检索结果-内蒙古大学图书馆

International Workshop on Frontiers in Handwriting recognition

作者： Soumik Bhattacharya Durjoy Sen Maitra Ujjwal Bhattacharya Swapan K. Parui Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9781509009824

A few studies of online Bangla handwriting recognition such as isolated character recognition or limited vocabulary cursive word recognition are found in the literature. However, development of an end-to-end recognition system of unconstrained online Bangla handwritten texts has not been duly attempted so far. In the present report, we describe a similar system which takes a piece of continuous online handwritten Bangla texts as the input. It first segments the input texts into individual lines, each line into its constituent words and each word into sub-strokes. In the present study, 152 different symbols which include basic characters, character modifiers, frequently used conjunct characters, a few special characters and numerals have been considered. The entire set of sub-strokes obtained from the training sample set has been exhaustively studied by 3 experts and 76 different shapes of sub-strokes have been identified based on consensus among these experts. Also, it has been observed that a character may produce at most 3 sub-strokes. Since a piece of Bangla texts often contains either Bangla or English numerals, the present character set consists of both the numeral set and 3 numeral shapes are common to both the scripts. The proposed recognition system uses two classifiers, one for characters and the other for sub-strokes. Sub-strokes are fed to the character classifier in their temporal order. A single sub-stroke followed by two consecutive sub-strokes and finally three successive sub-strokes are passed to the character classifier and the first two top responses of the character classifier among the three cases are compared. If the difference is less than a threshold, the response of sub-stroke classifier is used to reach a final decision. The proposed system provided 94.3% character level accuracy on a test set consisting of 33,453 word samples written by 31 writers.

关键词： Handwriting recognition Character recognition Shape Text recognition Support vector machines Vocabulary Trajectory

来源：评论

学校读者我要写书评

暂无评论

Fast and efficent multimodal eye biometrics using projective dictionary pair learning

Fast and efficent multimodal eye biometrics using projective...

引用

2016 IEEE Congress on Evolutionary Computation, CEC 2016

作者： Das, Abhijit Mondal, Prabir Pal, Umapada Ferrer, Miguel Angel Blumenstein, Michael Institute for Integrated and Intelligent Systems Griffith University QLD Australia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India IDeTIC University of Las Palmas de Gran Canaria Las Palmas Spain School of Software University of Technology Sydney Australia

ISBN: (纸本)9781509006229

This work proposes a projective pairwise dictionary learning-based approach for fast and efficient multimodal eye biometrics. The work uses a faster Projective pairwise Discriminative Dictionary Learning (DL) in contrast to the traditional DL which uses synthesis DL. Projective Pairwise Discriminative Dictionary (PPDD) uses a synthesis dictionary and an analysis dictionary jointly to achieve the goal of pattern representation and discrimination. As the PPDD process of DL is in contrast to the use of l0 or l1-norm sparsity constraints on the representation coefficients adopted in most traditional DL, it works faster than other DL. Moreover, the blending of synthesis dictionary and an analysis dictionary also enhance the feature representation of the complex eye patterns. We employed the combination of sclera and iris traits to establish multimodal biometrics. The experimental study and analysis conducted fulfill the hypothesis we considered. In this work we employed a part of the UBIRIS version 1 dataset to conduct the experiments. © 2016 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Collaborative representation based fine-grained species recognition

Collaborative representation based fine-grained species reco...

引用

International Conference on Image and vision Computing New Zealand, IVCNZ

作者： Tapabrata Chakraborti Brendan McCane Steven Mills Umapada Pal Department of Computer Science University of Otago Dunedin New Zealand Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9781509027491

Fine-grained Visual Categorization (FGVC) is an open problem in computer vision due to subtle differences between categories. The present paper demonstrates that Collaborative Representation based Classification (CRC) can address this problem successfully. Instead of the traditional discriminative approach of classification, CRC takes a co-operative approach by representing the query image as a weighted collaboration of training images across all classes in the feature space. The superior performance of CRC compared to some other modern classifiers including SVM is shown in this work using several popular descriptors like GIST+Color, SIFT and CNN features with Species recognition chosen as the representative FGVC problem. Besides experiments on the Oxford 102 Flowers and CUB200-2011 Bird benchmarks, the present work also introduces a new challenging dataset NZ Birds v1.0 with 600 images of 30 New Zealand endemic and native bird species.

