检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Chattopadhyay, Soumitri Manna, Siladittya Bhattacharya, Saumik Pal, Umapada Dept. of Information Technology Jadavpur University Kolkata India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Dept. of Electronics and Electrical Communication Engineering Indian Institute of Technology Kharagpur India

Offline Signature Verification (OSV) is a fundamental biometric task across various forensic, commercial and legal applications. The underlying task at hand is to carefully model fine-grained features of the signatures to distinguish between genuine and forged ones, which differ only in minute deformities. This makes OSV more challenging compared to other verification problems. In this work, we propose a two-stage deep learning framework that leverages self-supervised representation learning as well as metric learning for writer-independent OSV. First, we train an image reconstruction network using an encoder-decoder architecture that is augmented by a 2D spatial attention mechanism using signature image patches. Next, the trained encoder backbone is fine-tuned with a projector head using a supervised metric learning framework, whose objective is to optimize a novel dual triplet loss by sampling negative samples from both within the same writer class as well as from other writers. The intuition behind this is to ensure that a signature sample lies closer to its positive counterpart compared to negative samples from both intra-writer and cross-writer sets. This results in robust discriminative learning of the embedding space. To the best of our knowledge, this is the first work of using self-supervised learning frameworks for OSV. The proposed two-stage framework has been evaluated on two publicly available offline signature datasets and compared with various state-of-the-art methods. It is noted that the proposed method provided promising results outperforming several existing pieces of work. The code is publicly available at: https://***/soumitri2001/SURDS-SSL-OSV. © 2022, CC BY.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Machine Dating of Handwritten Manuscripts

Machine Dating of Handwritten Manuscripts

引用

International Conference on Document Analysis and recognition

作者： U. Garain S. Parui T. Paquet L. Heutte Computer Vision & Pattern Recognition Unit Indian Statistical Institute Kolkata India Laboratoire LITIS EA 4051 UFR des Sciences Université de Rouen Saint Etienne du Rouvray France

This paper presents a pioneering study on automatic dating of handwritten manuscripts. Analysis of handwriting style forms the core of the dating method. Initially, it is hypothesized that a manuscript can be dated, to a certain level of accuracy, by looking at the way it is written. The hypothesis is then verified with real samples of known dates. A general framework is proposed for machine dating of handwritten manuscripts. Experiments on a database containing manuscripts of Gustave Flaubert (1821- 1880), the famous French novelist reports about 62% accuracy when manuscripts are dated within a range of five calendar years with respect to their exact year of writing.

关键词： Testing Humans Calendars computer vision pattern recognition Databases Writing Watermarking Error analysis Libraries

来源：评论

学校读者我要写书评

暂无评论

ICDAR2019 robust reading challenge on multi-lingual scene text detection and recognition-RRC-MLT-2019 15

ICDAR2019 robust reading challenge on multi-lingual scene te...

引用

15th IAPR International Conference on Document Analysis and recognition, ICDAR 2019

作者： Nayef, Nibal Liu, Cheng-Lin Ogier, Jean-Marc Patel, Yash Busta, Michal Chowdhury, Pinaki Nath Karatzas, Dimosthenis Khlif, Wafa Matas, Jiri Pal, Umapada Burie, Jean-Christophe L3i Laboratory University of la Rochelle France Computer Vision Center Universitat Autonoma de Barcelona Spain CVPR Unit Indian Statistical Institute India Robotics Institute Carnegie Mellon Universiry Pittsburgh United States Center for Machine Perception Department of Cybernetics Czech Technical University Prague Czech Republic National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China

ISBN: (纸本)9781728128610

With the growing cosmopolitan culture of modern cities, the need of robust Multi-Lingual scene Text (MLT) detection and recognition systems has never been more immense. With the goal to systematically benchmark and push the state-of-the-art forward, the proposed competition builds on top of the RRC-MLT-2017 with an additional end-to-end task, an additional language in the real images dataset, a large scale multi-lingual synthetic dataset to assist the training, and a baseline End-to-End recognition method. The real dataset consists of 20,000 images containing text from 10 languages. The challenge has 4 tasks covering various aspects of multi-lingual scene text: (a) text detection, (b) cropped word script classification, (c) joint text detection and script classification and (d) end-to-end detection and recognition. In total, the competition received 60 submissions from the research and industrial communities. This paper presents the dataset, the tasks and the findings of the presented RRC-MLT-2019 challenge. © 2019 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Effective Document Image Enhancement Using tokens-to-token Transformer Network

SSRN

引用

SSRN 2023年

作者： Biswas, Risab Roy, Swalpa Kumar Pal, Umapada Maharashtra Mumbai400066 India Department of Computer Science and Engineering Jalpaiguri Government Engineering College West Bengal735102 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India

