检索结果-内蒙古大学图书馆

16th International Conference on Genetic and Evolutionary Computing, ICGEC 2024

作者： Kakinoki, Kanta Katayama, Tetsuro Department of Computer Science and Systems Engineering Faculty of Engineering University of Miyazaki 1-1 Gakuen-Kibanadai Nishi Miyazaki889-2192 Japan

ISBN: (纸本)9789819615346

To extract important information from the document images, document layout analysis research has been carried out. Previous research analyzes document layouts only for specific document formats. This paper proposes a document layout analysis method that adopts pre-processing based on document image classification to analyze document layouts for various document formats. From the application examples, we have confirmed that the proposed method can correctly analyze document layout by using training models trained for each document format. Furthermore, to evaluate the usefulness of the proposed method, we have compared the F score of the proposed method for document layout analysis using a single training model covering various document formats and using a training model generated for each document format. As a result, we have confirmed that our proposed method is useful in document layout analysis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： document image classification document layout analysis rule-based correction

来源：评论

学校读者我要写书评

暂无评论

document image classification: Progress over two decades

引用

NEUROCOMPUTING 2021年 453卷 223-240页

作者： Liu, Li Wang, Zhiyu Qiu, Taorong Chen, Qiu Lu, Yue Suen, Ching Y. Nanchang Univ Sch Informat Engn Nanchang 330031 Jiangxi Peoples R China Hunan Univ Sch Comp Sci & Elect Engn Changsha 410082 Hunan Peoples R China Kogakuin Univ Grad Sch Engn Elect Engn & Elect Tokyo 1638677 Japan East China Normal Univ Sch Commun & Elect Engn Shanghai 200241 Peoples R China Concordia Univ Ctr Pattern Recognit & Machine Intelligence Montreal PQ H3G 1M8 Canada

document image classification plays a vital role in the document image processing system. Thus it is of great importance to have a clear understanding of the state-of-the-art of the document image classification field, especially in this deep learning era, which will facilitate the development of effective document image processing systems. In this paper, we provide a comprehensive survey of the progress that has been made in the field of document image classification over the past two decades. We categorize the document images into non-mobile images and mobile images according to the way they are acquired. The existing document image classification methods for these two types of images are reviewed, which are classified as textual-based methods, structural-based methods, visual-based methods and hybrid methods. We further compare the performance of different classification methods on several public benchmark datasets. Finally, we highlight some open issues and recommend promising directions for future research. (c) 2021 Elsevier B.V. All rights reserved.

关键词： document image classification Non-mobile document images Mobile document images Survey

来源：评论

学校读者我要写书评

暂无评论

document image classification: Towards Assisting Visually Impaired

Document Image Classification: Towards Assisting Visually Im...

引用

IEEE Region 10 Conference on Technology, Knowledge, and Society (TENCON)

作者： Shahira, K. C. Lijiya, A. NIT Calicut Comp Sci & Engn Dept Calicut Kerala India

ISBN: (纸本)9781728118956

Our work aims to enable the visual information in a document to be accessible by the visually impaired or the blind people. The blind people prefer arts over science subjects in higher education because conveying equations and algorithms to them is seen as difficult. They should not be deprived of acquiring knowledge due to physical disabilities. In this work, we identify different types of images in an algorithm textbook as graphs, algorithm images, equations, and network flow diagrams with 98% accuracy. The Convolution Neural Networks used can predict new data instances with 99% accuracy except for recurrence tree images. We want to extend our work to extract the textual information in these images and produce image descriptions as alt text. This can produce a better speech output to assist the blind people.

关键词： Assistive Technology Visually Impaired Deep Learning document image classification Graphs image Processing CNN Education of Visually Impaired

来源：评论

学校读者我要写书评

暂无评论

document image classification Using SqueezeNet Convolutional Neural Network 5

Document Image Classification Using SqueezeNet Convolutional...

