检索结果-内蒙古大学图书馆

13th International Conference on Document Analysis and recognition, ICDAR 2015

作者： Mondal, Tanmoy Ragot, Nicolas Ramel, Jean-Yves Pal, Umapada Tours France Indian Statistical Institute Computer Vision and Pattern Recognition Unit Kolkata India

ISBN: (纸本)9781479918058

In word spotting literature, classical DTW has been widely employed. However there exists several other improved versions of DTW along with other robust sequence matching techniques. Very few of them have been studied in the context of word spotting and this scarcity of research work is the motivation of the paper. This paper presents a comparative study of classical Dynamic Time Warping (DTW) technique and many of its improved modifications, as well as other sequence matching techniques in the context of word spotting. An experimental study on historical documents is performed to evaluate the behavior of DTW's variants and other sequence matching techniques. A detailed comparative analysis along with wide range of experimentation is performed, which shows that classical DTW remains a good choice when there are no segmentation problems and when features are very local. In case of word segmentation errors, Continuous Dynamic Programming (CDP) seems to be a better choice. This research work has introduced several other improved sequence matching algorithms in the context of word spotting, which show interesting and improved results. © 2015 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

A complete system for detection and recognition of text in graphical documents using background information

A complete system for detection and recognition of text in g...

引用

4th International Conference on computer vision Theory and Applications, VISAPP 2009

作者： Roy, Partha Pratim Lladòs, Josep Pal, Umapada Spain Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata - 108 India

ISBN: (纸本)9789898111692

Automatic Text/symbols retrieval in graphical documents (map, engineering drawing) involves many challenges because they are not usually parallel to each other. They are multi-oriented and curve in nature to annotate the graphical curve lines and hence follow a curvi-linear way too. Sometimes, text and symbols frequently touch/overlap with graphical components (river, street, border line) which enhances the problem. For OCR of such documents we need to extract individual text lines and their corresponding words/characters. In this paper, we propose a methodology to extract individual text lines and an approach for recognition of the extracted text characters from such complex graphical documents. The methodology is based on the foreground and background information of the text components. To take care of background information, water reservoir concept and convex hull have been used. For recognition of multi-font, multi-scale and multi-oriented characters, Support Vector Machine (SVM) based classifier is applied. Circular ring and convex hull have been used along with angular information of the contour pixels of the characters to make the feature rotation and scale invariant.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Semi-automatic segmentation of tissue cells from confocal microscope images

Semi-automatic segmentation of tissue cells from confocal mi...

引用

13th International Conference on pattern recognition, ICPR 1996

作者： Adiga, P. S. Umesh Chaudhuri, B.B. Rodenacker, Karstein Computer Vision and Pattern Recognition Unit Indian Statistical Institute Calcutta 35 India Germany

ISBN: (纸本)081867282X

We present a semi-automatic method for extracting the 3D boundary of the cells in a compact tissue cross-section photographed by a confocal microscope. The confocal microscope provides pictures at different depths of the cells which can be considered as the image slices of the tissue section. Segmentation of cell boundary from different image slices and combining them to obtain 3D surface automatically is a difficult task. We have developed an approach where given one segmented image slice, the other image slices can be automatically segmented in a layered approach. The idea is to use the information of the previous segmented image slice for segmenting the current image slice. © 1996 IEEE.

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Kernel-based recognition of human actions using spatiotemporal salient points

Kernel-based recognition of human actions using spatiotempor...

引用

2006 Conference on computer vision and pattern recognition Workshops

作者： Oikonomopoulos, A. Patras, I. Pantic, M. Computing Department Imperial College London Computer Vision and Pattern Recognition Group University of York

ISBN: (纸本)0769526462

This paper addresses the problem of human action recognition by introducing a sparse representation of image sequences as a collection of spatiotemporal events that are localized at points that are salient both in space and time. We detect the spatiotemporal salient points by measuring the variations in the information content of pixel neighborhoods not only in space but also in time. We derive a suitable distance measure between the representations, which is based on the Chamfer distance, and we optimize this measure with respect to a number of temporal and scaling parameters. In this way we achieve invariance against scaling, while at the same time, we eliminate the temporal differences between the representations. We use Relevance Vector Machines (RVM) in order to address the classification problem. We propose new kernels for use by the RVM, which are specifically tailored to the proposed spatiotemporal salient point representation. The basis of these kernels is the optimized Chamfer distance of the previous step. We present results on real image sequences from a small database depicting people performing 19 aerobic exercises. © 2006 IEEE.

