检索结果-内蒙古大学图书馆

International Conference on Information Technology (ICIT)

作者： U. Pal T. Wakabayashi F. Kimura Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Graduate School of Engineering Mie University Tsu Mie Japan

recognition of handwritten characters of Indian script is difficult because of the presence of many complex shaped compound characters (cluster characters) as well as variability involved in the writing style of different individuals. This paper deals with recognition of off-line Bangla handwritten compound characters using modified quadratic discriminant function (MQDF). The features used for recognition purpose are mainly based on directional information obtained from the arc tangent of the gradient. To get the feature, at first, a 2 times 2 mean filtering is applied 4 times on the gray level image and a non-linear size normalization is done on the image. A Roberts filter is then applied on the normalized image to obtain gradient image. Next, the arc tangent of the gradient (direction of gradient) is initially quantized into 32 directions and the strength of the gradient is accumulated with each of the quantized direction. Finally, the frequencies of these directions are down sampled using Gaussian filter to get 392 dimensional feature vectors. Using 5-fold cross validation technique we obtained 85.90% accuracy from a dataset of Bangla compound characters containing 20,543 samples.

关键词： Character recognition Handwriting recognition Filters pattern recognition Filtering Automation Information technology computer vision Writing Frequency

来源：评论

学校读者我要写书评

暂无评论

A System for Off-Line Oriya Handwritten Character recognition Using Curvature Feature

A System for Off-Line Oriya Handwritten Character Recognitio...

引用

International Conference on Information Technology (ICIT)

作者： U. Pal T. Wakabayashi F. Kimura Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Graduate School of Engineering Mie University Tsu Mie Japan

In this paper we present a system towards the recognition of off-line Oriya handwritten characters. Since most of the Oriya characters have curve-like stroke, we use curvature feature for the recognition purpose. To get the feature, at first, the input image is size normalized and segmented into 49times49 blocks. Curvature is then computed using bi-quadratic interpolation method and quantized into 3 levels according to concave, linear and convex regions. Next direction of gradient is quantized into 32 levels with pi/16 intervals, and strength of the gradient is accumulated in each of the 32 directions and in each of the 3 curvature levels of every block. A spatial resolution is made to get 7times7 blocks from 49times49 blocks and a directional resolution is made to get 8 directions from 32 directions. Using curvature features for 3 levels we get 1176 (7times7 blocks times 8 directions times 3 levels) dimensional features. Finally using principal component analysis we reduce the dimension 1176 to 392 and this 392 dimensional feature vector is fed to a quadratic classifier for recognition. We tested 18190 samples of Oriya handwritten samples and obtained 94.60% accuracy from our proposed system.

关键词： Character recognition Shape Handwriting recognition computer vision Spatial resolution Speech recognition Information technology pattern recognition Image segmentation Interpolation

来源：评论

学校读者我要写书评

暂无评论

Text/Graphics Separation in Color Maps

Text/Graphics Separation in Color Maps

引用

International Conference on Computing: Theory and Applications, ICCTA

作者： Partha Pratim Roy Josep Llados Umapada Pal Computer Science Department Universitat Autònoma de Barcelona Barcelona Bellaterra Spain Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata Kolkata India

Text/graphics separation in document image analysis is one of the main concerns in present research work. The complexity enhances when both text and graphics overlap in the context of maps in color images. This paper discusses a number of improvements to text/graphics separation methods to make it suitable for maps. Emphasize is given to the overlapping regions of text and graphics. It also discusses a method of color separation using clustering method for the purpose of text/graphics separation

关键词： computer graphics Image color analysis Image segmentation Histograms Bit error rate computer vision Text analysis Clustering methods Engineering drawings Testing

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

A novel technique for the watermarking of symbolically compressed documents

A novel technique for the watermarking of symbolically compr...