引用

5th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS)

作者： Hassanpour, Mohammad Malek, Hamed Shahid Beheshti Univ Fac Comp Sci & Engn Tehran Iran

ISBN: (纸本)9781728153506

SqueezeNet networks perform well on image classification tasks, achieving accuracies comparable to state of the art convolutional neural networks. In this research we evaluate the performance of SqueezeNet networks in document image classification, showing that an imageNet pretrained SqueezeNet achieves an accuracy of approximately 75 percent over 10 classes on the Tobacco-3482 dataset, which is comparable to other state of the art convolutional neural networks in terms of accuracy, while containing 50 times less weights compared to them. We then visualize saliency maps of the gradient of our networks output to input, which shows that the network is able to learn meaningful features that are useful for document classification. Features such as the existence of handwritten text, document titles, text alignment and tabular structures, which are proof that the network does not overfit to redundant representations of the dataset itself.

关键词： Squeezenet Convolutional neural network document image classification

来源：评论

学校读者我要写书评

暂无评论

A survey of document image classification: problem statement, classifier architecture and performance evaluation

引用

INTERNATIONAL JOURNAL ON document ANALYSIS AND RECOGNITION 2007年第1期10卷 1-16页

作者： Chen, Nawei Blostein, Dorothea Queens Univ Sch Comp Kingston ON K7L 3N6 Canada

document image classification is an important step in Office Automation, Digital Libraries, and other document image analysis applications. There is great diversity in document image classifiers: they differ in the problems they solve, in the use of training data to construct class models, and in the choice of document features and classification algorithms. We survey this diverse literature using three components: the problem statement, the classifier architecture, and performance evaluation. This brings to light important issues in designing a document classifier, including the definition of document classes, the choice of document features and feature representation, and the choice of classification algorithm and learning mechanism. We emphasize techniques that classify single-page typeset document images without using OCR results. Developing a general, adaptable, high-performance classifier is challenging due to the great variety of documents, the diverse criteria used to define document classes, and the ambiguity that arises due to ill-defined or fuzzy document classes.

关键词： document image classification document classifiers document classification document categorization document features feature representations class models classification algorithms learning mechanisms performance evaluation

来源：评论

学校读者我要写书评

暂无评论

The Reality of High Performing Deep Learning Models: A Case Study on document image classification

引用

IEEE ACCESS 2024年 12卷 103537-103564页

作者： Saifullah Agne, Stefan Dengel, Andreas Ahmed, Sheraz DFKI GmbH Smart Data & Knowledge Serv SDS D-67663 Kaiserslautern Germany Univ Kaiserslautern Landau Dept Comp Sci D-67663 Kaiserslautern Germany DeepReader GmbH D-67663 Kaiserslautern Germany

Deep neural networks have demonstrated exceptional performance breakthroughs in the field of document image classification;yet, there has been limited research in the field that delves into the explainability of these models. In this paper, we present a comprehensive study in which we analyze 9 different explainability methods across 10 different state-of-the-art document classification models and 2 popular benchmark datasets, RVL-CDIP and Tobacco3482, making three major contributions. First, through an exhaustive qualitative and quantitative analysis of various explainability approaches, we demonstrate that the majority of them perform poorly in generating useful explanations for document images. Only two techniques, Occlusion and DeepSHAP, provide relatively faithful explanations, with DeepSHAP additionally offering better interpretability while Occlusion falls short in this regard. Second, to pinpoint the features most crucial to the models' predictions, we present an approach for generating counterfactual explanations, the analysis of which reveals that many document classification models can be highly susceptible to minor perturbations in the input. Additionally, it suggests that these models may easily fall victim to biases in the document data, ultimately relying on seemingly irrelevant features to make their decisions. Specifically, on the RVL-CDIP dataset, we show that 25-50% of the overall model predictions and up to 60% of predictions for some classes were strongly dependent on these irrelevant features. Lastly, our analysis reveals that the popular document benchmark datasets, RVL-CDIP and Tobacco3482, are inherently biased, with document identification (ID) numbers of specific styles consistently appearing in certain document regions. If unaddressed, this bias allows the models to predict document classes solely by looking at the ID numbers and prevents them from learning more complex document features. Overall, by unveiling the strengths and weaknesses