关键词： pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Clustered semi-supervised relevance feedback 15

Clustered semi-supervised relevance feedback

引用

24th ACM International Conference on Information and Knowledge Management, CIKM 2015

作者： Ghosh, Kripabandhu Parui, Swapan Kumar Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata West Bengal India

ISBN: (纸本)9781450337946

In relevance feedback, first-round search results are used to boost second-round search results. Two forms have been traditionally considered: exhaustively labelled feedback, where all first-round results to depth k arc annotated for relevance by the user;and blind feedback, where the top-k results arc all assumed to be relevant. In this paper, we consider an intermediate, semi-supervised scheme, in which only a subset of results is selected for annotation, and then their labels are propagated to their nearest neighbours. Specifically, we use clustering to determine the nearest-neighbour groups, and seed selection to choose documents for annotation. We find that the effectiveness of this method is indistinguishable from the exhaustive relevance feedback, and is significantly higher than both blind feedback and the use of the annotated subset alone. We show that this approach works well in environments in which some but limited amounts of human feedback arc available, such as early case assessment in e-discovcry. © 2015 ACM.

关键词： relevance assessment cluster hypothesis e-discovery

来源：评论

学校读者我要写书评

暂无评论

Revisiting the Generalization Problem of Low-level vision Models Through the Lens of Image Deraining

arXiv

引用

arXiv 2025年

作者： Hu, Jinfan You, Zhiyuan Gu, Jinjin Zhu, Kaiwen Xue, Tianfan Dong, Chao Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China The Chinese University of Hong Kong 999077 Hong Kong The University of Sydney NSW2006 Australia Shanghai Jiao Tong University Shanghai200240 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Shenzhen University of Advanced Technology Shenzhen518055 China

Generalization remains a significant challenge for low-level vision models, which often struggle with unseen degradations in real-world scenarios despite their success in controlled benchmarks. In this paper, we revisit the generalization problem in low-level vision models. Image deraining is selected as a case study due to its well-defined and easily decoupled structure, allowing for more effective observation and analysis. Through comprehensive experiments, we reveal that the generalization issue is not primarily due to limited network capacity but rather the failure of existing training strategies, which lead networks to overfit specific degradation patterns. Our findings show that guiding networks to focus on learning the underlying image content, rather than the degradation patterns, is key to improving generalization. We demonstrate that balancing the complexity of background images and degradations in the training data helps networks better fit the image distribution. Furthermore, incorporating content priors from pre-trained generative models significantly enhances generalization. Experiments on both image deraining and image denoising validate the proposed strategies. We believe the insights and solutions will inspire further research and improve the generalization of low-level vision models. Copyright © 2025, The Authors. All rights reserved.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Blind Image Inpainting via Omni-dimensional Gated Attention and Wavelet Queries

Blind Image Inpainting via Omni-dimensional Gated Attention ...

引用

2023 IEEE/CVF Conference on computer vision and pattern recognition Workshops, CVPRW 2023

作者： Phutke, Shruti S. Kulkarni, Ashutosh Vipparthi, Santosh Kumar Murala, Subrahmanyam Indian Institute of Technology Ropar Computer Vision and Pattern Recognition Lab Punjab Rupnagar India

