检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Shen, Haoran Zhang, Yifu Wang, Wenxuan Chen, Chen Liu, Jing Song, Shanshan Li, Jiangyun School of Automation and Electrical Engineering University of Science and Technology Beijing China Center for Research in Computer Vision University of Central Florida United States National Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences China

Recent works have shown that the computational efficiency of 3D medical image (e.g. CT and MRI) segmentation can be impressively improved by dynamic inference based on slice-wise complexity. As a pioneering work, a dynamic architecture network for medical volumetric segmentation (i.e. Med-DANet [44]) has achieved a favorable accuracy and efficiency trade-off by dynamically selecting a suitable 2D candidate model from the pre-defined model bank for different slices. However, the issues of incomplete data analysis, high training costs, and the two-stage pipeline in Med-DANet require further improvement. To this end, this paper further explores a unified formulation of the dynamic inference framework from the perspective of both the data itself and the model structure. For each slice of the input volume, our proposed method dynamically selects an important foreground region for segmentation based on the policy generated by our Decision Network and Crop Position Network. Besides, we propose to insert a stage-wise quantization selector to the employed segmentation model (e.g. U-Net) for dynamic architecture adapting. Extensive experiments on BraTS 2019 and 2020 show that our method achieves comparable or better performance than previous state-of-the-art methods with much less model complexity. Compared with previous methods Med-DANet and TransBTS with dynamic and static architecture respectively, our framework improves the model efficiency by up to nearly 4.1 and 17.3 times with comparable segmentation results on BraTS 2019. Copyright © 2023, The Authors. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

PIPAL: A Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration 16th

PIPAL: A Large-Scale Image Quality Assessment Dataset for Pe...

引用

16th European Conference on computer vision, ECCV 2020

作者： Jinjin, Gu Haoming, Cai Haoyu, Chen Xiaoxing, Ye Ren, Jimmy S. Chao, Dong The School of Data Science The Chinese University of Hong Kong Shenzhen China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China SenseTime Research Science Park Hong Kong SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9783030586201

Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent IR methods based on Generative Adversarial Networks (GANs) have achieved significant improvement in visual performance, but also presented great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. Then we raise two questions: (1) Can existing IQA methods objectively evaluate recent IR algorithms? (2) When focus on beating current benchmarks, are we getting better IR algorithms? To answer these questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) dataset. Especially, this dataset includes the results of GAN-based methods, which are missing in previous datasets. We collect more than 1.13 million human judgments to assign subjective scores for PIPAL images using the more reliable "Elo system". Based on PIPAL, we present new benchmarks for both IQA and super-resolution methods. Our results indicate that existing IQA methods cannot fairly evaluate GAN-based IR algorithms. While using appropriate evaluation methods is important, IQA methods should also be updated along with the development of IR algorithms. At last, we improve the performance of IQA networks on GAN-based distortions by introducing anti-aliasing pooling. Experiments show the effectiveness of the proposed method. © 2020, Springer Nature Switzerland AG.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

ICDAR 2013 Handwriting Segmentation Contest

ICDAR 2013 Handwriting Segmentation Contest

引用

International Conference on Document Analysis and recognition

作者： Nikolaos Stamatopoulos Basilis Gatos Georgios Louloudis Umapada Pal Alireza Alaei Computational Intelligence Laboratory Institute of Informatics and Telecommunications National Center for Scientific Research Demokritos Athens Greece Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India Computer Science Laboratory Universite Francois Rabelais Tours France

ISBN: (纸本)9781479901937

This paper presents the results of the Handwriting Segmentation Contest that was organized in the context of the ICDAR2013. The general objective of the contest was to use well established evaluation practices and procedures to record recent advances in off-line handwriting segmentation. Two benchmarking datasets, one for text line and one for word segmentation, were created in order to test and compare all submitted algorithms as well as some state-of-the-art methods for handwritten document image segmentation in realistic circumstances. Handwritten document images were produced by many writers in two Latin based languages (English and Greek) and in one Indian language (Bangla, the second most popular language in India). These images were manually annotated in order to produce the ground truth which corresponds to the correct text line and word segmentation results. The datasets of previously organized contests (ICDAR2007, ICDAR2009 and ICFHR2010 Handwriting Segmentation Contests) along with a dataset of Bangla document images were used as training dataset. Eleven methods are submitted in this competition. A brief description of the submitted algorithms, the evaluation criteria and the segmentation results obtained from the submitted methods are also provided in this manuscript.