关键词： Explainable document image classification document image classification explainability interpretable machine learning black box models Explainable document image classification document image classification explainability interpretable machine learning black box models

来源：评论

学校读者我要写书评

暂无评论

Towards privacy preserved document image classification: a comprehensive benchmark

引用

INTERNATIONAL JOURNAL ON document ANALYSIS AND RECOGNITION 2024年第3期27卷 475-499页

作者： Saifullah, Saifullah Mercier, Dominique Agne, Stefan Dengel, Andreas Ahmed, Sheraz German Res Ctr Artificial Intelligence D-67663 Kaiserslautern Germany RPTU Kaiserslautern Landau D-67663 Kaiserslautern Germany DeepReader GmbH D-67663 Kaiserslautern Germany

As data-driven AI systems become increasingly integrated into industry, concerns have recently arisen regarding potential privacy breaches and the inadvertent leakage of sensitive user data through the exploitation of these systems. In this paper, we explore the intersection of data privacy and AI-powered document analysis systems, presenting a comprehensive benchmark of well-known privacy-preserving methods for the task of document image classification. In particular, we investigate four different privacy methods-Differential Privacy (DP), Federated Learning (FL), Differentially Private Federated Learning (DP-FL), and Secure Multi-Party Computation (SMPC)-on two well-known document benchmark datasets, namely RVL-CDIP and Tobacco3482. Furthermore, we investigate the performance of each method under a variety of configurations for thorough benchmarking. Finally, the privacy strength of each approach is assessed by subjecting the private models to well-known membership inference attacks. Our results demonstrate that, with sufficient tuning of hyperparameters, Differential Privacy (DP) can achieve reasonable performance on the task of document image classification while also ensuring rigorous privacy constraints, both in standalone and federated learning setups. On the other hand, while FL-based approaches present less implementation complexity and incur little to no loss in performance on the task, they do not offer sufficient protection against privacy attacks. By rigorously benchmarking various privacy approaches, our study paves the way for integrating deep document classification models into industrial pipelines while meeting regulatory and ethical standards, including GDPR and the AI Act 2022.

关键词： document image classification Privacy-preserving deep learning Differential privacy Federated learning Secure multi-party computation

来源：评论

学校读者我要写书评

暂无评论

DocXclassifier: towards a robust and interpretable deep neural network for document image classification

引用

INTERNATIONAL JOURNAL ON document ANALYSIS AND RECOGNITION 2024年第3期27卷 447-473页

作者： Saifullah, Saifullah Agne, Stefan Dengel, Andreas Ahmed, Sheraz German Res Ctr Artificial Intelligence D-67663 Kaiserslautern Germany RPTU Kaiserslautern Landau D-67663 Kaiserslautern Germany DeepReader GmbH D-67663 Kaiserslautern Germany

Model interpretability and robustness are becoming increasingly critical today for the safe and practical deployment of deep learning (DL) models in industrial settings. As DL-backed automated document processing systems become increasingly common in business workflows, there is a pressing need today to enhance interpretability and robustness for the task of document image classification, an integral component of such systems. Surprisingly, while much research has been devoted to improving the performance of deep models for this task, little attention has been given to their interpretability and robustness. In this paper, we aim to improve upon both aspects and introduce two inherently interpretable deep document classifiers, DocXClassifier and DocXClassifierFPN, both of which not only achieve significant performance improvements over existing approaches but also hold the capability to simultaneously generate feature importance maps while making their predictions. Our approach involves integrating a convolutional neural network (ConvNet) backbone with an attention mechanism to perform weighted aggregation of features based on their importance to the class, enabling the generation of interpretable importance maps. Additionally, we propose integrating Feature Pyramid Networks with the attention mechanism to significantly enhance the resolution of the interpretability maps, especially for pyramidal ConvNet architectures. Our approach attains state-of-the-art performance in image-based classification on two popular document datasets, RVL-CDIP and Tobacco3482, with top-1 classification accuracies of 94.19% and 95.71%, respectively. Additionally, it sets a new record for the highest image-based classification accuracy on Tobacco3482 without transfer learning from RVL-CDIP, at 90.29%. In addition, our proposed training strategy demonstrates superior robustness compared to existing approaches, significantly outperforming them on 19 out of 21 different types of novel data di