引用

2nd International Conference on Document Image Analysis for Libraries (DIAL 2006)

作者： Palit, Sarbani Garain, Utpal Computer Vision and Pattern Recognition Unit India

ISBN: (纸本)0769525318

Symbolic compression is a lossy compression technique which has been found to perform very efficiently for Indian language text document images. A novel and efficient watermarking technique is proposed for such documents compressed symbolically. The approach embeds the watermark into prototypes which are unaffected during compression, leading to an exact recovery of the watermark both from the compressed document and the reconstructed one. The watermark is perfectly resistant to JPEG conversion and reasonably resistant to other attacks. The proposed technique, for the first time, combines the compression and watermarking of Indian language text document images in a common framework.

关键词： document image lossy symbolic compression prototype watermark embedding decompression watermark extraction

来源：评论

学校读者我要写书评

暂无评论

A novel technique for the watermarking of symbolically compressed documents

A novel technique for the watermarking of symbolically compr...

引用

International Workshop on Document Image Analysis for Libraries

作者： S. Palit U. Garain Computer Vision and Pattern Recognition Unit

关键词： Watermarking Image coding Data encapsulation Image storage Image reconstruction Prototypes Immune system Software libraries Communication standards computer vision

来源：评论

学校读者我要写书评

暂无评论

recognition of Handwritten Kannada Numerals

Recognition of Handwritten Kannada Numerals

引用

International Conference on Information Technology (ICIT)

作者： N. Sharma U. Pal F. Kimura Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Graduate School of Engineering Mie University Mie Japan

This paper deals with a quadratic classifier based scheme for the recognition of off-line handwritten numerals of Kannada, an important Indian script. The features used in the classifier are obtained from the directional chain code information of the contour points of the characters. The bounding box of a character is segmented into blocks and the chain code histogram is computed in each of the blocks. Here we have used 64 dimensional and 100 dimensional features for a comparative study on the recognition accuracy of our proposed system. This chain code features are fed to the quadratic classifier for recognition. We tested our scheme on 2300 data samples and obtained 97.87% and 98.45% recognition accuracy using 64 dimensional and 100 dimensional features respectively, from the proposed scheme using five-fold cross-validation technique.

关键词： Handwriting recognition Character recognition pattern recognition Histograms Natural languages computer vision Testing Automation Neural networks Training data

来源：评论

学校读者我要写书评

暂无评论

Processing of struck-out handwriting

Processing of struck-out handwriting

引用

2nd Indian International Conference on Artificial Intelligence, IICAI 2005

作者： Bhattacharya, U. Chaudhuri, B.B. Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)0972741216

Struck-out words are often found in handwritten manuscripts. A realistic off-line handwriting recognition system should take care of this common aspect. A simple but efficient approach to this problem is to subject each handwritten word to a two-class classifier in the initial stage. This classifier should take decision to pass the word to a word recognition engine in the next step or discard it as a struck-out/wrong word. In the present work, we studied a stroke analysis based technique, which can classify an input word as a correct or wrong (struck-out) word. We simulated the proposed approach on a database of 466 words collected from handwritten manuscripts of different languages and the results are promising. Copyright © IICAI 2005.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

A corpus for OCR research on mathematical expressions

引用

International Journal on Document Analysis and recognition 2005年第4期7卷 241-259页

作者： Garain, Utpal Chaudhuri, B.B. Computer Vision and Pattern Recognition Unit Indian Statistical Institute Calcutta-700 035 203 B.T. Road India

This paper is concerned with research on OCR (optical character recognition) of printed mathematical expressions. Construction of a representative corpus of technical and scientific documents containing expressions is discussed. A statistical investigation of the corpus is presented, and usefulness of this analysis is demonstrated in the related research problems, namely, (i) identification and segmentation of expression zones from the rest of the document, (ii) recognition of expression symbols, (iii) interpretation of expression structures, and (iv) performance evaluation of a mathematical expression recognition system. Moreover, a groundtruthing format has been proposed to facilitate automatic evaluation of expression recognition techniques. © Springer-Verlag Berlin/Heidelberg 2005.

关键词： Database Groundtruthing Mathematical expressions OCR Performance evaluation Statistical learning

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：