关键词： Image segmentation Educational institutions Handwriting recognition Benchmark testing Measurement Matched filters Text analysis

来源：评论

学校读者我要写书评

暂无评论

Asymmetric distances for binary embeddings

Asymmetric distances for binary embeddings

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Albert Gordo Florent Perronnin Computer Vision Center Universitat Autònoma Barcelona Spain Textual and Visual Pattern Analysis Xerox Research Centre Europe France

In large-scale query-by-example retrieval, embedding image signatures in a binary space offers two benefits: data compression and search efficiency. While most embedding algorithms binarize both query and database signatures, it has been noted that this is not strictly a requirement. Indeed, asymmetric schemes which binarize the database signatures but not the query still enjoy the same two benefits but may provide superior accuracy. In this work, we propose two general asymmetric distances which are applicable to a wide variety of embedding techniques including Locality Sensitive Hashing (LSH), Locality Sensitive Binary Codes (LSBC), Spectral Hashing (SH) and Semi-Supervised Hashing (SSH). We experiment on four public benchmarks containing up to 1M images and show that the proposed asymmetric distances consistently lead to large improvements over the symmetric Hamming distance for all binary embedding techniques. We also propose a novel simple binary embedding technique - PCA Embedding (PCAE) - which is shown to yield competitive results with respect to more complex algorithms such as SH and SSH.

关键词： Databases Kernel Euclidean distance Principal component analysis Approximation methods Table lookup Random access memory

来源：评论

学校读者我要写书评

暂无评论

MORPHEME-BASED FEATURE-RICH LANGUAGE MODELS USING DEEP NEURAL NETWORKS FOR LVCSR OF EGYPTIAN ARABIC

MORPHEME-BASED FEATURE-RICH LANGUAGE MODELS USING DEEP NEURA...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Amr El-Desoky Mousa Hong-Kwang Jeff Kuo Lidia Mangu Hagen Soltau Human Language Technology and Pattern Recognition - Computer Science Department RWTH Aachen University IBM T. J. Watson Research Center

ISBN: (纸本)9781479903573

Egyptian Arabic (EA) is a colloquial version of Arabic. It is a low-resource morphologically rich language that causes problems in Large Vocabulary Continuous Speech recognition (LVCSR). Building LMs on morpheme level is considered a better choice to achieve higher lexical coverage and better LM probabilities. Another approach is to utilize information from additional features such as morphological tags. On the other hand, LMs based on Neural Networks (NNs) with a single hidden layer have shown superiority over the conventional n-gram LMs. Recently, Deep Neural Networks (DNNs) with multiple hidden layers have achieved better performance in various tasks. In this paper, we explore the use of feature-rich DNN-LMs, where the inputs to the network are a mixture of words and morphemes along with their features. Significant Word Error Rate (WER) reductions are achieved compared to the traditional word-based LMs.

关键词： Language model Morpheme Feature-rich Deep neural network Egyptian Arabic modelling languages Neural network Arabic language additional features Word Religious Missions Continuous speech recognition

来源：评论

学校读者我要写书评

暂无评论

A simple and effective approach for border noise removal from document images

A simple and effective approach for border noise removal fro...

引用

IEEE International Conference on Multi Topic

作者： Faisal Shafait Thomas M. Breuel Image Understanding and Pattern Recognition Research Group German Research Center for Artificial Intelligence Kaiserslautern Germany Department of Computer Science Technical University of Kaiserslautern Kaiserslautern Germany

When digitizing bound material like books or magazines, marginal noise appears along the page border. This noise consists of undesired text parts from the neighboring page and/or speckles that result from the binarization process. When a keyword based search is performed in a digitized collection, textual noise in particular poses problems since the returned search results might correspond to textual noise instead of actual contents of the page. Manually removing marginal noise for each page is not feasible in large scale digitization projects. In this paper, we present a simple and effective approach for removing both textual and non-textual noise by finding borders of noise regions using projection profile analysis. We demonstrate the effectiveness of our approach by evaluating it quantitatively on the widely used University of Washington (UW3) dataset. The results show that our approach reduces the noise ratio from 70% to 20% while retaining more than 99% of actual page contents. Comparison with state-of-the-art approaches shows that our algorithm performs comparable to them, while being simple to understand and easy to implement. We also provide an open source implementation of our method as part of the OCRopus OCR system.

关键词： Books Optical character recognition software Filters Signal to noise ratio Optical noise Character recognition Bars Cleaning Image analysis pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Learning to predict context-adaptive convolution for semantic segmentation

arXiv

引用

arXiv 2020年

作者： Liu, Jianbo He, Junjun Ren, Jimmy S. Qiao, Yu Li, Hongsheng CUHK-SenseTime Joint Laboratory Chinese University of Hong Kong Shenzhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SenseTime Research

Long-range contextual information is essential for achieving high-performance semantic segmentation. Previous feature re-weighting methods [34] demonstrate that using global context for re-weighting feature channels can effectively improve the accuracy of semantic segmentation. However, the globally-sharing feature re-weighting vector might not be optimal for regions of different classes in the input image. In this paper, we propose a Context-adaptive Convolution Network (CaC-Net) to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps. In CaC-Net, a set of context-adaptive convolution kernels are predicted from the global contextual information in a parameter-efficient manner. When used for convolution with the semantic feature maps, the predicted convolutional kernels can generate the spatially-varying feature weighting factors capturing both global and local contextual information. Comprehensive experimental results show that our CaC-Net achieves superior segmentation performance on three public datasets, PASCAL Context, PASCAL VOC 2012 and ADE20K. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Automated scoring of Bender Gestalt Test using image analysis techniques

Automated scoring of Bender Gestalt Test using image analysi...

