检索结果-内蒙古大学图书馆

2nd International Workshop on Automated Forensic Handwriting Analysis, AFHA 2013

作者： Pal, Srikanta Pal, Umapada Blumenstein, Michael School of Information and Communication Technology Griffith University Gold Coast Australia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

Signature identification and verification are of great importance in authentication systems. The purpose of this paper is to introduce an experimental contribution in the direction of multi-script off-line signature identification and verification using a novel technique involving off-line English, Hindi (Devnagari) and Bangla (Bengali) signatures. In the first evaluation stage of the proposed signature verification technique, the performance of a multi-script off-line signature verification system, considering a joint dataset of English, Hindi and Bangla signatures, was investigated. In the second stage of experimentation, multi-script signatures were identified based on the script type, and subsequently the verification task was explored separately for English, Hindi and Bangla signatures based on the identified script result. The gradient and chain code features were employed, and Support Vector Machines (SVMs) along with the Modified Quadratic Discriminate Function (MQDF) were considered in this scheme. From the experimental results achieved, it is noted that the verification accuracy obtained in the second stage of experiments (where a signature script identification method was introduced) is better than the verification accuracy produced following the first stage of experiments. Experimental results indicated that an average error rate of 20.80% and 16.40% were obtained for two different types of verification experiments.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Depth Estimation From Single Image And Semantic Prior

Depth Estimation From Single Image And Semantic Prior

引用

IEEE International Conference on Image Processing

作者： Praful Hambarde Akshay Dudhane Prashant W. Patil Subrahmanyam Murala Abhinav Dhall Computer Vision and Pattern Recognition Lab IIT Ropar

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

The multi-modality sensor fusion technique is an active research area in scene understating. In this work, we explore the RGB image and semantic-map fusion methods for depth estimation. The LiDARs, Kinect, and TOF depth sensors are unable to predict the depth-map at illuminate and monotonous pattern surface. In this paper, we propose a semantic-to-depth generative adversarial network (S2D-GAN) for depth estimation from RGB image and its semantic-map. In the first stage, the proposed S2D-GAN estimates the coarse level depthmap using a semantic-to-coarse-depth generative adversarial network (S2CD-GAN) while the second stage estimates the fine-level depth-map using a cascaded multi-scale spatial pooling network. The experimental analysis of the proposed S2D-GAN performed on NYU-Depth-V2 dataset shows that the proposed S2D-GAN gives outstanding result over existing single image depth estimation and RGB with sparse samples methods. The proposed S2D-GAN also gives efficient results on the real-world indoor and outdoor image depth estimation.

关键词： Estimation Semantics Generators Robot sensing systems Laser radar Generative adversarial networks Training

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

Word-wise Thai and Roman script identification

引用

ACM Transactions on Asian Language Information Processing 2009年第3期8卷 1–21页

作者： Chanda, Sukalpa Pal, Umapada Terrades, Oriol Ramos Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B. T. Road Kolkatta-700108 India Instituto Tecnologico de Informatica Univ. Politécnica de Valencia 46022 Valencia Spain

In some Thai documents, a single text line of a printed document page may contain words of both Thai and Roman scripts. For the Optical Character recognition (OCR) of such a document page it is better to identify, at first, Thai and Roman script portions and then to use individual OCR systems of the respective scripts on these identified portions. In this article, an SVM-based method is proposed for identification of word-wise printed Roman and Thai scripts from a single line of a document page. Here, at first, the document is segmented into lines and then lines are segmented into character groups (words). In the proposed scheme, we identify the script of a character group combining different character features obtained from structural shape, profile behavior, component overlapping information, topological properties, and water reservoir concept, etc. Based on the experiment on 10,000 data (words) we obtained 99.62% script identification accuracy from the proposed scheme. © 2009 ACM.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Handwriting segmentation of unconstrained Oriya text

Handwriting segmentation of unconstrained Oriya text

引用

International Workshop on Frontiers in Handwriting recognition

作者： N. Tripathy U. Pal Computer Vision and Pattern Recognition Unit Kolkata India

