检索结果-内蒙古大学图书馆

International Conference on Document Analysis and recognition

作者： Hemmaphan Suwanwiwat Michael Blumenstein Umapada Pal School of Information and Communication Technology Griffith University Australia Computer Vision and Pattern Recognition Unit Indian Statistical Institute India

There are only a few studies undertaken in developing automatic assessment systems using handwriting recognition, even though a successful system would undoubtedly benefit the education system as schools and universities in many countries still employ paper-based examinations. To the best of the authors' knowledge, there is no existing work on an automatic off-line short answer assessment system comprising a student identification component. Hence in this paper, the authors propose a system towards this, where a new feature extraction technique called the Enhanced Water Reservoir, Loop and Gaussian Grid Feature, as well as other enhanced feature extraction techniques were utilised. Artificial Neural Networks and Support Vector Machines were employed as the classifiers; they were used for the investigation, and a comparison of the recognition and accuracy rates of the proposed systems, as well as the feature extraction techniques, was undertaken. The proposed assessment system achieved a recognition rate of 87.12% with 91.12% assessment accuracy, and the student identification component obtained a recognition rate of 99.52% with a 100% identification accuracy rate.

关键词： Feature extraction Field effect transistors Erbium

来源：评论

学校读者我要写书评

暂无评论

Bengali Noun Morphological Analyzer

Bengali Noun Morphological Analyzer

引用

International Conference on Advances in Computing, Communications and Informatics

作者： Priyanka Das Arjun Das Dept. of Computational Linguistics The English and Foreign Languages University Computer Vision and Pattern Recognition Unit Indian statistical Institute

ISBN: (纸本)9781467361262

This paper describes a linguistics approach towards development of a Bengali Noun Morphological Analyzer implemented at first on the semi-manually created database of 87697 inflected words list tokens, i.e. Input2 for Linguistics Resource Creation comprising of Noun, Pronoun, Adjective roots with and without its suffixes. Then after the first implementation the developed Linguistic Resource knowledge is applied on an unknown Bengali corpus database containing 6157 tokens. At the initial stage of this research a linguistic analysis is done which leads to framing of the nominal suffix list which is later on used in nominal suffix extraction. This linguistic knowledge is implemented in developing the finite-state transducer grammar for Linguistic Resource which gives way to the development of Bengali Noun Morphological Analyzer. The final output obtained is around 44% accuracy. This accuracy can be always improved with time if we keep on increasing the nominal roots in the FST grammar file.

关键词： Morphological Analyzer Finite-State Transducer Grammar Nominal Suffix Xerox Finite-State Tool Compiler Lookup Tool

来源：评论

学校读者我要写书评

暂无评论

Exploiting multi-scale fusion, spatial attention and patch interaction techniques for text-independent writer identification

arXiv

引用

arXiv 2021年

作者： Srivastava, Abhishek Chanda, Sukalpa Pal, Umapada Computer Vision & Pattern Recognition Unit Indian Statistical Institute Kolkata India Department of Computer Science and Communication Østfold University College Halden Norway

Text independent writer identification is a challenging problem that differentiates between different handwriting styles to decide the author of the handwritten text. Earlier writer identification relied on handcrafted features to reveal pieces of differences between writers. Recent work with the advent of convolutional neural network, deep learning-based methods have evolved. In this paper, three different deep learning techniques - spatial attention mechanism, multi-scale feature fusion and patch-based CNN were proposed to effectively capture the difference between each writer's handwriting. Our methods are based on the hypothesis that handwritten text images have specific spatial regions which are more unique to a writer's style, multi-scale features propagate characteristic features with respect to individual writers and patch-based features give more general and robust representations that helps to discriminate handwriting from different writers. The proposed methods outperforms various state-of-the-art methodologies on word-level and page-level writer identification methods on three publicly available datasets - CVL, Firemaker, CERUG-EN datasets and give comparable performance on the IAM dataset. © 2021, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Short Answer Question Examination using an Automatic Off-line Handwriting recognition System and a Novel Combined Feature

Short Answer Question Examination using an Automatic Off-lin...

引用

International Joint Conference on Neural Networks

ISBN: (纸本)9781479919611

Off-line automatic assessment systems can be an aid for teachers in the marking process. There has been no recent work in the development of off-line automatic assessment systems using handwriting recognition, even though such systems will clearly benefit the education sector. The reason is many schools and universities in many parts of the world still use paper-based examination. This research proposes the use of a newly developed feature extraction technique called the Modified Water Reservoir, Loop and Gaussian Grid Feature, as well as other feature extraction techniques. These techniques were investigated employing artificial neural networks and support vector machines as classifiers to develop an automatic assessment system for marking short answer questions. The system has high assessment accuracy (up to 94.75% for hand printed, 96.09% for cursive handwritten, and 95.71% for hand printed and cursive handwritten combined). The proposed system also includes assessment criteria to augment its accuracy.