ISBN: (纸本)9798350302493

Blind image inpainting is a crucial restoration task that does not demand additional mask information to restore the corrupted regions. Yet, it is a very less explored research area due to the difficulty in discriminating between corrupted and valid regions. There exist very few approaches for blind image inpainting which sometimes fail at producing plausible inpainted images. Since they follow a common practice of predicting the corrupted regions and then inpaint them. To skip the corrupted region prediction step and obtain better results, in this work, we propose a novel end-to-end architecture for blind image inpainting consisting of wavelet query multi-head attention transformer block and the omni-dimensional gated attention. The proposed wavelet query multi-head attention in the transformer block provides encoder features via processed wavelet coefficients as query to the multi-head attention. Further, the proposed omni-dimensional gated attention effectively provides all dimensional attentive features from the encoder to the respective decoder. Our proposed approach is compared numerically and visually with existing state-of-the-art methods for blind image inpainting on different standard datasets. The comparative and ablation studies prove the effectiveness of the proposed approach for blind image inpainting. The testing code is available at : https://***/shrutiphutke/Blind-Omni-Wav-Net © 2023 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Bangla pronouns - a corpus based study

引用

Literary and Linguistic Computing 2000年第4期15卷 433-444页

作者： Dash, Ns Computer Vision and Pattern Recognition Unit Indian Statistical Institute Calcutta 700035 203 Barrackpore Trunk Road India

Bangla is the second most widely spoken language in the Indian subcontinent, yet has not been the focus of much research activity in either corpus linguistics or language engineering to date. This paper describes the automatic processing of pronouns in three and a half million words of Bangla corpus data. A corpus-based analysis of Bangla pronouns is developed, and a new approach to the analysis of Bangla pronouns is taken as a consequence. On the basis of this analysis a system is then developed to identify and analyse Bangla pronouns in corpus data. © 2000 Oxford University Press.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Touching text character localization in graphical documents using SIFT

Touching text character localization in graphical documents ...

引用

8th IAPR Workshop on Graphics recognition, GREC 2009

作者： Roy, Partha Pratim Pal, Umapada Lladós, Josep 08193 Spain Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata 108 India

ISBN: (纸本)364213727X

Interpretation of graphical document images is a challenging task as it requires proper understanding of text/graphics symbols present in such documents. Difficulties arise in graphical document recognition when text and symbol overlapped/touched. Intersection of text and symbols with graphical lines and curves occur frequently in graphical documents and hence separation of such symbols is very difficult. Several pattern recognition and classification techniques exist to recognize isolated text/symbol. But, the touching/overlapping text and symbol recognition has not yet been dealt successfully. An interesting technique, Scale Invariant Feature Transform (SIFT), originally devised for object recognition can take care of overlapping problems. Even if SIFT features have emerged as a very powerful object descriptors, their employment in graphical documents context has not been investigated much. In this paper we present the adaptation of the SIFT approach in the context of text character localization (spotting) in graphical documents. We evaluate the applicability of this technique in such documents and discuss the scope of improvement by combining some state-of-the-art approaches. © 2010 Springer-Verlag.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

A fast correlation attack for LFSR-based stream ciphers

A fast correlation attack for LFSR-based stream ciphers

引用

1st International Conference on Applied Cryptography and Network Security, ACNS 2003

作者： Palit, Sarbani Roy, Bimal K. De Arindom Computer Vision and Pattern Recognition Unit Indian Statistical Institute India Applied Statistics Unit Indian Statistical Institute India Computer Vision and Pattern Recognition Unit Indian Statistical Institute India

ISBN: (纸本)3540202080

This paper describes a novel fast correlation attack of stream ciphers. The salient feature of the algorithm is the absence of any pre-processing or iterative phase, an usual feature of existing fast correlation attacks. The algorithm attempts to identify a number of bits of the original linear feedback shift register (LFSR) output from the received bits of the ciphertext. These are then used to construct a system of linear equations which are subsequently solved to obtain the initial conditions. The algorithm is found to perform well for LFSRs of large sizes but having sparse polynomials. It may be noted that such polynomials have low Hamming weight which is one more than the number of feedback connections or "taps" of the corresponding LFSR. Its performance is good in situations even where limited cipherlength is available. Another important contribution of the paper is a modification of the approach when the LFSR outputs are combined by a function which is correlation immune and perhaps, unknown to the decrypter. © Springer-Verlag Berlin Heidelberg 2003.

关键词： Polynomials

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

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

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：