Segmentation of handwritten text into lines, words and characters is one of the important steps in the handwritten recognition system. For the segmentation of unconstrained Oriya handwritten text into individual characters, a water reservoir-concept based scheme is proposed in this paper. Here, at first, the text image is segmented into lines, and then lines are segmented into individual words, and words are segmented into individual characters. For line segmentation the document is divided into vertical stripes. Analyzing the heights of the water reservoirs obtained from different components of the document, the width of a stripe is calculated. Stripe-wise horizontal histograms are then computed and the relationship of the peak-valley points of the histograms is used for line segment. Based on vertical projection profile and structural features of Oriya characters, text lines are segmented into words. For character segmentation, at first, isolated and connected (touching) characters in a word are detected. Using structural, topological and water-reservoir-concept based features touching characters of the word are then segmented.

关键词： Image segmentation Histograms Handwriting recognition pattern recognition Character recognition Text recognition Shape computer vision Water resources Reservoirs

来源：评论

学校读者我要写书评

暂无评论

Text line identification in Tagore's manuscript

Text line identification in Tagore's manuscript

引用

2014 3rd IEEE Students' Technology Symposium, IEEE TechSym 2014

作者： Adak, Chandranath Chaudhuri, Bidyut B. Dept. of Computer Science and Engg. University of Kalyani West-Bengal-741235 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata-700108 India

ISBN: (纸本)9781479926084

In this paper, a text line identification method is proposed. The text lines of printed document are easy to segment due to uniform straightness of the lines and sufficient gap between the lines. But in handwritten documents, the line is nonuniform and interline gaps are variable. We take Rabindranath Tagore's manuscript as it is one of the most difficult manuscripts that contain doodles. Our method consists of a preprocessing stage to clean the document image. Then we separate doodles from the manuscript to get the textual region. After that we identify the text lines on the manuscript. For text line identification, we use window examination, black run-length smearing, horizontal histogram and connected component analysis. © 2014 IEEE.

关键词： document image processing handwritten character recognition image segmentation optical character recognition text analysis Rabindranath Tagore manuscript black run-length smearing connected component analysis document image cleaning doodle separation handwritten documents horizontal histogram nonuniform line preprocessing stage printed document text line identification method text line segmentation textual region uniform line straightness variable interline gaps window examination Character recognition Frequency modulation Handwriting recognition Histograms Image analysis Optical filters Text analysis document image analysis doodle handwritten document manuscript processing text line identification

来源：评论

学校读者我要写书评

暂无评论

Shape code based word-image matching for retrieval of Indian multi-lingual documents

Shape code based word-image matching for retrieval of Indian...

引用

International Conference on pattern recognition

作者： Tarafdar, Arundhati Mondal, Ranju Pal, Srikanta Pal, Umapada Kimura, Fumitaka Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata-700108 India Graduate School of Engineering Mie University Kurimamachiya-cho Tsu Japan

ISBN: (纸本)9780769541099

In the current scenario retrieving information from document images is a challenging problem. In this paper we propose a shape code based word-image matching (words-potting) technique for retrieval of multilingual documents written in Indian languages. Here, each query word image to be searched is represented by a primitive shape code using (i) zonal information of extreme points (ii) vertical shape based feature (iii) crossing count (with respect to vertical bar position) (iv) loop shape and position (v) background information etc. Each candidate word (a word having similar aspect ratio and topological feature to the query word) of the document is also coded accordingly. Then, an inexact string matching technique is used to measure the similarity between the primitive codes generated from the query word image and each candidate word of the document with which the query image is to be searched. Based on the similarity score, we retrieve the document where the query image is found. Experimental results on Bangla, Devnagari and Gurumukhi scripts document image databases confirm the feasibility and efficiency of our proposed approach. © 2010 IEEE.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

STRNet:Triple-stream Spatiotemporal Relation Network for Action recognition

引用

International Journal of Automation and computing 2021年第5期18卷 718-730页

作者： Zhi-Wei Xu Xiao-Jun Wu Josef Kittler School of Artificial Intelligence and Computer Science Jiangnan UniversityWuxi 214122China Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Wuxi 214122China Centre for Vision Speech and Signal ProcessingUniversity of SurreyGuildfordGU27XHUK

