vision and image processing techniques Knowledge engineering techniques Optical, image and video signal processing content-based retrieval query specific weight image classification Information retrieval techniques document processing techniques max-margin learning query category mapping table text retrieval learning (artificial intelligence) image retrieval

来源：评论

学校读者我要写书评

暂无评论

Handwritten document image segmentation into text lines and words

引用

PATTERN RECOGNITION 2010年第1期43卷 369-377页

作者： Papavassiliou, Vassilis Stafylakis, Themos Katsouros, Vassilis Carayannis, George Inst Language & Speech Proc RC Athena Artemidos 6 GR-15125 Maroussi Greece Natl Tech Univ Athens Sch Elect & Comp Engn GR-15780 Athens Greece

Two novel approaches to extract text lines and words from handwritten document are presented. The line segmentation algorithm is based on locating the optimal succession of text and gap areas within vertical zones by applying Viterbi algorithm. Then, a text-line separator drawing technique is applied and finally the connected components are assigned to text lines. Word segmentation is based on a gap metric that exploits the objective function of a soft-margin linear SVM that separates successive connected components. The algorithms tested on the benchmarking datasets of ICDAR07 handwriting segmentation contest and outperformed the participating algorithms. (C) 2009 Elsevier Ltd. All rights reserved.

关键词： Handwritten text line segmentation Handwritten word segmentation document image processing Viterbi estimation Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Stroke width-based directional total variation regularisation for document image super resolution

引用

IET image processing 2016年第2期10卷 158-166页

作者： Abedi, Ali Kabir, Ehsanollah Tarbiat Modares Univ Dept Elect & Comp Engn Tehran Iran

In the Bayesian image super resolution (SR), a regularisation term is minimised along with a data-fidelity term to generate a high-resolution (HR) image from input low-resolution (LR) image. The regularisation term is incorporated into the SR to fulfil a prior knowledge over the HR image. For instance, smoothness in the background and foreground regions is a prior knowledge about document images. The bilateral total variation (BTV), as a known regularisation term, uniformly smooths the image in all directions while preserving the edges. In this study, the authors present a document image SR method by introducing a new regularisation term called the stroke width-based directional total variation (SWDTV). It is a modified version of the BTV, and adaptively performs smoothing based on the local width and local direction of the character strokes. By analysing the input LR image and its interpolation, the local stroke width and local stroke direction in the output image are approximated. This information is encapsulated into the SWDTV regularisation term. By minimising the linear combination of the regularisation and data-fidelity terms, the HR image is reconstructed. The authors' method achieves significant improvements in visual image quality and optical character recognition accuracy compared to related non-example-based document image SR methods.

关键词： image resolution document image processing Bayes methods variational techniques smoothing methods edge detection interpolation data encapsulation image reconstruction stroke width-based directional total variation regularisation document image super resolution Bayesian image super resolution bilateral total variation BTV uniform image smoothing edge preservation document image SR method LR image analysis interpolation local direction local width SWDTV regularisation information encapsulation HR image reconstruction visual image quality improvement

来源：评论

学校读者我要写书评

暂无评论

A document image Model and Estimation Algorithm for Optimized JPEG Decompression

引用

IEEE TRANSACTIONS ON image processing 2009年第11期18卷 2518-2535页

作者： Wong, Tak-Shing Bouman, Charles A. Pollak, Ilya Fan, Zhigang Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA Xerox Corp Xerox Res & Technol Webster NY 14580 USA

The JPEG standard is one of the most prevalent image compression schemes in use today. While JPEG was designed for use with natural images, it is also widely used for the encoding of raster documents. Unfortunately, JPEG's characteristic blocking and ringing artifacts can severely degrade the quality of text and graphics in complex documents. We propose a JPEG decompression algorithm which is designed to produce substantially higher quality images from the same standard JPEG encodings. The method works by incorporating a document image model into the decoding process which accounts for the wide variety of content in modern complex color documents. The method works by first segmenting the JPEG encoded document into regions corresponding to background, text, and picture content. The regions corresponding to text and background are then decoded using maximum a posteriori (MAP) estimation. Most importantly, the MAP reconstruction of the text regions uses a model which accounts for the spatial characteristics of text and graphics. Our experimental comparisons to the baseline JPEG decoding as well as to three other decoding schemes, demonstrate that our method substantially improves the quality of decoded images, both visually and as measured by PSNR.

关键词： Decoding document image processing image enhancement image reconstruction image segmentation JPEG

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：