检索结果-内蒙古大学图书馆

Conference on computer vision and pattern recognition (CVPR)

作者： Lech Szumilas Rene Donner Georg Langs Allan Hanbury Pattern Recognition and Image Processing Group University of Technology Vienna Vienna Austria Institute for Computer Graphics and Vision Graz University of Technology Graz Austria

Local image descriptors have proved themselves as useful tools for many computer vision tasks such as matching points between multiple images of a scene and object recognition. Current descriptors, such as SIFT, are designed to match image features with unique local neighborhoods. However, the interest point detectors used with SIFT often fail to select perceptible local structures in the image, and the SIFT descriptor does not directly encode the local neighborhood shape. In this paper we propose a symmetry based interest point detector and radial local structure descriptor which consistently captures the majority of basic local image structures and provides a geometrical description of the structure boundaries. This approach concentrates on the extraction of shape properties in image patches, which are an intuitive way to represent local appearance for matching and classification. We explore the specificity and sensitivity of this local descriptor in the context of classification of natural patterns. The implications of the performance comparison with standard approaches like SIFT are discussed.

关键词： Detectors Shape computer vision Layout Object recognition

来源：评论

学校读者我要写书评

暂无评论

Page layout analyser for multilingual Indian documents

Page layout analyser for multilingual Indian documents

引用

Language Engineering Conference

作者： A.R. Chaudhuri A.K. Mandal B.B. Chaudhuri Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Electronics and Communication Sciences Unit Indian Statistical Institute Kolkata India

An advanced Optical Character recognition (OCR) system is equipped with the module of the page layout analyser. It separates textual zones from non-textual zones. It identifies textual blocks from multicolumn documents and groups them into homogenous regions in terms of geometric shape and spatial distribution. All existing OCR modules developed for various Indian scripts can handle text only single-column documents. In this paper, a page, layout analyser that uses typical common features present in most of the Indian scripts is introduced. A simple compatibility criterion that allows various degrees of homogeneity is defined. The page-analyser is robust in the sense that it can distinguish text regions from non-textual entities such as images, rulers, and noisy signals due to smudges and poor quality of the paper. Test results are shown in two most popular Indian Scripts, Devnagari (Hindi) and Bangla.

关键词： Optical character recognition software Geometrical optics Optical sensors Character recognition Shape Robustness Testing

来源：评论

学校读者我要写书评

暂无评论

Duplicate open page removal from video stream of book flipping

Duplicate open page removal from video stream of book flippi...

引用

National Conference on computer vision, pattern recognition, Image Processing and Graphics (NCVPRIPG)

作者： Dibyayan Chakraborty Partha Pratim Roy Jose M. Alvarez Umapada Pal Department of computer Science Ramakrishna Mission Vivekananda University Howrah India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India NICTA Australia

Book flipping scanning refers to the process of recording a book while the user performs the flipping action of its pages. In recent years it has gained much attention as it reduces the workload of book digitization significantly. It is a challenging task because flipping at random speed and direction causes difficulties to identify distinct open page images (OPI) which represent each page of the book. In this paper, we propose a fast technique for removing duplicate open pages introduced in the video stream due to erroneous flipping. We present an algorithm that exploits cues from edge information of flipping pages. The nature of the cues extracted from the region of interest (ROI) of the frame, determines the flipping or an open state of a page whereas temporal position a flipping page determines the direction of the flipping. Combining these information we decide whether an open page image is a duplicate or not. Experiments are performed on video documents recorded using a standard resolution camera to validate the duplicate open page removal algorithm and we have obtained 95% accuracy.

关键词： Streaming media Feature extraction Cameras Optical character recognition software Image edge detection Accuracy Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Tensor Low-Rank Reconstruction for Semantic Segmentation 1

引用

16th European Conference on computer vision, ECCV 2020

作者： Chen, Wanli Zhu, Xinge Sun, Ruoqi He, Junjun Li, Ruiyu Shen, Xiaoyong Yu, Bei The Chinese University of Hong Kong New Territories Hong Kong Shanghai Jiao Tong University Shanghai China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SmartMore Shenzhen China