关键词： Birds Collaboration Training Visualization Image recognition Face recognition Cost function

来源：评论

学校读者我要写书评

暂无评论

引用

International Conference on pattern recognition

作者： Anjan Dutta Umapada Pal Josep Lladós Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Computer Science Dept. Universitat Autònoma de Barcelona Bellaterra Spain

ISBN: (纸本)9781509048489

This paper considers the offline signature verification problem which is considered to be an important research line in the field of pattern recognition. In this work we propose hybrid features that consider the local features and their global statistics in the signature image. This has been done by creating a vocabulary of histogram of oriented gradients (HOGs). We impose weights on these local features based on the height information of water reservoirs obtained from the signature. Spatial information between local features are thought to play a vital role in considering the geometry of the signatures which distinguishes the originals from the forged ones. Nevertheless, learning a condensed set of higher order neighbouring features based on visual words, e.g., doublets and triplets, continues to be a challenging problem as possible combinations of visual words grow exponentially. To avoid this explosion of size, we create a code of local pairwise features which are represented as joint descriptors. Local features are paired based on the edges of a graph representation built upon the Delaunay triangulation. We reveal the advantage of combining both type of visual codebooks (order one and pairwise) for signature verification task. This is validated through an encouraging result on two benchmark datasets viz. CEDAR and GPDS300.

关键词： Feature extraction Reservoirs Histograms Visualization Forgery

来源：评论

学校读者我要写书评

暂无评论

An Automatic Off-Line Short Answer Assessment System Using Novel Hybrid Features

An Automatic Off-Line Short Answer Assessment System Using N...

引用

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Hemmaphan Suwanwiwat Umapada Pal Michael Blumenstein College of Business James Cook University Australia Computer Vision and Pattern Recognition Unit Indian Statistical Institute India School of Software University of Technology Sydney Australia

To date, paper-based examinations are still in use worldwide on all levels of education levels (e.g. secondary, tertiary levels). However, literature regarding off-line automatic assessment systems employing off-line handwriting recognition is not numerous. This paper proposes an off-line automatic assessment system employing a hybrid feature extraction technique - a newly proposed Modified Direction and Gaussian Grid Feature (MDGGF), along with its enhanced technique. In this study other original feature extraction techniques, together with their enhanced features, were also used for feature extraction technique efficiency comparison purposes. Classifiers, namely artificial neural networks and support vector machines, were selected to be employed in the experiments. Two types of datasets were employed in the experiment for both feature extraction technique accuracy and efficiency comparisons. The best correctly recognised rate of 98.33% with 100% accuracy was obtained when employing the proposed MDGGF to the off-line automatic assessment system.

关键词： Feature extraction Gravity Training Testing Artificial neural networks Support vector machines Handwriting recognition

来源：评论

学校读者我要写书评

暂无评论

Automatic Hyperlinking of Engineering Drawing Documents

Automatic Hyperlinking of Engineering Drawing Documents

引用

IAPR International Workshop on Document Analysis Systems, DAS

作者： Purnendu Banerjee Sumit Choudhary Supriya Das Himadri Majumdar Rahul Roy Bidyut B. Chaudhuri ARC Document Solutions Kolkata India Computer Vision and Pattern Recongnition Unit Indian Statistical Institute Kolkata

In construction or manufacturing industry, engineering drawings are used as blueprint or plan documents to facilitate the construction or manufacturing process. A fairly large construction project involves very large number of these documents, divided into different sub-sections. An engineer or architect often needs to refer different documents while preparing a new one or marking some irregularity in some document. Therefore they need to navigate through different files. It becomes an extremely difficult and time consuming task to move from one file to another in an interactive way. This paper describes an automated technique to access information from the existing drawing documents and create hyperlinks in order to enable the engineers to quickly navigate between files. The overall accuracy of our system for a class of documents is a decent 94.46%.

关键词： Shape Optical character recognition software Engineering drawings Transforms Engines Image edge detection

来源：评论

学校读者我要写书评

暂无评论

Offline handwritten Devanagari word recognition: Information fusion at feature and classifier levels 3

Offline handwritten Devanagari word recognition: Information...

引用

3rd IAPR Asian Conference on pattern recognition, ACPR 2015

作者： Shaw, Bikash Bhattacharya, Ujjwal Parui, Swapan Kumar Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India

ISBN: (纸本)9781479961009

This article presents our recent study on fusion of information at feature and classifier output levels for improved performance of offline handwritten Devanagari word recognition. We consider here two state-of-the-art features, viz., Directional Distance Distribution (DDD) and Gradient-Structural-Concavity (GSC) features along with multi-class SVM classifiers. Here, we study various combinations of DDD features along with one or more features from the GSC feature set. We experiment by presenting different combined feature vectors as input to SVM classifiers. Also, the output vectors of different SVM classifiers fed with different feature vectors are combined by another SVM classifier. The combination of the outputs of two SVMs each being fed with a different feature vector provides superior performance to the performance of a single SVM classifier fed with the combined feature vector. Experimental results are obtained on a large handwritten Devanagari word sample image database of 100 indian town names. The recognition results on its test samples show that SVM recognition output of DDD features combined with the SVM output of GSC features improves the final recognition accuracy significantly. © 2015 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Exemplary Sequence Cardinality: An effective application for word spotting 13

Exemplary Sequence Cardinality: An effective application for...

