检索结果-内蒙古大学图书馆

Iranian Machine vision and Image Processing (MVIP)

作者： Neda Azouji Zohreh Azimifar Computer Vision and Pattern Recognition Lab Shiraz University Shiraz Iran

Human action recognition is the process of labeling videos contain human motion with action classes. The run time complexity is one of the most important challenges in action recognition. In this paper, we address this problem using video abstraction techniques including key-frame extraction and video skimming. At first we extract key-frames and then skim the video clip by concatenating excerpts around the selected key-frames. This shorter sequence is used as input for classifier. Our proposed approach not only reduces the space complexity but also reduces the run time in both train and test steps. The experimental results provided on KTH action datasets show that the proposed method achieves good performance without losing considerable classification accuracy.

关键词： Videos Feature extraction Accuracy Image color analysis Shape Support vector machines computer vision

来源：评论

学校读者我要写书评

暂无评论

Human motion correction and representation method from motion camera

引用

Journal of Engineering 2017年第1期1卷 370-375页

作者： Zhang, Hong-Bo Guo, Feng Zhang, Miaohui Lin, Ying Hsiao, Tsung-Chih Department of Computer Science and Technology Huaqiao University Xiamen China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Xiamen China School of Information Science and Engineering Xiamen University Xiamen China Institute of Energy Jiangxi Academy of Sciences Jiangxi Province China

Motion estimation is a basic issue for many computer vision tasks, such as human-computer interaction, motion objection detection and intelligent robot. In many practical scenes, the object movement goes with camera motion. Generally, motion descriptors directly based on optical flow are inaccurate and have low discrimination power. To this end, a novel motion correction method is proposed and a novel motion feature descriptor called the motion difference histogram (MDH) for recognising human action is proposed in this study. Motion estimation results are corrected by background motion estimation and MDH encodes the motion difference between the background and the objects. Experimental results on video shot with camera motion show that the proposed motion correction method is effective and the recognition accuracy of MDH is better than that of the state-of-the-art motion descriptor.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Automatic motion-guided video stylization and personalization 11

Automatic motion-guided video stylization and personalizatio...

引用

19th ACM International Conference on Multimedia ACM Multimedia 2011, MM'11

作者： Cao, Chen Chen, Shifeng Zhang, Wei Tang, Xiaoou Shenzhen Key Laboratory for Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Department of Information Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781450306164

Video stylization transfers a source video into an artistic version while maintaining temporal coherence between adjacent frames. In this paper, we formulate the unsupervised example-based video stylization with Markov random field model. In our algorithm, we implement an improved optical flow algorithm to maintain temporal coherence while improve the accuracy of estimation along motion boundaries. We also extend our algorithm to the application of video personalization, in which human faces keep clear and distinguishable. A series of techniques are fused in video personalization, including face detection and alignment, motion flow, skin detection, and illumination blending. Given a source video and a style template image, our algorithm produces the stylized and/or personalized video(s) automatically. Experimental results demonstrate that our algorithm performs excellently in both video stylization and personalization. Copyright 2011 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Convex hull based approach for multi-oriented character recognition from graphical documents

Convex hull based approach for multi-oriented character reco...

引用

作者： Roy, Partha Pratim Pal, Umapada Lladós, Josep Kimura, Fumitaka Computer Vision Center Universitat Autònoma De Barcelona 08193 Bellaterra Spain Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata - 108 India Graduate School of Engineering Mie University 1577 Kurimamachiya Mie 514-8504 Japan

ISBN: (纸本)9781424421756

In this paper, we present a scheme towards recognition of English character in multi-scale and multi-oriented environments. Graphical document such as map consists of text lines which appear in different orientation. Sometimes, characters in a single word may follow a curvi-linear way to annotate the graphical curve lines. For recognition of such multi-scale and multi-oriented characters a Support Vector Machine (SVM) based scheme is presented in this paper. The feature used here is invariant to character orientation. Circular ring and convex hull have been used along with angular information of the contour pixels of the character to make the feature rotation invariant. We tested our proposed scheme on two different datasets. Combining circular and convex hull feature we have obtained 96.73% and 99.56% accuracy in these two datasets. © 2008 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Combining the advantages of local and global optic flow methods

Combining the advantages of local and global optic flow meth...

引用

24th Symposium of the German pattern recognition Association, DAGM 2002

作者： Bruhn, Andres Weickert, Joachim Schnorr, Christoph Mathematical Image Analysis Group Faculty of Mathematics and Computer Science Saarland University 66041 Saarbrücken Germany Computer Vision Graphics and Pattern Recognition Group Department of Mathematics and Computer Science University of Mannheim 68131 Mannheim Germany

ISBN: (纸本)354044209X

Differential methods are frequently used techniques for optic flow computations. They can be classified into local methods such as the Lucas-Kanade technique or Bigün's structure tensor method, and into global methods such as the Horn-Schunck approach and its modifications. Local methods are known to be more robust under noise, while global techniques yield 100% dense flow fields. No clear attempts to combine the advantages of these two classes of methods have been made in the literature so far. This problem is addressed in our paper. First we juxtapose the role of smoothing processes that are required in local and global differential methods for optic flow computation. This discussion motivates us to introduce and evaluate a novel method that combines the advantages of local and global approaches: It yields dense flow fields that are robust against noise. Finally experiments with different sequences are performed demonstrating its excellent results. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Flow fields

来源：评论

学校读者我要写书评

暂无评论

Anaphora Resolution in Bangla Using Global Discourse Knowledge

Anaphora Resolution in Bangla Using Global Discourse Knowled...

