检索结果-内蒙古大学图书馆

Dual-branch dilated context convolutional for table detection transformer in the document images

VISUAL COMPUTER 2025年第4期41卷 2709-2720页

作者： Ni, Ying Wang, Xiaoli Peng, Hanghang Li, Yonzhi Wang, Jinyang Li, Haoxuan Huang, Jin Guotai Asset Management Co Ltd Shanghai Peoples R China Shanghai Jiao Tong Univ Shanghai Peoples R China State Key Lab New Text Mat & Adv Proc Technol Wuhan Peoples R China

With the increasing automation of document images like financial reports, table detection has become a critical component of document automation. It requires models to extract the position information of tables in document images without losing information. However, existing techniques still fall short in detecting certain small-sized or irregularly shaped tables. To address this issue, we propose a Transformer-based table detection model. To enhance both training efficiency and prediction performance, we employ a pretrained Transformer framework for fine-tuning to effectively capture underlying features. Additionally, we integrate a dual-branch dilated context convolutional module to further improve the detection accuracy and robustness for tables of various sizes and shapes by processing high-dimensional features. Furthermore, we integrated multiple layers of residual convolutional layers to capture and fuse features at different scales, enhancing the network's ability to represent features in multi-scale feature fusion, thus enhancing the detection performance of the network. We used feature maps and heatmaps for visualization to verify the reliability of our method. We evaluate our method on publicly available document datasets, and the results demonstrate that our approach achieves more advanced performance in evaluation metrics such as Precision. https://***/GT-HZ/TD

关键词： table detection Transformer Dilated convolution Visualization

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for table detection and Structure Recognition: A Survey

引用

ACM COMPUTING SURVEYS 2024年第12期56卷 1-41页

作者： Kasem, Mahmoud salaheldin Abdallah, Abdelrahman Berendeyev, Alexander Elkady, Ebrahem Mahmoud, Mohamed Abdalla, Mahmoud Hamada, Mohamed Vascon, Sebastiano Nurseitov, Daniyar Taj-eddin, Islam Assiut Univ Fac Comp & Informat Assiut Egypt Chungbuk Natl Univ Cheongju South Korea CaFoscari Univ Venice Veneto Italy Satbayev Univ Alma Ata Kazakhstan Informat Technol Inst Alexandria Egypt Int IT Univ Dept Informat Syst Alma Ata Kazakhstan JSC NC KazMunayGas Astana Kazakhstan Assiut Univ Fac Comp & Informat Assiut Egypt

tables are everywhere, from scientific journals, articles, websites, and newspapers all the way to items we buy at the supermarket. Detecting them is thus of utmost importance to automatically understanding the content of a document. The performance of table detection has substantially increased thanks to the rapid development of deep learning networks. The goals of this survey are to provide a profound comprehension of the major developments in the field of table detection, offer insight into the different methodologies, and provide a systematic taxonomy of the different approaches. Furthermore, we provide an analysis of both classic and new applications in the field. Lastly, the datasets and source code of the existing models are organized to provide the reader with a compass on this vast literature. Finally, we go over the architecture of utilizing various object detection and table structure recognition methods to create an effective and efficient

关键词： Convolutional neural networks deep learning table detection table structure recognition

来源：评论

学校读者我要写书评

暂无评论

End-to-end semi-supervised approach with modulated object queries for table detection in documents

引用

INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION 2024年第3期27卷 363-378页

作者： Ehsan, Iqraa Shehzadi, Tahira Stricker, Didier Afzal, Muhammad Zeshan Tech Univ Kaiserslautern Dept Comp Sci D-67663 Kaiserslautern Germany Tech Univ Kaiserslautern Mindgarage D-67663 Kaiserslautern Germany German Res Inst Artificial Intelligence DFKI Comp Vis D-67663 Kaiserslautern Germany