Document image enhancement is a fundamental and important stage for attaining the best performance in any document analysis assignment because there are many degradation situations that could harm document images, making it more difficult to recognize and analyze them. In this paper, we propose to employ a Tokens-to-Token Transformer net- work for document image enhancement, a novel encoder-decoder architecture based on a tokens-to-token vision transformer. The proposed architecture uses a tokens-to-token architecture in the encoder section. Each image is divided into a set of tokens with a de- fined length using the ViT model, which is then applied several times to model the global relationship between the tokens. However, the conventional tokenization of input data does not adequately reflect the crucial local structure between adjacent pixels of the input image, which results in low efficiency. Instead of using a simple ViT and hard splitting of images for the document image enhancement task, we employed a progressive tokeniza- tion technique to capture this local information from an image for achieving more ef- fective results. Experiments on various DIBCO and H-DIBCO benchmarks demonstrate that the proposed model outperforms the existing CNN and ViT-based state-of-the-art methods. In this research, the primary area of examination is the application of the pro- posed architecture to the task of document binarization. The source code will be made available at https://***/RisabBiswas/T2T-BinFormer. © 2023, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Signature segmentation and recognition from scanned documents

Signature segmentation and recognition from scanned document...

引用

International Conference on Intelligent Systems Design and Applications (ISDA)

作者： Ranju Mandal Partha Pratim Roy Umapada Pal Michael Blumenstein School of Information and Communication Technology Griffith University Queensland Australia Automation Engineering Department Synchromedia Lab Montreal Canada Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

Signature as a query is important for content-based document image retrieval from a scanned document repository. This paper presents a two-stage approach towards automatic signature segmentation and recognition from scanned document images. In the first stage, signature blocks are segmented from the document using word-wise component extraction and classification. Gradient based features are extracted from each component at the word level to perform the classification task. In the 2nd stage, SIFT (Scale-Invariant Feature Transform) descriptors and Spatial Pyramid Matching (SPM)-based approaches are used for signature recognition. Support Vector Machines (SVMs) are employed as the classifier for both levels in this experiment. The experiments are performed on the publicly available “Tobacco-800” and GPDS [1] datasets and the results obtained from the experiments are promising.

关键词： Image segmentation Industries Vector quantization Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

ICDAR 2019 CROHME + TFD: Competition on recognition of Handwritten Mathematical Expressions and Typeset Formula Detection

ICDAR 2019 CROHME + TFD: Competition on Recognition of Handw...

引用

International Conference on Document Analysis and recognition

作者： Mahshad Mahdavi Richard Zanibbi Harold Mouchere Christian Viard-Gaudin Utpal Garain Document and Pattern Recognition Lab Rochester Institute of Technology Rochester NY USA University of Nantes Nantes France LS2N - UMR CNRS 6004 University of Nantes Nantes France Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

We summarize the tasks, protocol, and outcome for the 6th Competition on recognition of Handwritten Mathematical Expressions (CROHME), which includes a new formula detection in document images task (+ TFD). For CROHME + TFD 2019, participants chose between two tasks for recognizing handwritten formulas from 1) online stroke data, or 2) images generated from the handwritten strokes. To compare LATEX strings and the labeled directed trees over strokes (label graphs) used in previous CROHMEs, we convert LATEX and stroke-based label graphs to label graphs defined over symbols (symbol-level label graphs, or symLG). More than thirty (33) participants registered for the competition, with nineteen (19) teams submitting results. The strongest formula recognition results were produced by the USTC-iFLYTEK research team, for both stroke-based (81%) and image-based (77%) input. For the new typeset formula detection task, the Samsung R&D institute Ukraine (Team 2) obtained a very strong F-score (93%). System performance has improved since the last CROHME - still, the competition results suggest that recognition of handwritten formulae remains a difficult structural pattern recognition task.

关键词： Task analysis Handwriting recognition Tools Measurement Layout Image recognition

来源：评论

学校读者我要写书评

暂无评论

Off-line Signature Identification Using Background and Foreground Information

Off-line Signature Identification Using Background and Foreg...

引用

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

作者： Srikanta Pal Alaei Alireza Umapada Pal Michael Blumenstein School of Information and Communication Technology Griffith University Gold Coast Australia Department of Studies in Computer Science University of Mysore Mysore India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

Biometric systems play an important role in the field of information security as they are extremely required for user authentication. Automatic signature recognition and verification is one of the biometric techniques, which is currently receiving renewed interest and is only one of several techniques used to verify the identities of individuals. Signatures provide a secure means for confirmation and authorization in legal documents. So nowadays, signature identification and verification becomes an essential component in automating the rapid processing of documents containing embedded signatures. In this paper, a technique for a bi-script off-line signature identification system is proposed. In the proposed signature identification system, the signatures of English and Bengali (Bangla) are considered for the identification process. Different features such as under sampled bitmaps, modified chain-code direction features and gradient features computed from both background and foreground components are employed for this purpose. Support Vector Machines (SVMs) and Nearest Neighbour (NN) techniques are considered as classifiers for signature identification in the proposed system. A database of 1554 English signatures and 1092 Bengali signatures are used to generate the experimental results. Various results based on different features are calculated and analysed. The highest accuracies of 99.41%, 98.45% and 97.75% are obtained based on the modified chain-code direction, under-sampled bitmaps and gradient features respectively using 1800 (1100 English+700 Bengali) samples for training and 846 (454 English+392 Bengali) samples for testing.