引用

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

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

ISBN: (纸本)9781479918058

In this paper proposed. ESC combines several abilities of other sequence matching algorithms e.g. DTW, SSDTW, CDP, FSM, MVM, OSB1. Depending on the application domain, ESC can be tuned to∗∗a new sequence matching algorithm called as Exemplary Sequence Cardinality (ESC) is behave such as these different sequence matching algorithms. Its generality and robustness comes from its ability to find subsequences (as in CDP and SSDTW), to skip outliers inside the target sequences (as in MVM and FSM) and also in the query sequence (as in OSB ) and it has the ability to have many to one and one to many correspondences (as in DTW) between the elements of the query and the target sequences. It's special characteristic of skipping noisy elements from query sequence along with other afore mentioned properties gives it an edge over FSM. In case of word spotting application, the outliers skipping capability of ESC makes it less sensible to local variations in the spelling of words, and also to noise present in the query and/or in the target word images. Due to it's capability of sub-sequence matching, the ESC algorithm has the ability to retrieve a query inside a line or piece of line. Finally, its multiple matching facilities (many to one and one to many matching) is proven to be well advantageous in case of different length of target and query sequences due to the variability in scale, font, type/size factors. By experimenting on printed historical document images, we have demonstrated the interest of proposed ESC algorithm in specific cases when incorrect word segmentation and word level local variations occur regularly. © 2015 IEEE.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Global investments in pandemic preparedness and COVID-19: development assistance and domestic spending on health between 1990 and 2026

引用

The Lancet Global Health 2023年第3期11卷 e385-e413页

作者： Micah, Angela E. Bhangdia, Kayleigh Cogswell, Ian E. Lasher, Dylan Lidral-Porter, Brendan Maddison, Emilie R. Nguyen, Trang Nhu Ngoc Patel, Nishali Pedroza, Paola Solorio, Juan Stutzman, Hayley Tsakalos, Golsum Wang, Yifeng Warriner, Wesley Zhao, Yingxi Zlavog, Bianca S. Abbafati, Cristiana Abbas, Jaffar Abbasi-Kangevari, Mohsen Abbasi-Kangevari, Zeinab Abdelmasseh, Michael Abdulah, Deldar Morad Abedi, Aidin Abegaz, Kedir Hussein Abhilash, E.S. Aboagye, Richard Gyan Abolhassani, Hassan Abrigo, Michael R.M. Abubaker Ali, Hiwa Abu-Gharbieh, Eman Adem, Mohammed Hussien Afzal, Muhammad Sohail Ahmadi, Ali Ahmed, Haroon Ahmed Rashid, Tarik Aji, Budi Akbarialiabad, Hossein Akelew, Yibeltal Al Hamad, Hanadi Alam, Khurshid Alanezi, Fahad Mashhour Alanzi, Turki M. Al-Hanawi, Mohammed Khaled Alhassan, Robert Kaba Aljunid, Syed Mohamed Almustanyir, Sami Al-Raddadi, Rajaa M. Alvis-Guzman, Nelson Alvis-Zakzuk, Nelson J. Amare, Azmeraw T. Ameyaw, Edward Kwabena Amini-Rarani, Mostafa Amu, Hubert Ancuceanu, Robert Andrei, Tudorel Anwar, Sumadi Lukman Appiah, Francis Aqeel, Muhammad Arabloo, Jalal Arab-Zozani, Morteza Aravkin, Aleksandr Y. Aremu, Olatunde Aruleba, Raphael Taiwo Athari, Seyyed Shamsadin Avila-Burgos, Leticia Ayanore, Martin Amogre Azari, Samad Baig, Atif Amin Bantie, Abere Tilahun Barrow, Amadou Baskaran, Pritish Basu, Sanjay Batiha, Abdul-Monim Mohammad Baune, Bernhard T. Berezvai, Zombor Bhardwaj, Nikha Bhardwaj, Pankaj Bhaskar, Sonu Boachie, Micheal Kofi Bodolica, Virginia Botelho, João Silva Botelho Braithwaite, Dejana Breitborde, Nicholas J.K. Busse, Reinhard Cahuana-Hurtado, Lucero Catalá-López, Ferrán Chansa, Collins Charan, Jaykaran Chattu, Vijay Kumar Chen, Simiao Chukwu, Isaac Sunday Dadras, Omid Dandona, Lalit Dandona, Rakhi Dargahi, Abdollah Debela, Sisay Abebe Denova-Gutiérrez, Edgar Desye, Belay Dharmaratne, Samath Dhamminda Diao, Nancy Doan, Linh Phuong Dodangeh, Milad dos Santos, Wendel Mombaque Doshmangir, Leila Dube, John Eini, Ebrahim El Sayed Zaki, Maysaa El Tantawi, Maha Enyew, Daniel Berhanie Institute for Health Metrics and Evaluation University of Washington Seattle WA United States Department of Applied Mathematics University of Washington Seattle WA United States Department of Health Metrics Sciences School of Medicine University of Washington Seattle WA United States Nuffield Department of Medicine University of Oxford Oxford United Kingdom Department of Juridical and Economic Studies La Sapienza University Rome Italy Antai College of Economics Shanghai Jiao Tong University Shanghai China Non-communicable Diseases Research Center Tehran University of Medical Sciences Tehran Iran Research Center for Immunodeficiencies Tehran University of Medical Sciences Tehran Iran Multiple Sclerosis Research Center Tehran University of Medical Sciences Tehran Iran Children’s Medical Center Tehran University of Medical Sciences Tehran Iran Department of Epidemiology and Biostatistics Tehran University of Medical Sciences Tehran Iran Tehran Heart Center Tehran University of Medical Sciences Tehran Iran Faculty of Medicine Tehran University of Medical Sciences Tehran Iran National Institute for Health Research Tehran University of Medical Sciences Tehran Iran Department of Pharmacology Tehran University of Medical Sciences Tehran Iran Department of Cardiology Tehran University of Medical Sciences Tehran Iran Sina Trauma and Surgery Research Center Tehran University of Medical Sciences Tehran Iran Digestive Diseases Research Institute Tehran University of Medical Sciences Tehran Iran Department of Neurology Tehran University of Medical Sciences Tehran Iran Social Determinants of Health Research Center Shahid Beheshti University of Medical Sciences Tehran Iran Department of Epidemiology Shahid Beheshti University of Medical Sciences Tehran Iran Department of Health Economics and Statistics Shahid Beheshti University of Medical Sciences Tehran Iran Department of Neurosurgery Shahid Beheshti University of Medical Sciences Tehran Iran Ophthalmic R