table detection, a pivotal task in document analysis, aims to precisely recognize and locate tables within document images. Although deep learning has shown remarkable progress in this realm, it typically requires an extensive dataset of labeled data for proficient training. Current CNN-based semi-supervised table detection approaches use the anchor generation process and non-maximum suppression in their detection process, limiting training efficiency. Meanwhile, transformer-based semi-supervised techniques adopted a one-to-one match strategy that provides noisy pseudo-labels, limiting overall efficiency. This study presents an innovative transformer-based semi-supervised table detector. It improves the quality of pseudo-labels through a novel matching strategy combining one-to-one and one-to-many assignment techniques. This approach significantly enhances training efficiency during the early stages, ensuring superior pseudo-labels for further training. Our semi-supervised approach is comprehensively evaluated on benchmark datasets, including PubLayNet, ICADR-19, and tableBank. It achieves new state-of-the-art results, with a mAP of 95.7% and 97.9% on tableBank (word) and PubLaynet with 30% label data, marking a 7.4 and 7.6 point improvement over previous semi-supervised table detection approach, respectively. The results clearly show the superiority of our semi-supervised approach, surpassing all existing state-of-the-art methods by substantial margins. This research represents a significant advancement in semi-supervised table detection methods, offering a more efficient and accurate solution for practical document analysis tasks.

关键词： table detection Document analysis Semi-supervised learning detection transformer

来源：评论

学校读者我要写书评

暂无评论

Pre-training transformer with dual-branch context content module for table detection in document images

引用

虚拟现实与智能硬件（中英文） 2024年第5期6卷 408-420页

作者： Yongzhi LI Pengle ZHANG Meng SUN Jin HUANG Ruhan HE School of Computer Science and Artificial Intelligence Wuhan Textile UniversityWuhan 430064China School of Computer Science South-Central Minzu UniversityWuhan 430064China Hubei Provincial Engineering Research Center for Intelligent Textile and Fashion Wuhan Textile UniversityWuhan 430064China

Background Document images such as statistical reports and scientific journals are widely used in information *** detection of table areas in document images is an essential prerequisite for tasks such as information ***,because of the diversity in the shapes and sizes of tables,existing table detection methods adapted from general object detection algorithms,have not yet achieved satisfactory *** detection results might lead to the loss of critical *** Therefore,we propose a novel end-to-end trainable deep network combined with a self-supervised pretraining transformer for feature extraction to minimize incorrect *** better deal with table areas of different shapes and sizes,we added a dualbranch context content attention module(DCCAM)to high-dimensional features to extract context content information,thereby enhancing the network's ability to learn shape *** feature fusion at different scales,we replaced the original 3×3 convolution with a multilayer residual module,which contains enhanced gradient flow information to improve the feature representation and extraction *** We evaluated our method on public document datasets and compared it with previous methods,which achieved state-of-the-art results in terms of evaluation metrics such as recall and ***://***/Yong Z-Lee/TD-DCCAM.

关键词： table detection Document image analysis Transformer Dilated convolution Deformable convolution Feature fusion

来源：评论

学校读者我要写书评

暂无评论

table detection Method Based on Faster-RCNN and Window Attention 12

Table Detection Method Based on Faster-RCNN and Window Atten...

引用

12th International Conference on Networks, Communication and Computing (ICNCC)

作者： Chen, Han Song, Shengli Su, Rijian Zhengzhou Univ Light Ind Sch Software Zhengzhou Henan Peoples R China Zhengzhou Univ Light Ind Sch Comp Sci & Technol Zhengzhou Henan Peoples R China

ISBN: (纸本)9798400709265

As an important carrier of information, tables possess the characteristics of high data storage density, conciseness, and intuitiveness, and are widely applied in offices and daily life. Due to the complexity of table structures and diverse presentation formats, the automated processing of a large number of image-based tables has always been a challenge in the field of document recognition. This algorithm addresses the task of table detection in table processing and proposes a table detection algorithm based on an improved window self-attention network for feature extraction of image-based tables. It utilizes a two-stage object detection algorithm, introduces local feature extraction blocks and backward feed-forward residual network blocks, and designs a feature pyramid network within the backbone to enhance the model's detection performance by improving its ability to learn document spatial layout features. The effectiveness of the proposed method is verified through experimental comparisons on publicly available datasets.

关键词： Self-attention table detection Inverted residual feed-forward network

来源：评论

学校读者我要写书评

暂无评论

Improving table detection for document images using boundary

引用

COMPLEX & INTELLIGENT SYSTEMS 2024年第2期10卷 1703-1714页

作者： Liu, Yingli Zheng, Jianfeng Zhang, Guangtao Shen, Tao Kunming Univ Sci & Technol Fac Informat Engn & Automat Wujiaying St Kunming 650500 Yunnan Peoples R China Kunming Univ Sci & Technol Yunnan Key Lab Comp Technol Applicat Wujiaying St Kunming 650500 Yunnan Peoples R China