关键词： Handwriting recognition Off-line Automatic Assessment System Modified direction feature Gaussian grid feature Water Reservoir Feature Modified Water Reservoir Loop and Gaussian Grid Feature handwriting recognition AUTOMATIC Feature extraction OFF LINE Hand Answer Classifiers Support Vector Network

来源：评论

学校读者我要写书评

暂无评论

Off-Line Handwritten Bilingual Name recognition for Student Identification in an Automated Assessment System

Off-Line Handwritten Bilingual Name Recognition for Student ...

引用

International Workshop on Frontiers in Handwriting recognition

作者： Hemmaphan Suwanwiwat Vu Nguyen Michael Blumenstein Umapada Pal School of Information and Communication Technology Griffith University Australia Computer Vision and Pattern Recognition Unit Indian Statistical Institute India

The Student name Identification System (SIS) proposed here was investigated for English and Thai languages combined. The proposed system recognises each name by using an approach for whole word recognition. In the proposed system, the Gaussian Grid Feature (GGF), and Modified Direction Feature (MDF), together with a proposed hybrid feature extraction technique called Water Reservoir, Loop and Gaussian Grid Feature (WRLGGF) were investigated on full word contour images of each name sample. Artificial neural networks and support vector machines were used as classifiers. An encouraging recognition accuracy of 99.25% was achieved employing the proposed technique compared to 98.59% for GGF, and 96.63% using MDF.

关键词： Feature extraction Reservoirs Support vector machines Vectors Image recognition Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Structural, Syntactic, and Statistical pattern recognition 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： Edwin R. Hancock Richard C. Wilson Terry Windeatt Ilkay Ulusoy Francisco Escolano

ISBN: (数字)9783642149801

ISBN: (纸本)9783642149795

This volume in the Springer Lecture Notes in computer Science (LNCS) series contains the papers presented at the S+SSPR 2010 Workshops, which was the seventh occasion that SPR and SSPR workshops have been held jointly. S+SSPR 2010 was organized by TC1 and TC2, Technical Committees of the International Association for pattern recognition(IAPR), andheld inCesme, Izmir, whichis a seaside resort on the Aegean coast of Turkey. The conference took place during August 18–20, 2010, only a few days before the 20th International Conference on pattern recognition (ICPR) which was held in Istanbul. The aim of the series of workshops is to create an international forum for the presentation of the latest results and exchange of ideas between researchers in the ?elds of statistical and structural pattern recognition. SPR 2010 and SSPR 2010 received a total of 99 paper submissions from many di?erent countries around the world, giving it a truly international perspective, as has been the case for previous S+SSPR workshops. This volume contains 70 accepted papers, 39 for oral and 31 for poster presentation. In addition to par- lel oral sessions for SPR and SSPR, there were two joint oral sessions of interest to both SPR and SSPR communities. Furthermore, to enhance the workshop experience, there were two joint panel sessions on “Structural Learning” and “Clustering,” in which short author presentations were followed by discussion. Another innovation this year was the ?lming of the proceedings by Videol- tures.

关键词： Artificial Intelligence Programming Techniques Information Systems Applications (incl. Internet) Information Storage and Retrieval Database Management Algorithm Analysis and Problem Complexity

来源：评论

学校读者我要写书评

暂无评论

One-Shot Learning-Based Handwritten Word recognition 5th

One-Shot Learning-Based Handwritten Word Recognition

引用

5th Asian Conference on pattern recognition, ACPR 2019

作者： Chakrapani Gv, Asish Chanda, Sukalpa Pal, Umapada Doermann, David Electronics and Communication Department Manipal University Jaipur Jaipur India Centre for Image Analysis Department of Information Technology Uppsala University Uppsala Sweden Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India University at Buffalo SUNY Buffalo United States

ISBN: (纸本)9783030412982

One-Shot and Few-shot Learning algorithms have emerged as techniques that can imitate a humans ability to learn from very few examples. This is an advantage over traditional deep networks which require a lot of training samples and lack of robustness due to their excessive domain specific discriminators. In this paper, we explore a one-shot learning approach to recognizing handwritten words using Siamese networks to classify the handwritten images at the word level. The Siamese network’s ability to compute similarities between two images is learned using a supervised metric but the fully trained Siamese network can be used to classify new data that has previously not been used to train the network. The model learns to discriminate inputs from a small labelled support set. By using a convolutional architecture we were able to achieve robust results. We also expect that training the system over a larger distributions of data will result in improved general handwritten word classification. Accuracy as high as 92.4% was obtained while performing 5-way one-shot word recognition on a publicly available dataset which is quite high in comparison to the state-of-the-art methods. © 2020, Springer Nature Switzerland AG.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Abstract: Learning to avoid poor images: towards task-aware c-arm cone-beam ct trajectories

Abstract: Learning to avoid poor images: towards task-aware ...