ISBN: (数字)9783030585204

ISBN: (纸本)9783030585198

Context information plays an indispensable role in the success of semantic segmentation. Recently, non-local self-attention based methods are proved to be effective for context information collection. Since the desired context consists of spatial-wise and channel-wise attentions, 3D representation is an appropriate formulation. However, these non-local methods describe 3D context information based on a 2D similarity matrix, where space compression may lead to channel-wise attention missing. An alternative is to model the contextual information directly without compression. However, this effort confronts a fundamental difficulty, namely the high-rank property of context information. In this paper, we propose a new approach to model the 3D context representations, which not only avoids the space compression but also tackles the high-rank difficulty. Here, inspired by tensor canonical-polyadic decomposition theory (i.e, a high-rank tensor can be expressed as a combination of rank-1 tensors.), we design a low-rank-to-high-rank context reconstruction framework (i.e, RecoNet). Specifically, we first introduce the tensor generation module (TGM), which generates a number of rank-1 tensors to capture fragments of context feature. Then we use these rank-1 tensors to recover the high-rank context features through our proposed tensor reconstruction module (TRM). Extensive experiments show that our method achieves state-of-the-art on various public datasets. Additionally, our proposed method has more than 100 times less computational cost compared with conventional non-local-based methods. © 2020, Springer Nature Switzerland AG.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

WDA-Net: Weakly-Supervised Domain Adaptive Segmentation of Electron Microscopy

arXiv

引用

arXiv 2022年

作者： Qiu, Dafei Yi, Jiajin Peng, Jialin Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University China Meitu Inc. Xiamen China College of Computer Science and Technology Huaqiao University China

Accurate segmentation of organelle instances is essential for electron microscopy analysis. Despite the outstanding performance of fully supervised methods, they highly rely on sufficient per-pixel annotated data and are sensitive to domain shift. Aiming to develop a highly annotation-efficient approach with competitive performance, we focus on weakly-supervised domain adaptation (WDA) with a type of extremely sparse and weak annotation demanding minimal annotation efforts, i.e., sparse point annotations on only a small subset of object instances. To reduce performance degradation arising from domain shift, we explore multi-level transferable knowledge through conducting three complementary tasks, i.e., counting, detection, and segmentation, constituting a task pyramid with different levels of domain invariance. The intuition behind this is that after investigating a related source domain, it is much easier to spot similar objects in the target domain than to delineate their fine boundaries. Specifically, we enforce counting estimation as a global constraint to the detection with sparse supervision, which further guides the segmentation. A cross-position cut-and-paste augmentation is introduced to further compensate for the annotation sparsity. Extensive validations show that our model with only 15% point annotations can achieve comparable performance as supervised models and shows robustness to annotation selection. © 2022, CC BY-NC-ND.

关键词： Electron microscopy

来源：评论

学校读者我要写书评

暂无评论

An improved convex programming model for the inverse problem in intensity-modulated radiation therapy

引用

International Journal of Performability Engineering 2018年第5期14卷 871-884页

作者： Lan, Yihua Zhang, Xingang Zhang, Jianyang Wang, Yang Hung, Chih-Cheng School of Computer and Information Technology Nanyang Normal University Nanyang473061 China Institute of Image Processing and Pattern Recognition Nanyang Normal University Nanyang473061 China Radiology Department Central Hospital of Nanyang Nanyang473061 China Laboratory for Machine Vision and Security Research College of Computing and Software Engineering Kennesaw State University - Marietta Campus 1100 South Marietta Parkway MariettaGA30067-2896 United States

Intensity modulated radiation therapy technology (IMRT) is one of the main approaches in cancer treatment because it can guarantee the killing of cancer cells while optimally protecting normal tissue from complications. Inverse planning, which is the core component of the entire IMRT system, is mainly based on accurate mathematical modeling and associated fast solving methods. In inverse planning, the fluence map optimization, which considers the multi-leaf collimator (MLC) modulation, is the current research focus. Although the hitting constrain problem with the unidirectional movement of leaf-sweeping has been solved, our goal is to solve the hitting constrain problem with the bidirectional movement of leaf-sweeping. In this study, we propose a non-synchronized type to solve the hitting constrain problem with the bidirectional movement of leaf-sweeping schemes for IMRT. In solving this problem, a new mathematical model is proposed under the framework of convex programming. The advantage of the convex model is to avoid the uncertainty and inaccuracy that occurs in the non-convex programming solving process. Experimental results for two clinical testing cases show that under the same condition of total number of monitoring units, the new proposed model produces better dose distribution than those of the total variance and quadratic models. © 2018 Totem Publisher, Inc. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Combination of product graph and random walk kernel for symbol spotting in graphical documents

Combination of product graph and random walk kernel for symb...