关键词： Feature extraction Support vector machines Handwriting recognition Training Educational institutions Kernel Databases

来源：评论

学校读者我要写书评

暂无评论

CRNN based jersey-bib number/text recognition in sports and marathon images 15

CRNN based jersey-bib number/text recognition in sports and ...

引用

15th IAPR International Conference on Document Analysis and recognition, ICDAR 2019

作者： Nag, Sauradip Ramachandra, Raghavendra Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Kankanhalli, Mohan Department of Computer Science & Engineering Kalyani Government Engineering College Kalyani India Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Norway Faculty of Computer System and Information Technology University of Malaya Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University China Department of Computer Science School of Computing National University of Singapore Singapore Singapore

ISBN: (纸本)9781728128610

The primary challenge in tracing the participants in sports and marathon video or images is to detect and localize the jersey/Bib number that may present in different regions of their outfit captured in cluttered environment conditions. In this work, we proposed a new framework based on detecting the human body parts such that both Jersey Bib number and text is localized reliably. To achieve this, the proposed method first detects and localize the human in a given image using Single Shot Multibox Detector (SSD). In the next step, different human body parts namely, Torso, Left Thigh, Right Thigh, that generally contain a Bib number or text region is automatically extracted. These detected individual parts are processed individually to detect the Jersey Bib number/text using a deep CNN network based on the 2-channel architecture based on the novel adaptive weighting loss function. Finally, the detected text is cropped out and fed to a CNN-RNN based deep model abbreviated as CRNN for recognizing jersey/Bib/text. Extensive experiments are carried out on the four different datasets including both bench-marking dataset and a new dataset. The performance of the proposed method is compared with the state-of-the-art methods on all four datasets that indicates the improved performance of the proposed method on all four datasets. © 2019 IEEE.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

Frequency-plane analysis of normal and pathological ECG signals for disease identification

引用

Journal of Medical Engineering and Technology 2005年第5期29卷 219-227页

作者： Mitra, S. Mitra, M. Chaudhuri, B.B. Department of Applied Physics Faculty of Technology University of Calcutta 92 APC Road Kolkata - 700009 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B.T. Road Kolkata - 700 108 India

In this paper a frequency plane analysis of both normal and diseased ECG signals is performed specifically for disease identification. Image processing techniques are used to develop an automated data acquisition package of 12 lead ECG signals from paper records. A regeneration domain is also developed to check the captured pattern with the original wave shape. A QRS complex detector with an accuracy level ∼98.4% in up to 30% signal to noise level is developed. Discrete Fourier transform (DFT) is performed to obtain the frequency spectrum of every ECG signal. Some interesting amplitude and phase response properties of chest lead V2, V3, V4, V6 and limb lead I, II, III, AVL, AVF are seen. Both amplitude and phase properties are different for normal and diseased subjects and can serve an important role in disease identification. A statistical analysis of amplitude property is carried out to show that this property is significantly different for normal and diseased subjects. © 2005 Taylor & Francis.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

A Layer-Wise Tokens-to-Token Transformer Network for Improved Historical Document Image Enhancement

arXiv

引用

arXiv 2023年

作者： Biswas, Risab Roy, Swalpa Kumar Pal, Umapada Maharashtra Mumbai400066 India Department of Computer Science and Engineering Alipurduar Government Engineering and Management College West Bengal 736206 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India

Document image enhancement is a fundamental and important stage for attaining the best performance in any document analysis assignment because there are many degradation situations that could harm document images, making it more difficult to recognize and analyze them. In this paper, we propose T2T-BinFormer which is a novel document binarization encoder-decoder architecture based on a Tokens-to-token vision transformer. Each image is divided into a set of tokens with a defined length using the ViT model, which is then applied several times to model the global relationship between the tokens. However, the conventional tokenization of input data does not adequately reflect the crucial local structure between adjacent pixels of the input image, which results in low efficiency. Instead of using a simple ViT and hard splitting of images for the document image enhancement task, we employed a progressive tokenization technique to capture this local information from an image to achieve more effective results. Experiments on various DIBCO and H-DIBCO benchmarks demonstrate that the proposed model outperforms the existing CNN and ViT-based state-of-the-art methods. In this research, the primary area of examination is the application of the proposed architecture to the task of document binarization. The source code will be made available at https://***/RisabBiswas/T2T-BinFormer. © 2023, CC BY-SA.

关键词： Image enhancement

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：