引用

International Conference on Asian Language Processing (IALP)

作者： Apurbalal Senapati Utpal Garain Computer Vision & Pattern Recognition Unit Indian Statistical Institute Kolkata India

This paper presents a pronominal anaphora resolution (PAR) approach that makes use of the global discourse knowledge along with other traditional features. So far the features used in finding the referent of an anaphoric pronoun are computed locally. Normally the sentence containing the anaphor and a few sentences immediately before form the local context. In this process, the knowledge base gets updated as more and more of the discourse is processed. Keeping this approach as the core, the present paper explores use of some prior knowledge after examining the entire discourse (whole article). Addition of this processing step improves the PAR's efficiency. This improvement is demonstrated using ICON 2011 Bangla dataset.

关键词： Pragmatics Natural language processing Organizations Communities computer vision pattern recognition Roads

来源：评论

学校读者我要写书评

暂无评论

A New Defect Detection Method for Improving Text Detection and recognition Performances in Natural Scene Images

A New Defect Detection Method for Improving Text Detection a...

引用

2020 Swedish Workshop on Data Science, SweDS 2020

作者： Mokayed, Hamam Shivakumara, Palaiahnakote Liwicki, Marcus Pal, Umapada University of Malaya Faculty of Computer Science and Information Technology Kuala Lumpur Malaysia Lulea University of Technology Department of Computer Science Electrical and Space Engineering Sweden Indian Statistical Institute Computer Vision and Pattern Recognition Unit Kolkata India

ISBN: (纸本)9781728192048

This paper presents a new idea for improving text detection and recognition performances by detecting defects in the text detection results. Despite the rapid development of powerful deep learning based models for scene text detection and recognition in the wild, in complex situations (logos or decorated components connected with text), existing methods do not yield satisfactory results. In this paper, we propose to use post-processing method to improve the text detection and recognition performance. The proposed method extracts features, namely phase congruency, entropy and compactness for the text detection results. To strengthen discriminative power for feature extraction, we explore the combination of SVM classifier and Gaussian distribution of text components to determine proper weight, which represents true text component. The weights are multiplied with the features to detect defect components though clustering. The bounding boxes are redrawn, which results proper bounding box without defects components. Experimental results show that the proposed defect detection reports satisfactory results. To validate the effectiveness of defect detection, we conduct experiments on benchmark datasets of MSRA-TD-500 and SVT for detection and recognition before and after defect detection. The result shows that the performance of text detection and recognition improves significantly after defect detection. © 2020 IEEE.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Extraction of type style based meta-information from imaged documents

Extraction of type style based meta-information from imaged ...

引用

International Conference on Document Analysis and recognition

作者： U. Garain B.B. Chaudhuri Computer Vision & Pattern Recognition Unit Indian Statistical Institute Calcutta India

Extraction of some meta-information from printed documents without an OCR approach is considered. It can be statistically verified that important terms in articles are printed in italic, bold and all capital style. Detection of these type styles helps in automatic extraction of the lines containing titles, authors' names, subtitles, references as well as sentences having important terms occurring in the text. It also helps in improving the OCR performance for reading the italic text. Some experimental results on the performance of the approach on good quality as well as degraded document images are presented.

关键词： Optical character recognition software Data mining Sections computer vision pattern recognition Postal services Read only memory Pressing Search engines Image converters

来源：评论

学校读者我要写书评

暂无评论

Bengali Place Name recognition - Comparative Analysis Using Different CNN Architectures 5th

Bengali Place Name Recognition - Comparative Analysis Using ...

引用

5th International Conference on computer vision and Image Processing, CVIP 2020

作者： Prasad, Prashant Kumar Banerjee, Pamela Chanda, Sukalpa Pal, Umapada RCC Institute of Information Technology Kolkata India Department of Information Technology Østfold University College Halden Norway Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9789811610912

Optical Character recognition (OCR) has been deployed in the past in different application areas such as automatic transcription and indexing of document images, reading aid for the visually impaired persons, postal automation etc. However, the performance in many cases has not been impressive due to the fact that character segmentation is itself an error-prone and difficult operation, which leads to the poor performance of the system due to erroneous segmentation of characters. Hence, for many applications (like document indexing, Postal automation) where full character-wise transcription is not required, word recognition is the preferred method these days. This article investigates recognition of Bengali place names as word images using 5 different traditional architectures. Experiments on word images (of Bengali place names) from 608 classes were conducted. Encouraging results were obtained in all instances. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Very Low Resolution Screen-Rendered Text

Segmentation of Very Low Resolution Screen-Rendered Text

引用

International Conference on Document Analysis and recognition

作者： S. Wachenfeld S. Fleischer H.-U. Klein X. Jiang Computer Vision and Pattern Recognition Group Department of Computer Science University of Muenster Germany

The lower the resolution of a given text is, the more difficult it becomes to segment it into single characters. The resolution of screen-rendered text can be very low. This paper focuses on smoothed screen-rendered text of very low resolution with typical x-heights of 4 to 7 pixels which is much lower than in other low resolution OCR situations. We propose a recognition-based segmentation algorithm which makes use of over segmentation by dynamic programming, candidate rating by single character classifiers and a graph based search algorithm for an optimal cut sequence. The algorithm is described in detail and experimental results are presented which show the performance on example screen- shot images taken from the public Screen-Word database.

关键词： Image segmentation Classification algorithms Optical character recognition software Dynamic programming Focusing Image databases computer vision pattern recognition computer science Character 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：