检索结果-内蒙古大学图书馆

4th International Workshop on Multilingual OCR, MOCR 2013

作者： Rothacker, L. Fink, G.A. Banerjee, P. Bhattacharya, U. Chaudhuri, B.B. Department of Computer Science TU Dortmund University 44221 Dortmund Germany Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B. T. Road Kolkata-700 0108 India

ISBN: (纸本)9781450321143

In this paper we present how Bag-of-Features Hidden Markov Models can be applied to printed Bangla word spotting. These statistical models allow for an easy adaption to different problem domains. This is possible due to the integration of automatically estimated visual appearance features and Hidden Markov Models for spatial sequential modeling. In our evaluation we are able to report high retrieval scores on a new printed Bangla dataset. Furthermore, we outperform state-of-the-art results on the well-known George Washington word spotting benchmark. Both results have been achieved using an almost identical parametric method configuration. © 2013 ACM.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Bootstrap Diffusion Model Curve Estimation for High Resolution Low-Light Image Enhancement 20th

Bootstrap Diffusion Model Curve Estimation for High Resolut...

引用

20th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2023

作者： Huang, Jiancheng Liu, Yifan Chen, Shifeng ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819970247

Learning-based methods have attracted a lot of research attention and led to significant improvements in low-light image enhancement. However, most of them still suffer from two main problems: expensive computational cost in high resolution images and unsatisfactory performance in simultaneous enhancement and denoising. To address these problems, we propose BDCE, a bootstrap diffusion model that exploits the learning of the distribution of the curve parameters instead of the normal-light image itself. Specifically, we adopt the curve estimation method to handle the high-resolution images, where the curve parameters are estimated by our bootstrap diffusion model. In addition, a denoise module is applied in each iteration of curve adjustment to denoise the intermediate enhanced result of each iteration. We evaluate BDCE on commonly used benchmark datasets, and extensive experiments show that it achieves state-of-the-art qualitative and quantitative performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Close-range photometric stereo with point light sources 2

Close-range photometric stereo with point light sources

引用

2014 2nd International Conference on 3D vision, 3DV 2014

作者： Wetzler, Aaron Kimmel, Ron Bruckstein, Alfred M. Mecca, Roberto Computer Science Department Technion Israel Institute of Technology Technion City Haifa32000 Israel Pattern Analysis and Computer Vision Department Istituto Italiano di Tecnologia via Morego 30 Genova16163 Italy

ISBN: (纸本)9781479970018

Shape recovery based on shading variations of a lighted object was recently revisited with improvements that allow for the photometric stereo approach to serve as a competitive alternative for other shape reconstruction methods. However, most efforts of using photometric stereo tend to ignore some factors that are relevant in practical applications. The approach we consider tackles the photometric stereo reconstruction in the case of near-field imaging which means that both camera and light sources are close to the imaged object. The known challenges that characterize the problem involve perspective viewing geometry, attenuation of light and possibly missing regions. Here, we pay special attention to the question of how to faithfully model these aspects and by the same token design an efficient and robust numerical solver. We present a well-posed mathematical representation that integrates the above assumptions into a single coherent model. The surface reconstruction in our near-field scenario can then be executed efficiently in linear time. The merging strategy of the irradiance equations provided for each light source allows us to consider a characteristic expansion model which enables the direct computation of the surface. We evaluate several types of light attenuation models with nonuniform albedo and noise on synthetic data using four virtual sources. We also demonstrate the proposed method on surface reconstruction of real data using three images, each one taken with a different light source. © 2014 IEEE.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

Head detection and localization from sparse 3D data

Head detection and localization from sparse 3D data

引用

24th German Association for pattern Recognition Symposium, DAGM 2002

作者： Clabian, Markus Rötzer, Harald Bischof, Horst Kropatsch, Walter Advanced Computer Vision GmbH Donau City Str.1 ViennaA-1220 Austria Institute for Computer Graphics and Vision Graz University of Technology Inffeldgasse 16 GrazA-8010 Austria Pattern Recognition and Image Processing Group Institute of Computer Aided Automation Computer Science Department Vienna University of Technology Favoritenstr. 9 ViennaA-1040 Austria

ISBN: (纸本)354044209X

Head detection is an important, but difficult task, if no restrictions such as static illumination, frontal face appearance or uniform background can be assumed. We present a system that is able to perform head detection under very general conditions by employing a 3D measurement system namely a structured light distance measurement. An algorithm of head detection from sparse 3D data (19x19 data points) is developed that reconstructs a 3D surface over the image plane and detects head hypotheses of ellipsoidal shape. We demonstrate that detection and rough localization is possible in up to 90% of the images. © Springer-Verlag Berlin Heidelberg 2002.

关键词： computers

来源：评论

学校读者我要写书评

暂无评论

Non-deterministic Behavior of Ranking-Based Metrics When Evaluating Embeddings 2nd

Non-deterministic Behavior of Ranking-Based Metrics When Eva...