引用

International Conference on Document Analysis and recognition

作者： Momina Moetesum Imran Siddiqi Uzma Masroor Chawki Djeddi Center of Computer Vision and Pattern Recognition Bahria University Islamabad Pakistan Dept. of Professional Psychology Bahria University Islamabad Pakistan LAMIS Laboratory Larbi Tebessi University Tebessa Algeria

ISBN: (纸本)9781479918065

Drawing tests have been long used by practitioners and researchers for early detection of psychological and neurological impairments. These tests allow subjects to naturally express themselves as opposed to an interview or a written assessment. Bender Gestalt Test (BGT) is a well-known and established neurological test designed to detect signs of perceptual distortions. Subjects are shown a number of geometric patterns for reconstruction and assessments are made by observing properties like rotation, angulations, simplification and closure difficulty. The manual scoring of the test, however, is a time consuming and lengthy procedure especially when a large number of subjects is to be analyzed. This paper proposes the application of image analysis techniques to automatically score a subset of hand drawn images in the BGT test. A comparison of the scores reported by the automated system with those assigned by the psychologists not only reveals the effectiveness of the proposed system but also reflects the huge research potential this area possesses.

关键词： Manuals Psychology Biomedical imaging Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Color constancy and non-uniform illumination: Can existing algorithms work?

Color constancy and non-uniform illumination: Can existing a...

引用

International Conference on computer vision Workshops (ICCV Workshops)

作者： Michael Bleier Christian Riess Shida Beigpour Eva Eibenberger Elli Angelopoulou Tobias Tröger André Kaup Pattern Recognition Lab University of Erlangen-Nuremberg Germany Computer Vision Center Universidad Autónoma de Barcelona Spain Multimedia Communications and Signal Processing University of Erlangen-Nuremberg Germany

The color and distribution of illuminants can significantly alter the appearance of a scene. The goal of color constancy (CC) is to remove the color bias introduced by the illuminants. Most existing CC algorithms assume a uniformly illuminated scene. However, more often than not, this assumption is an insufficient approximation of real-world illumination conditions (multiple light sources, shadows, interreflections, etc.). Thus, illumination should be locally determined, taking under consideration that multiple illuminants may be present. In this paper we investigate the suitability of adapting 5 state-of-the-art color constancy methods so that they can be used for local illuminant estimation. Given an arbitrary image, we segment it into superpixels of approximately similar color. Each of the methods is applied independently on every superpixel. For improved accuracy, these independent estimates are combined into a single illuminant-color value per superpixel. We evaluated different fusion methodologies. Our experiments indicate that the best performance is obtained by fusion strategies that combine the outputs of the estimators using regression.

关键词： Image color analysis Lighting Databases Light sources Image segmentation Estimation Bayesian methods

来源：评论

学校读者我要写书评

暂无评论

Neural Information Processing 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： Nikhil Ranjan Pal Nik Kasabov Rajani K. Mudi Srimanta Pal Swapan Kumar Parui

ISBN: (数字)9783540304999

ISBN: (纸本)9783540239314

It is our great pleasure to welcome you to the 11th International Conference on Neural Information Processing (ICONIP 2004) to be held in Calcutta. ICONIP 2004 is organized jointly by the Indian Statistical Institute (ISI) and Jadavpur University (JU). We are con?dent that ICONIP 2004, like the previous conf- ences in this series,will providea forum for fruitful interactionandthe exchange of ideas between the participants coming from all parts of the globe. ICONIP 2004 covers all major facets of computational intelligence, but, of course, with a primary emphasis on neural networks. We are sure that this meeting will be enjoyable academically and otherwise. We are thankful to the track chairs and the reviewers for extending their support in various forms to make a sound technical program. Except for a few cases, where we could get only two review reports, each submitted paper was reviewed by at least three referees, and in some cases the revised versions were againcheckedbythereferees. Wehad470submissionsanditwasnotaneasytask for us to select papers for a four-day conference. Because of the limited duration of the conference, based on the review reports we selected only about 40% of the contributed papers. Consequently, it is possible that some good papers are left out. We again express our sincere thanks to all referees for accomplishing a great job. In addition to 186 contributed papers, the proceedings includes two plenary presentations, four invited talks and 18 papers in four special sessions. The proceedings is organized into 26 coherent topical groups.

关键词： Artificial Intelligence Computation by Abstract Devices pattern recognition Image Processing and computer vision Probability and Statistics in computer Science Algorithm Analysis and Problem Complexity

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：