检索结果-内蒙古大学图书馆

Tensor Low-Rank Reconstruction for Semantic Segmentation 1

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

Age estimation using disconnectedness features in handwriting 15

Age estimation using disconnectedness features in handwritin...

引用

15th IAPR International Conference on Document Analysis and recognition, ICDAR 2019

作者： Basavaraja, V. Shivakumara, Palaiahnakote Guru, D.S. Pal, Umapada Lu, Tong Blumenstein, Michael Department of Studies in Computer Science University of Mysore Mysore Karnataka India Faculty of Computer System and Information Technology University of Malaya Kuala Lumpur Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University Nanjing China University of Technology Sydney Australia

ISBN: (纸本)9781728128610

Real-time applications of handwriting analysis have increased drastically in the fields of forensic and information security because of accurate cues. One of such applications is human age estimation based on handwriting for the purpose of immigrant checking. In this paper, we have proposed a new method for age estimation using handwriting analysis using Hu invariant moments and disconnectedness features. To make the proposed method robust to both ruled and un-ruled documents, we propose to explore intersection point detection in Canny edge images of each input document, which results in text components. For each text component pair, we propose Hu invariant moments for extracting disconnectedness features, which in fact measure multi-shape components based on distance, shape and mutual position analysis of components. Furthermore, iterative k-means clustering is proposed for the classification of different age groups. Experimental results on our dataset and some standard datasets, namely, IAM and KHATT, show that the proposed method is effective and outperforms the state-of-the-art methods. © 2019 IEEE.

关键词： Security of data

来源：评论

学校读者我要写书评

暂无评论

Efficient adaptive face recognition systems based on capture conditions

Efficient adaptive face recognition systems based on capture...

引用

2014 IEEE Symposium Series on Computational Intelligence, IEEE SSCI 2014 - 2014 IEEE Symposium on Computational Intelligence in Biometrics and Identity Management, CIBIM 2014

作者： Pagano, C. Granger, E. Sabourin, R. Rattani, A. Marcialis, G.-L. Roli, F. Lab. d'Imagerie De Vision et d'Intelligence Artificielle École de Technologie Supérieure Université du Québec MontrealQC Canada Pattern Recognition and Applications Group Dept. of Electrical and Electronic Engineering University of Cagliari Cagliari Italy

ISBN: (纸本)9781479945344

In many face recognition (FR) applications, changing capture conditions lead to divergence between facial models stored during enrollment and faces captured during operations. Moreover, it is often costly or infeasible to capture several high quality reference samples a priori to design representative facial models. Although self-updating models using high-confidence face captures appear promising, they raise several challenges when capture conditions change. In particular, face models of individuals may be corrupted by misclassified input captures, and their growth may require pruning to bound system complexity over time. This paper presents a system for self-update of facial models that exploits changes in capture conditions to assure the relevance of templates and to limit the growth of template galleries. The set of reference templates (facial model) of an individual is only updated to include new faces that are captured under significantly different conditions. In a particular implementation of this system, illumination changes are detected in order to select face captures from bio-login to be stored in a gallery. Face captures from a built-in still or video camera are taken at periodic intervals to authenticate the user having accessed a secured computer or network. Experimental results produced with the DIEE dataset show that the proposed system provides a comparable level of performance to the FR system that self-updates the gallery on all high-confidence face captures, but with significantly lower complexity, i.e., number of templates per individual. © 2014 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Local Structure Detection with Orientation-invariant Radial Configuration

Local Structure Detection with Orientation-invariant Radial ...

引用

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

MetaCleaner: Learning to Hallucinate Clean Representations for Noisy-labeled Visual recognition

MetaCleaner: Learning to Hallucinate Clean Representations f...

引用

IEEE/CVF Conference on computer vision and pattern recognition

作者： Weihe Zhang Yali Wang Yu Qiao Shenzhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences

ISBN: (纸本)9781728132945

Deep Neural Networks (DNNs) have achieved remarkable successes in large-scale visual recognition. However, they often suffer from overfitting under noisy labels. To alleviate this problem, we propose a conceptually simple but effective MetaCleaner, which can learn to hallucinate a clean representation of an object category, according to a small noisy subset from the same category. Specially, MetaCleaner consists of two flexible submodules. The first sub-module, namely Noisy Weighting, can estimate the confidence scores of all the images in the noisy subset, by analyzing their deep features jointly. The second submodule, namely Clean Hallucinating, can generate a clean representation from the noisy subset, by summarizing the noisy images with their confidence scores. Via MetaCleaner, DNNs can strengthen its robustness to noisy labels, as well as enhance its generalization capacity with richer data diversity. Moreover, MetaCleaner can be easily integrated into the standard training procedure of DNNs, which promotes its value for real-life applications. We conduct extensive experiments on two popular benchmarks in noisy-labeled recognition, i.e., Food-101N and Clothing1M. For both datasets, our MetaCleaner significantly outperforms baselines, and achieves the state-of-the-art performance.