引用

2nd International Workshop on Reproducible Research in pattern Recognition, RRPR 2018

作者： Nicolaou, Anguelos Dey, Sounak Christlein, Vincent Maier, Andreas Karatzas, Dimosthenis Computer Vision Center Edificio O Campus UAB Bellaterra08193 Spain Pattern Recognition Lab Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany

ISBN: (纸本)9783030239862

Embedding data into vector spaces is a very popular strategy of pattern recognition methods. When distances between embeddings are quantized, performance metrics become ambiguous. In this paper, we present an analysis of the ambiguity quantized distances introduce and provide bounds on the effect. We demonstrate that it can have a measurable effect in empirical data in state-of-the-art systems. We also approach the phenomenon from a computer security perspective and demonstrate how someone being evaluated by a third party can exploit this ambiguity and greatly outperform a random predictor without even access to the input data. We also suggest a simple solution making the performance metrics, which rely on ranking, totally deterministic and impervious to such exploits. © Springer Nature Switzerland AG 2019.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Dual Branch PnP Based Network for Monocular 6D Pose Estimation

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 3243-3256页

作者： Jia-Yu Liang Hong-Bo Zhang Qing Lei Ji-Xiang Du Tian-Liang Lin Department of Computer Science and Technology Huaqiao UniversityXiamen361000China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao UniversityXiamen361000China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao UniversityXiamen361000China College of Mechanical Engineering and Automation Xiamen361000China

Monocular 6D pose estimation is a functional task in the field of com-puter vision and *** recent years,2D-3D correspondence-based methods have achieved improved performance in multiview and depth data-based ***,for monocular 6D pose estimation,these methods are affected by the prediction results of the 2D-3D correspondences and the robustness of the per-spective-n-point(PnP)*** is still a difference in the distance from the expected estimation *** obtain a more effective feature representation result,edge enhancement is proposed to increase the shape information of the object by analyzing the influence of inaccurate 2D-3D matching on 6D pose regression and comparing the effectiveness of the intermediate ***,although the transformation matrix is composed of rotation and translation matrices from 3D model points to 2D pixel points,the two variables are essentially different and the same network cannot be used for both variables in the regression ***,to improve the effectiveness of the PnP algo-rithm,this paper designs a dual-branch PnP network to predict rotation and trans-lation ***,the proposed method is verified on the public LM,LM-O and YCB-Video *** ADD(S)values of the proposed method are 94.2 and 62.84 on the LM and LM-O datasets,*** AUC of ADD(-S)value on YCB-Video is *** experimental results show that the performance of the proposed method is superior to that of similar methods.

关键词： 6D pose monocular RGB edge enhancement dual-branch PnP 2D-3D correspondence

来源：评论

学校读者我要写书评

暂无评论

A probabilistic framework for logo detection and localization in natural scene images

A probabilistic framework for logo detection and localizatio...

引用

International Conference on pattern Recognition

作者： Ankush Roy Utpal Garain Computer Vision and Pattern Recognition Unit Indian Statistical Institute India

ISBN: (纸本)9781467322164

This paper presents a probabilistic approach for logo detection and localization in natural scene images. Two probability distributions are computed, one considering the features extracted from the key points located inside a region and the second refers to shape geometry defined by the key points. The barycentric co-ordinates are considered to define the shape statistics. The performance of the proposed approach has been reported on two publicly available datasets: BelgaLogos and Flickr Logos27. It is shown that statistically significant improvement is achieved over a recently proposed method.

关键词： Feature extraction Shape Geometry Accuracy Probabilistic logic Databases Visualization

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

Symmetry features for license plate classification

引用

CAAI Transactions on Intelligence Technology 2018年第3期3卷 176-183页

作者： Karpuravalli Srinivas Raghunandan Palaiahnakote Shivakumara Lolika Padmanabhan Govindaraju Hemantha Kumar Tong Lu Umapada Pal Department of Studies in Computer Science University of Mysore Karnataka India Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia PES Institute of Technology Bangalore Karnataka India National Key Lab for Novel Software Technology Nanjing University Nanjing People's Republic of China Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

Achieving high recognition rate for license plate images is challenging due to multi-type images. We present new symmetry features based on stroke width for classifying each input license image as private, taxi, cursive text, when they expand the symbols by writing and non-text such that an appropriate optical character recognition （OCR） can be chosen for enhancing recognition performance. The proposed method explores gradient vector flow （GVF） for defining symmetry features, namely, GVF opposite direction, stroke width distance, and stroke pixel direction. Stroke pixels in Canny and Sobel which satisfy the above symmetry features are called local candidate stroke pixels. Common stroke pixels of the local candidate stroke pixels are considered as the global candidate stroke pixels. Spatial distribution of stroke pixels in local and global symmetry are explored by generating a weighted proximity matrix to extract statistical features, namely, mean, standard deviation, median and standard deviation with respect the median. The feature matrix is finally fed to an support vector machine （SVM） classifier for classification. Experimental results on large datasets for classification show that the proposed method outperforms the existing methods. The usefulness and effectiveness of the proposed classification is demonstrated by conducting recognition experiments before and after classification.

关键词：车牌图像图像识别识别技术计算机技术

来源：评论

学校读者我要写书评

暂无评论

On road vehicle make and model recognition via sparse feature coding

On road vehicle make and model recognition via sparse featur...

引用

Iranian Machine vision and Image Processing (MVIP)

作者： A. Nazemi M. J. Shafiee Z. Azimifar Computer Vision and Pattern Recognition Lab Shiraz University Shiraz Iran

Automatic vehicle Make and Model Recognition (MMR) system offers a competent way to vehicle classification and recognition systems. This paper proposes a real time while robust vehicle make and model recognition system extracting the vehicle sub-image from the background and studies some sparse feature coding methods such as Orthogonal Matching Pursuit (OMP), some variation of Sparse Coding (SC) methods and compares them to choose the best one. Our method employs the sparse feature coding methods on dense Scale-Invariant Feature Transform (SIFT) features and Support Vector Machine (SVM) for classification. The proposed system is examined by an Iranian on road vehicles dataset, which its samples are in different point of views, various weather conditions and illuminations.

关键词： Feature extraction Vehicles Encoding Dictionaries Image coding Kernel computer vision

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：