引用

International workshop on Algorithmen - Systeme - Anwendungen, 2020

作者： Zaech, Jan-Nico Gao, Cong Bier, Bastian Taylor, Russell Maier, Andreas Navab, Nassir Unberath, Mathias Laboratory for Computational Sensing and Robotics Johns Hopkins University Baltimore United States Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Computer Vision Laboratory Eidgenössische Technische Hochschule Zürich Zürich Germany

ISBN: (纸本)9783658292669

Metal artifacts in computed tomography (CT) arise from a mismatch between physics of image formation and idealized assumptions during tomographic reconstruction. These artifacts are particularly strong around metal implants, inhibiting widespread adoption of 3D cone-beam CT (CBCT) despite clear opportunity for intra-operative verification of implant positioning, e. g. in spinal fusion surgery. On synthetic and real data, we demonstrate that much of the artifact can be avoided by acquiring better data for reconstruction in a task-aware and patient-specific manner, and describe the first step towards the envisioned task-aware CBCT protocol. © Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature 2020.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

RBF-Softmax: Learning Deep Representative Prototypes with Radial Basis Function Softmax 1

引用

16th European Conference on computer vision, ECCV 2020

作者： Zhang, Xiao Zhao, Rui Qiao, Yu Li, Hongsheng CUHK-SenseTime Joint Lab The Chinese University of Hong Kong Hong Kong SenseTime Research Hong Kong ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9783030585747

ISBN: (纸本)9783030585730

Deep neural networks have achieved remarkable successes in learning feature representations for visual classification. However, deep features learned by the softmax cross-entropy loss generally show excessive intra-class variations. We argue that, because the traditional softmax losses aim to optimize only the relative differences between intra-class and inter-class distances (logits), it cannot obtain representative class prototypes (class weights/centers) to regularize intra-class distances, even when the training is converged. Previous efforts mitigate this problem by introducing auxiliary regularization losses. But these modified losses mainly focus on optimizing intra-class compactness, while ignoring keeping reasonable relations between different class prototypes. These lead to weak models and eventually limit their performance. To address this problem, this paper introduces a novel Radial Basis Function (RBF) distances to replace the commonly used inner products in the softmax loss function, such that it can adaptively assign losses to regularize the intra-class and inter-class distances by reshaping the relative differences, and thus creating more representative prototypes of classes to improve optimization. The proposed RBF-Softmax loss function not only effectively reduces intra-class distances, stabilizes the training behavior, and reserves ideal relations between prototypes, but also significantly improves the testing performance. Experiments on visual recognition benchmarks including MNIST, CIFAR-10/100, and ImageNet demonstrate that the proposed RBF-Softmax achieves better results than cross-entropy and other state-of-the-art classification losses. The code is at https://***/2han9x1a0release/RBF-Softmax. © 2020, Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Font identification — In context of an Indic script

Font identification — In context of an Indic script

引用

International Conference on pattern recognition

作者： Sukalpa Chanda Umapada Pal Katrin Franke Department of Computer Science and Media Technology Gjøvik University College Norway Computer Vision and Pattern Recognition Unit Indian Statistical Institute India

ISBN: (纸本)9781467322164

Font can be used as a notion of similarity amongst multiple documents written in same script. We could automatically retrieve document images with specific font from a huge digital document repository. So Optical Font recognition could be a useful pre-processing step in an automated questioned document analysis system for sorting documents with similar fonts. We propose a scheme to identify 10 different fonts for an Indic script (Bangla). Curvature-based features are extracted from segmented characters and are fed to a Support Vector Machine (SVM) classifier. The classifier determines the font type for each segmented character obtained from a document. Later, font identification for that document is executed on the basis of majority voting amongst 10 different fonts for all characters. Using a Multiple Kernel SVM classifier we obtained 98.5% accuracy from 400 test documents (40 documents for each font type).

关键词： Support vector machines Kernel Accuracy Feature extraction Training Image segmentation pattern recognition

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：