关键词： document image classification Explainable document classification Model interpretability Inherent interpretability Model robustness Corruption robustness

来源：评论

学校读者我要写书评

暂无评论

A document image classification system fusing deep and machine learning models

引用

APPLIED INTELLIGENCE 2023年第12期53卷 15295-15310页

作者： Omurca, Sevinc Ilhan Ekinci, Ekin Sevim, Semih Edinc, Eren Berk Eken, Suleyman Sayar, Ahmet Kocaeli Univ Dept Comp Engn Kocaeli Turkey Sakarya Univ Appl Sci Dept Comp Engn Sakarya Turkey Bandirma Onyedi Eylul Univ Dept Comp Engn Balikesir Turkey Kocaeli Univ Dept Informat Syst Engn Kocaeli Turkey

Artificial Intelligence (AI) technologies are now widely employed to overcome human-induced faults in a variety of systems used in our daily lives, thanks to the digital *** example of such systems is online document tracking systems (DTS). The DTS's reliability and preferability are enhanced by automatic document classification and understanding features. Although automatic document classification systems can assist humans in document understanding tasks, most of of them are not designed to function with Portable document Format (PDF), which contains text, tables or figures. In this study, we investigate separate ways to efficiently classify student documents that are uploaded in PDF format and are required for university education. We propose three possible techniques for this issue. The first approach is based on Optical Character Recognition (OCR) and traditional machine learning methods. The second is purely on deep learning. The third one is based on fusion of deep learning methods based on entropy. The proposed techniques can classify twelve distinct types of digital documents. The validity of the proposed methods has been verified by student affairs department of Kocaeli University in Turkey. The system has not only increased the efficiency of online document uploading steps for students, but also reduced the human cost for tracking the documents. The highest F-score (94.45%) is obtained by the ensemble of EfficientNetB3 and ExtraTree.

关键词： document image classification document understanding Deep learning Machine learning Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Analyzing the potential of active learning for document image classification

引用

INTERNATIONAL JOURNAL ON document ANALYSIS AND RECOGNITION 2023年第3期26卷 187-209页

Deep learning has been extensively researched in the field of document analysis and has shown excellent performance across a wide range of document-related tasks. As a result, a great deal of emphasis is now being placed on its practical deployment and integration into modern industrial document processing pipelines. It is well known, however, that deep learning models are data-hungry and often require huge volumes of annotated data in order to achieve competitive performances. And since data annotation is a costly and labor-intensive process, it remains one of the major hurdles to their practical deployment. This study investigates the possibility of using active learning to reduce the costs of data annotation in the context of document image classification, which is one of the core components of modern document processing pipelines. The results of this study demonstrate that by utilizing active learning (AL), deep document classification models can achieve competitive performances to the models trained on fully annotated datasets and, in some cases, even surpass them by annotating only 15-40% of the total training dataset. Furthermore, this study demonstrates that modern AL strategies significantly outperform random querying, and in many cases achieve comparable performance to the models trained on fully annotated datasets even in the presence of practical deployment issues such as data imbalance, and annotation noise, and thus, offer tremendous benefits in real-world deployment of deep document classification models. The code to reproduce our experiments is publicly available at .

关键词： document image classification document analysis Active learning Deep active learning

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：