关键词： Noise Hallucinations confidence training procedure submodule recognition (Psychology) Dataset

来源：评论

学校读者我要写书评

暂无评论

Deformation Robust Text Spotting with Geometric Prior

Deformation Robust Text Spotting with Geometric Prior

引用

IEEE International Conference on Image Processing

作者： Xixuan Hao Aozhong Zhang Xianze Meng Bin Fu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institute of Advanced Technology Chinese Academy of Sciences The University of Hong Kong

The goal of text spotting is to perform text detection and recognition simultaneously. Although the diversity of luminosity and orientation in scene texts has been widely studied, the font diversity and shape variance of the same character are ignored in recent works, since most characters in natural images are rendered in standard fonts. To solve this problem, we present a Chinese Artistic Dataset, termed as ARText, which contains 33, 000 artistic images with rich shape deformation and font diversity. Based on this database, we develop a deformation robust text spotting method (DR TextSpotter) to solve the recognition problem of complex deformation of characters in different fonts. Specifically, we propose a geometric prior module to highlight the important features based on the unsupervised landmark detection sub-network. A graph convolution network is further constructed to fuse the character features and landmark features, and then performs semantic reasoning to enhance the discrimination for different characters. The experiments are conducted on ARText and IC19-ReCTS datasets. Our results demonstrate the effectiveness of our proposed method. The datasets and models will become publicly available after publication.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The equipment nameplate dataset for scene text detection and recognition

The equipment nameplate dataset for scene text detection and...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Chen, Xiaolong Zhang, Zhengfu Qiao, Yu Zhang, Pu Guo, Lanqing Chen, Wenrui Chen, Chen Fu, Bin Guangzhou Power Supply Bureau Co. Ltd. Guangzhou China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

ISBN: (纸本)9781728163215

In this paper, we introduce the Equipment Nameplate Dataset, a large dataset for scene text detection and recognition. Natural images in this dataset are taken in the wild and thus this dataset includes various intra-class inconsistency such as ill illumination conditions and partly occluded, which makes our dataset more challenging than other datasets. In order to make people train detection and recognition model separately, we annotate our dataset not only word instance, but also text region by using rectangle bounding boxes. Some detailed statistics information about our dataset will be given so that people can use them to analyse and develop their own models. Moreover, we use our dataset to test some famous detection and recognition models and present the corresponding results in order to make researcher compare them with their own models. Dataset will be publicly available on the website. © 2019 IEEE.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Image compression with recurrent neural network and generalized divisive normalization

arXiv

引用

arXiv 2021年

作者： Islam, Khawar Dang, L. Minh Lee, Sujin Moon, Hyeonjoon Computer Vision and Pattern Recognition Lab. Sejong University Korea Republic of Department of Artificial Intelligence Sejong University Korea Republic of

Image compression is a method to remove spatial redundancy between adjacent pixels and reconstruct a high-quality image. In the past few years, deep learning has gained huge attention from the research community and produced promising image reconstruction results. Therefore, recent methods focused on developing deeper and more complex networks, which significantly increased network complexity. In this paper, two effective novel blocks are developed: analysis and synthesis block that employs the convolution layer and Generalized Divisive Normalization (GDN) in the variable-rate encoder and decoder side. Our network utilizes a pixel RNN approach for quantization. Furthermore, to improve the whole network, we encode a residual image using LSTM cells to reduce unnecessary information. Experimental results demonstrated that the proposed variable-rate framework with novel blocks outperforms existing methods and standard image codecs, such as George’s [11] and JPEG in terms of image similarity. © 2021, CC BY.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Car Plate Detection Using Cascaded Tree-Style Learner Based on Hybrid Object Features

Car Plate Detection Using Cascaded Tree-Style Learner Based ...

引用

IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS)

作者： Qiang Wu Huaifeng Zhang Wenjing Jia Xiangjian He Jie Yang Tom Hintz Computer Vision Research Group University of Technology Broadway NSW Australia Institute of Image Process. & Pattern Recognition Shanghai Jiaotong University China

Car plate detection is a key component in automatic license plate recognition system. This paper adopts an enhanced cascaded tree style learner framework for car plate detection using the hybrid object features including the simple statistical features and Harr-like features. The statistical features are useful for simplifying the process on cascade classifier. The cascaded tree-style detector design will further reduce the false alarm and the false dismissal while retaining a high detection ratio. The experimental results obtained by the proposed algorithm exhibit the encouraging performance.

关键词： Object detection Licenses Detectors computer vision pattern recognition Lighting Interference Australia Image recognition Robustness

来源：评论

学校读者我要写书评

暂无评论

Orientation robust scene text recognition in natural scene

Orientation robust scene text recognition in natural scene

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Chen, Xiaolong Zhang, Zhengfu Qiao, Yu Lai, Jiangyu Jiang, Jian Zhang, Zeyu Fu, Bin Guangzhou Power Supply Bureau Co. Ltd. Guangzhou China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

ISBN: (纸本)9781728163215

In recent years, scene text recognition has achieved significant improvement and various state-of-the-art recognition approaches have been proposed. This paper focused on recognizing text in natural photos of equipment nameplates, which has wide applications in industrial automations. This task only receives little attentions in previous works. The challenge of this problem comes from multi-orientation, curved, noisy and blurry text patches in equipment nameplates. To address this problem, we propose a deep model for text recognition in multi-oriented nameplates, namely, Orientation Robust Scene Text recognition (ORSTR). Specifically, our model employs a rectification module to transform curved, distorted or multi-orientation text to near-horizontal text with a carefully designed rectification module. Once the near-horizontal text has been generated, recognition network will output the predictions of text patches. Our scene text recognition model achieves 90.8% recognition accuracy on equipment nameplate dataset which outperforms previous scene text recognition model (CRNN) about 0.8%. Several extensive experiments have been conducted to verify the effectiveness of our model. © 2019 IEEE.

关键词： Nameplates

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：