检索结果-内蒙古大学图书馆

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

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

An efficient line segmentation approach for handwritten Bangla document image

An efficient line segmentation approach for handwritten Bang...

引用

International Conference on Advances in pattern recognition (ICAPR)

作者： K. Mullick S. Banerjee U. Bhattacharya Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India Computer Vision & Pattern Recognition Unit Indian Statistical Institute Kolkata India

Text line segmentation plays a vital role in the overall performance of a document recognition system. In the literature, similar segmentation works for offline handwritten Bangla documents are rarely found. On the other hand, certain peculiarities of handwritten Bangla script such as widespread occurrences of ascenders and descenders or some of its characters appearing only as an ascender or descender often cause unique difficulties to this segmentation task. Existence of connected components over a number of successive text lines is a common phenomenon in unconstrained handwritten Bangla documents. In this article, we propose a novel and efficient approach for text line segmentation where initially, we smudge the input document image, to blur-out white spaces between words, while preserving gaps between consecutive lines. Next, we obtain an initial segmentation scheme by shredding the image based on the white most pixels in between consecutive smudged lines. Multi-line connected components have been taken care of by thinning, and then finding the most probable point of separation in the component. Combining it with the initial segmentation, we obtain the final output. The proposed approach has been evaluated on ICDAR 2013 Handwriting Segmentation Contest dataset of Bangla. The segmentation results show the efficiency of the proposed approach.

关键词： Image segmentation Junctions Image color analysis Estimation Transforms Handwriting recognition Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

A robust matching algorithm for active appearance models 1

引用

Workshops Bildverarbeitung fur die Medizin: Algorithmen - Systeme - Anwendungen, BVM 2005 - Workshop on Image Processing for Medicine: Algorithms - Systems - Applications, BVM 2005

作者： Beichel, Reinhard Bischof, Horst Langs, Georg Sonka, Milan Institute for Computer Graphics and Vision Graz University of Technology Inffeldgasse 16/2 A-8010 Graz Austria Pattern Recognition and Image Processing Group Vienna University of Technology Favoritenstr. 9 A-1040 Vienna Austria Department of Electrical and Computer Engineering University of Iowa Iowa City IA 52242 United States

ISBN: (数字)9783540264316

ISBN: (纸本)3540250522

This paper proposes a method for robustly matching active appearance models (AAMs) on images with gross disturbances (outliers). The method consists of two steps. First, an initial residual is calculated by comparing model and image appearance, and modes of the residual are analyzed. Second, all possible mode combinations are tested by evaluating an objective function. The objective function allows the selection of an outlier-free mode combination. Experiments demonstrate the ability of the robust matching method to successfully cope with outliers - compared to standard AAM matching, no degeneration of the model during matching occurs.

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Promoted Self-adjusting Correlation Learning for Facial Action Unit Detection

引用

IEEE Transactions on Affective Computing 2024年第02期16卷 697-711页

作者： Liu, Xin Yuan, Kaishen Niu, Xuesong Shi, Jingang Yu, Zitong Yue, Huanjing Yang, Jingyu Tianjin University School of Electrical and Information Engineering Tianjin300072 China Lappeenranta-Lahti University of Technology LUT Computer Vision and Pattern Recognition Laboratory School of Engineering Science Lappeenranta53850 Finland Beijing Institute for General Artificial Intelligence Beijing100080 China Xi'an Jiaotong University School of Software Engineering Xi'an710049 China Great Bay University Dongguan523000 China

Facial Action Unit (AU) detection is a crucial task in affective computing and social robotics as it helps to identify emotions expressed through facial expressions. Anatomically, there are innumerable correlations between AUs, which contain rich information and are vital for AU detection. Previous methods used fixed AU correlations based on expert experience or statistical rules on specific benchmarks, but it is challenging to comprehensively reflect complex correlations between AUs via hand-crafted settings. There are alternative methods that employ a fully connected graph to learn these dependencies exhaustively. However, these approaches can result in a computational explosion and high dependency with a large dataset. To address these challenges, this paper proposes a novel self-adjusting AU-correlation learning (SACL) method with less computation for AU detection. This method adaptively learns and updates AU correlation graphs by efficiently leveraging the characteristics of different levels of AU motion and emotion representation information extracted in different stages of the network. Moreover, this paper explores the role of multi-scale learning in correlation information extraction, and design a simple yet effective multi-scale feature learning (MSFL) method to promote better performance in AU detection. By integrating AU correlation information with multi-scale features, the proposed method obtains a more robust feature representation for the final AU detection. Extensive experiments show that the proposed method outperforms the state-of-the-art methods on widely used AU detection benchmark datasets, with only 28.7% and 12.0% of the parameters and FLOPs of the best method, respectively. The code for this method is available at https://***/linuxsino/Self-adjusting-AU. © 2010-2012 IEEE.

关键词： Contrastive Learning

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：