Background: The COVID-19 pandemic highlighted gaps in health surveillance systems, disease prevention, and treatment globally. Among the many factors that might have led to these gaps is the issue of the financing of national health systems, especially in low-income and middle-income countries (LMICs), as well as a robust global system for pandemic preparedness. We aimed to provide a comparative assessment of global health spending at the onset of the pandemic;characterise the amount of development assistance for pandemic preparedness and response disbursed in the first 2 years of the COVID-19 pandemic;and examine expectations for future health spending and put into context the expected need for investment in pandemic preparedness. Methods: In this analysis of global health spending between 1990 and 2021, and prediction from 2021 to 2026, we estimated four sources of health spending: development assistance for health (DAH), government spending, out-of-pocket spending, and prepaid private spending across 204 countries and territories. We used the Organisation for Economic Co-operation and Development (OECD)'s Creditor Reporting System (CRS) and the WHO Global Health Expenditure Database (GHED) to estimate spending. We estimated development assistance for general health, COVID-19 response, and pandemic preparedness and response using a keyword search. Health spending estimates were combined with estimates of resources needed for pandemic prevention and preparedness to analyse future health spending patterns, relative to need. Findings: In 2019, at the onset of the COVID-19 pandemic, US$9·2 trillion (95% uncertainty interval [UI] 9·1–9·3) was spent on health worldwide. We found great disparities in the amount of resources devoted to health, with high-income countries spending $7·3 trillion (95% UI 7·2–7·4) in 2019;293·7 times the $24·8 billion (95% UI 24·3–25·3) spent by low-income countries in 2019. That same year, $43·1 billion in development assistance was provided

关键词：

来源：评论

学校读者我要写书评

暂无评论

Writer Identification from offline isolated Bangla characters and numerals 13

Writer Identification from offline isolated Bangla character...

引用

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

作者： Adak, Chandranath Chaudhuri, Bidyut B. Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India

ISBN: (纸本)9781479918058

Writer identification is an essential component in computational forensic. In this paper, we attempt to do this job based only on isolated characters and numerals. For that, at first, some points of interest (keypoints) on the image are detected by structural analysis and SIFT based detector. Then we calculate a set of features within a certain neighborhood of the keypoint and employ fusion rule on multiple probabilistic SVM classifiers output for writer identification. For experimental analysis, a database containing 212,300 isolated Bangla orthosyllabic characters and numerals are generated with the help of 100 writers. We obtain fairly good result to identify a writer. We also try to find a small set of highly discriminative characters storing extra information about the writing style of an individual. © 2015 IEEE.

关键词： handwriting recognition natural language processing probability support vector machines Bangla orthosyllabic characters SIFT based detector computational forensic isolated Bangla characters isolated Bangla numerals isolated characters multiple probabilistic SVM classifiers structural analysis writer identification Chlorine Discriminative Bangla character Handwriting analysis Writer identification Numerals handwriting recognition structural analysis Structural analysis Support Vector Network Natural Language Processing Writers Chlorine

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：