引用

International Conference on pattern recognition

作者： Anjan Dutta Jaume Gibert Josep Lladós Horst Bunke Umapada Pal Computer Vision Center Universitat Autònoma de Barcelona Barcelona Spain Institute of Computer Science and Applied Mathematics Universitat Bern Bern Switzerland Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9781467322164

This paper explores the utilization of product graph for spotting symbols on graphical documents. Product graph is intended to find the candidate subgraphs or components in the input graph containing the paths similar to the query graph. The acute angle between two edges and their length ratio are considered as the node labels. In a second step, each of the candidate subgraphs in the input graph is assigned with a distance measure computed by a random walk kernel. Actually it is the minimum of the distances of the component to all the components of the model graph. This distance measure is then used to eliminate dissimilar components. The remaining neighboring components are grouped and the grouped zone is considered as a retrieval zone of a symbol similar to the queried one. The entire method works online, i.e., it doesn't need any preprocessing step. The present paper reports the initial results of the method, which are very encouraging.

关键词： Kernel Computational modeling pattern recognition Databases Labeling Equations Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Networks Exploiting Attributes of Biological Neurons

arXiv

引用

arXiv 2023年

作者： Singh, Neeraj Kumar Pal, Nikhil R. Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Electronics and Communication Sciences Unit Indian Statistical Institute Kolkata India

In this era of artificial intelligence, deep neural networks like Convolutional Neural Networks (CNNs) have emerged as front-runners, often surpassing human capabilities. These deep networks are often perceived as the panacea for all challenges. Unfortunately, a common downside of these networks is their"black-box" character, which does not necessarily mirror the operation of biological neural systems. Some even have millions/billions of learnable (tunable) parameters, and their training demands extensive data and time. Here, we integrate the principles of biological neurons in certain layer(s) of CNNs. Specifically, we explore the use of neuro-science-inspired computational models of the Lateral Geniculate Nucleus (LGN) and simple cells of the primary visual cortex. By leveraging such models, we aim to extract image features to use as input to CNNs, hoping to enhance training efficiency and achieve better accuracy. We aspire to enable shallow networks with a Push-Pull Combination of Receptive Fields (PP-CORF) model of simple cells as the foundation layer of CNNs to enhance their learning process and performance. To achieve this, we propose a two-tower CNN, one shallow tower and the other as ResNet 18. Rather than extracting the features blindly, it seeks to mimic how the brain perceives and extracts features. The proposed system exhibits a noticeable improvement in the performance (on an average of 5% − 10%) on CIFAR-10, CIFAR-100, and ImageNet-100 datasets compared to ResNet-18. We also check the efficiency of only the Push-Pull tower of the network. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Recovering epipolar geometry by reactive tabu search

Recovering epipolar geometry by reactive tabu search

引用

International Conference on computer vision (ICCV)

作者： Qifa Ke Gang Xu Song De Ma National Laboratory of Pattern Recognition Institute of Automation Chinese Academy and Sciences Beijing China Computer Vision Laboratory Department of Computer Science Ritsumeikan University Kusatsu Shiga Japan

ISBN: (纸本)8173192219

In this paper we propose a new approach to recovering epipolar geometry from a pair of uncalibrated images. We first detect the feature points. By minimizing a proposed cost function, we match the feature points, discard the outliers and recover the epipolar geometry in one step. Experiments on real images show that this approach is effective and fast.

关键词： Equations Cost function computer vision Laboratories pattern recognition Automation computer science Computational geometry Image reconstruction Layout

来源：评论

学校读者我要写书评

暂无评论

A Statistics and Local Homogeneity Based Color Edge Detection Algorithm

A Statistics and Local Homogeneity Based Color Edge Detectio...

引用

International Conference on Advances in Recent Technologies in Communication and Computing, ARTCom

作者： Soumya Dutta Bidyut B. Chaudhuri Department of Electronics and Communication Netaji Subhash Engineering College Kolkata India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

Edge detection is one of the most commonly used operations in image processing and pattern recognition, the reason for this is that edges form the outline of an object. An edge is the boundary between an object and the background, and indicates the boundary between overlapping objects. This means that if the edges in an image can be identified accurately, all of the objects can be located and basic properties such as area, perimeter, and shape can be measured. Since computer vision involves the identification and classification of objects in an image, edge detection is an essential tool. Efficient and accurate edge detection will lead to increase the performance of subsequent image processing techniques, including image segmentation, object-based image coding, and image retrieval. A novel color edge detection algorithm is proposed in this paper. On the basis of standard deviation calculation of pixels the discontinuity among the pixels are detected. Then the image is segmented into a binary image with a fixed threshold where black pixels signify homogeneous region and white pixels signify edges. Finally, a thinning technique is applied to extract thin edges. The proposed method is applied over large database of color images both synthetic and real life images and performance of the algorithm is evident from the results and is comparable with other edge detection algorithms.

关键词： Statistics Image edge detection Image processing Object recognition Shape measurement Image segmentation Pixel pattern recognition Area measurement 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：