检索结果-内蒙古大学图书馆

作者： Frinken, Volkmar Fischer, Andreas Baumgartner, Markus Bunke, Horst Computer Vision Center Autonomous University of Barcelona Edifici O 08193 Bellaterra Barcelona Spain Centre for Pattern Recognition and Machine Intelligence Concordia University 1455 de Maisonneuve Blvd West Montreal QC H3G 1M8 Canada Institute of Computer Science and Applied Mathematics University of Bern Neubrückstrasse 10 CH-3012 Bern Switzerland

The automatic transcription of unconstrained continuous handwritten text requires well trained recognition systems. The semi-supervised paradigm introduces the concept of not only using labeled data but also unlabeled data in the learning process. Unlabeled data can be gathered at little or not cost. Hence it has the potential to reduce the need for labeling training data, a tedious and costly process. Given a weak initial recognizer trained on labeled data, self-training can be used to recognize unlabeled data and add words that were recognized with high confidence to the training set for re-training. This process is not trivial and requires great care as far as selecting the elements that are to be added to the training set is concerned. In this paper, we propose to use a bidirectional long short-term memory neural network handwritten recognition system for keyword spotting in order to select new elements. A set of experiments shows the high potential of self-training for bootstrapping handwriting recognition systems, both for modern and historical handwritings, and demonstrate the benefits of using keyword spotting over previously published self-training schemes. © 2013 Elsevier Ltd. All rights reserved.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Adaptive nonlinear auto-associative modeling through manifold learning

引用

9th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining, PAKDD 2005

作者： Zhang, Junping Li, Stan Z. Intelligent Information Processing Laboratory Department of Computer Science and Engineering Fudan University Shanghai 200433 China Key Laboratory of Complex Systems and Intelligence Science Chinese Academy of Sciences China National Laboratory of Pattern Recognition Center for Biometrics and Security Research Institute of Automation Beijing 100080 China

ISBN: (纸本)3540260765

We propose adaptive nonlinear auto-associative modeling (ANAM) based on Locally Linear Embedding algorithm (LLE) for learning intrinsic principal features of each concept separately and recognition thereby. Unlike traditional supervised manifold learning algorithm, the proposed ANAM algorithm has several advantages: 1) it implicitly embodies discriminant information because the suboptimal parameters of ANAM are determined based on error rate of the validation set. 2) it avoids the curse of dimensionality without loss accuracy because recognition is completed in the original space. Experiments on character and digit databases show that the advantages of the proposed ANAM algorithm. © Springer-Verlag Berlin Heidelberg 2005.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Leveraging category-level labels for instance-level image retrieval

Leveraging category-level labels for instance-level image re...

引用

Conference on computer vision and pattern recognition (CVPR)

作者： Albert Gordoa José A. Rodríguez-Serrano Florent Perronnin Ernest Valveny Computer Vision Center Universitat Autònoma de Barcelona Spain Textual and Visual Pattern Analysis Xerox Research Center Europe France

In this article, we focus on the problem of large-scale instance-level image retrieval. For efficiency reasons, it is common to represent an image by a fixed-length descriptor which is subsequently encoded into a small number of bits. We note that most encoding techniques include an unsupervised dimensionality reduction step. Our goal in this work is to learn a better subspace in a supervised manner. We especially raise the following question: "can category-level labels be used to learn such a subspace?" To answer this question, we experiment with four learning techniques: the first one is based on a metric learning framework, the second one on attribute representations, the third one on Canonical Correlation Analysis (CCA) and the fourth one on Joint Subspace and Classifier Learning (JSCL). While the first three approaches have been applied in the past to the image retrieval problem, we believe we are the first to show the usefulness of JSCL in this context. In our experiments, we use ImageNet as a source of category-level labels and report retrieval results on two standard dataseis: INRIA Holidays and the University of Kentucky benchmark. Our experimental study shows that metric learning and attributes do not lead to any significant improvement in retrieval accuracy, as opposed to CCA and JSCL. As an example, we report on Holidays an increase in accuracy from 39.3% to 48.6% with 32-dimensional representations. Overall JSCL is shown to yield the best results.

关键词： Measurement Vectors Principal component analysis Accuracy Encoding Correlation Image retrieval

来源：评论

学校读者我要写书评

暂无评论

Med-DANet V2: A Flexible Dynamic Architecture for Efficient Medical Volumetric Segmentation

arXiv

引用

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

A multi-objective deep reinforcement learning algorithm for spatio-temporal latency optimization in mobile IoT-enabled edge computing networks

引用

Simulation Modelling Practice and Theory 2025年 143卷

作者： Parisa Khoshvaght Amir Haider Amir Masoud Rahmani Farhad Soleimanian Gharehchopogh Ferzat Anka Jan Lansky Mehdi Hosseinzadeh Institute of Research and Development Duy Tan University Da Nang Vietnam School of Engineering & Technology Duy Tan University Da Nang Vietnam Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura 140401 Punjab India Department of AI and Robotics Sejong University Seoul 05006 Republic of Korea Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Computer Engineering Ur. C. Islamic Azad University Urmia Iran Data Science Application and Research Center (VEBIM) Fatih Sultan Mehmet Vakif University Istanbul Türkiye Department of Computer Science and Mathematics Faculty of Economic Studies University of Finance and Administration Prague Czech Republic Pattern Recognition and Machine Learning Laboratory School of Computing Gachon University Seongnam Republic of Korea

The rapid increase in Mobile Internet of Things (IoT) devices requires novel computational frameworks. These frameworks must meet strict latency and energy efficiency requirements in Edge and Mobile Edge Computing (MEC) systems. Spatio-temporal dynamics, which include the position of edge servers and the timing of task schedules, pose a complex optimization problem. These challenges are further exacerbated by the heterogeneity of IoT workloads and the constraints imposed by device mobility. The balance between computational overhead and communication challenges is also a problem. To solve these issues, advanced methods are needed for resource management and dynamic task scheduling in mobile IoT and edge computing environments. In this paper, we propose a Deep Reinforcement Learning (DRL) multi-objective algorithm, called a Double Deep Q-Learning (DDQN) framework enhanced with Spatio-temporal mobility prediction, latency-aware task offloading, and energy-constrained IoT device trajectory optimization for federated edge computing networks. DDQN was chosen for its optimize stability and reduced overestimation in Q-values. The framework employs a reward-driven optimization model that dynamically prioritizes latency-sensitive tasks, minimizes task migration overhead, and balances energy efficiency across devices and edge servers. It integrates dynamic resource allocation algorithms to address random task arrival patterns and real-time computational demands. Simulations demonstrate up to a 35 % reduction in end-to-end latency, a 28 % improvement in energy efficiency, and a 20 % decrease in the deadline-miss ratio compared to benchmark algorithms.

关键词：

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

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：