Learning comprehensive spatiotemporal features is crucial for human action recognition. Existing methods tend to model the spatiotemporal feature blocks in an integrate-separate-integrate form, such as appearance-and-relation network(ARTNet) and spatiotemporal and motion network(STM). However, with blocks stacking up, the rear part of the network has poor interpretability. To avoid this problem, we propose a novel architecture called spatial temporal relation network(STRNet), which can learn explicit information of appearance, motion and especially the temporal relation information. Specifically, our STRNet is constructed by three branches,which separates the features into 1) appearance pathway, to obtain spatial semantics, 2) motion pathway, to reinforce the spatiotemporal feature representation, and 3) relation pathway, to focus on capturing temporal relation details of successive frames and to explore long-term representation dependency. In addition, our STRNet does not just simply merge the multi-branch information, but we apply a flexible and effective strategy to fuse the complementary information from multiple pathways. We evaluate our network on four major action recognition benchmarks: Kinetics-400, UCF-101, HMDB-51, and Something-Something v1, demonstrating that the performance of our STRNet achieves the state-of-the-art result on the UCF-101 and HMDB-51 datasets, as well as a comparable accuracy with the state-of-the-art method on Something-Something v1 and Kinetics-400.

关键词： Action recognition spatiotemporal relation multi-branch fusion long-term representation video classification

来源：评论

学校读者我要写书评

暂无评论

Word–wise script identification from indian documents

引用

6th IAPR International Workshop on Document Analysis Systems, DAS 2004

作者： Sinha, Suranjit Pal, Umapada Chaudhuri, B.B. Computer Vision and Pattern Recognition Unit Indian Statistical Unit 203 B.T. Road Kolkata700 108 India

ISBN: (纸本)3540230602

In a country like India, a single text line of most of the official documents contains two different script words. Under two-language formula, the Indian documents are written in English and the state official language. For Optical Character recognition (OCR) of such a document page, it is necessary to separate different script words before feeding them to the OCRs of individual scripts. In this paper a robust technique is proposed to extract word-wise script identification from Indian doublet form documents. Here, at first, the document is segmented into lines and then the lines are segmented into words. Using different topological and structural features (like number of loops, headline feature, water reservoir concept based features, profile features, etc.) individual script words are identified from the documents. The proposed scheme is tested on 24210 words of different doublets and we received more than 97% accuracy, on average. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Two-stage recognition of handwritten bangla alphanumeric characters using neural classifiers

Two-stage recognition of handwritten bangla alphanumeric cha...

引用

2nd Indian International Conference on Artificial Intelligence, IICAI 2005

作者： Bhattacharya, U. Parui, S.K. Sridhar, M. Kimura, F. Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Department of Electrical and Computer Engineering University of Michigan-Dearborn United States Faculty of Engineering Mie University Japan

ISBN: (纸本)0972741216

No significant research work towards recognition of handwritten Bangla characters has yet been done. Only a few works in this area are found in the literature which are based on small databases col-lected in laboratory environments. Recently, a large and representative database of Bangla character images [1] has been developed. The first part of this article is devoted to shape analysis of samples of this database vis-a-vis shapes of the respective printed characters. The next part describes a two-stage scheme for recognition of handwritten Bangla alphanumeric characters. This is a 57 class problem (shapes of 3 numerals are not distinguishable from shapes of 3 basic characters among 10 numerals and 50 basic characters). In the first stage of this recognition scheme, an input character is identified in one of 11 smaller groups of characters. In the second stage, classification is performed within the particular smaller group as determined by the first stage. In both the stages of the proposed approach, local chain code histograms of character skeleton are used as the feature vector and multilayer perceptron (MLP) as the classifier. recognition accuracies obtained by the proposed approach on the training and test sets of the present handwritten Bangla alphanumeric character database are respectively 91.45% and 84.65%. Copyright © IICAI 2005.

关键词： Database systems

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：