Locating tables in document images is the first step to extracting table information, and high location precision is required. The dominant approach of table detection is based on an object detection algorithm, and the detector defines the prediction task as a regression problem, which inevitably leads to positioning errors. To address this issue, this paper presents an approach called Border Line Correction (BLC) to refine the rough prediction results of the original detector through the table boundary lines extracted from the document image. Our approach transforms the regression task into a classification problem, thus avoiding the inherent regression error of the object detection algorithm. Traditional annotation methods are inadequate for table detection tasks as they fail to capture the completeness and purity of the detection results. Therefore, this study treats the correct position of a table as a tolerance region. Additionally, to overcome the limitations of existing datasets in the materials domain, we collected 1183 samples from scientific literature in the materials field and created the MatTab dataset, annotating the tables with tolerance regions. This paper use Cascade RCNN with Swin Transformer as baseline models, and BLC is utilized to optimize the detection results. Experimental results demonstrate significant improvements with BLC at an IOU of 0.95 on the MatTab, ICDAR2019, and ICDAR2017 datasets. In MatTab, the percentage of correctly detected complete and pure tables increased from 72.3% to 82.1%.

关键词： table detection Deep learning Document image Object detection

来源：评论

学校读者我要写书评

暂无评论

YOLO-table: disclosure document table detection with involution

引用

INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION 2023年第1期26卷 1-14页

作者： Zhang, Daqian Mao, Ruibin Guo, Runting Jiang, Yang Zhu, Jing Shenzhen Secur Informat Co Ltd Shenzhen Peoples R China

As financial document automation becomes more general, table detection is receiving more and more attention as an important part of document automation. Disclosure documents contain both bordered and borderless tables of varying lengths, and there is currently no model that performs well on these types of documents. To solve this problem, we propose a table detection model based on YOLO-table. We introduce involution into the backbone of the network to improve the network's ability to learn table spatial layout features and design a simple Feature Pyramid Network to improve model effectiveness. In addition, this paper proposes a table-based augment method. We experiment on a disclosure document dataset, and the results show that the F1-measure of the YOLO-table reaches 97.3%. Compared with YOLOv3, our method improves the accuracy by 2.8% and the speed by 1.25 times. It also evaluates the ICDAR2013 and ICDAR2019 table Competition datasets and achieves state-of-the-art performance.

关键词： table detection Involution FPNs Deep learning

来源：评论

学校读者我要写书评

暂无评论

Towards End-to-End Semi-supervised table detection with Semantic Aligned Matching Transformer 18th

Towards End-to-End Semi-supervised Table Detection with Sema...

引用

18th International Conference on Document Analysis and Recognition (ICDAR)

作者： Shehzadi, Tahira Sarode, Shalini Stricker, Didier Afzal, Muhammad Zeshan Tech Univ Kaiserslautern Dept Comp Sci D-67663 Kaiserslautern Germany Tech Univ Kaiserslautern Mindgarage D-67663 Kaiserslautern Germany German Res Inst Artificial Intelligence DFKI D-67663 Kaiserslautern Germany

ISBN: (纸本)9783031705489;9783031705496

table detection within document images is a crucial task in document processing, involving the identification and localization of tables. Recent strides in deep learning have substantially improved the accuracy of this task, but it still heavily relies on large labeled datasets for effective training. Several semi-supervised approaches have emerged to overcome this challenge, often employing CNN-based detectors with anchor proposals and post-processing techniques like non-maximal suppression (NMS). However, recent advancements in the field have shifted the focus towards transformer-based techniques, eliminating the need for NMS and emphasizing object queries and attention mechanisms. Previous research has focused on two key areas to improve transformer-based detectors: refining the quality of object queries and optimizing attention mechanisms. However, increasing object queries can introduce redundancy, while adjustments to the attention mechanism can increase complexity. To address these challenges, we introduce a semi-supervised approach employing SAM-DETR, a novel approach for precise alignment between object queries and target features. Our approach demonstrates remarkable reductions in false positives and substantial enhancements in table detection performance, particularly in complex documents characterized by diverse table structures. This work provides more efficient and accurate table detection in semi-supervised settings.

关键词： Semi-Supervised Learning detection Transformer SAM-DETR table Analysis table detection

来源：评论

学校读者我要写书评

暂无评论

ClusterTabNet: Supervised Clustering Method for table detection and table Structure Recognition 18th

ClusterTabNet: Supervised Clustering Method for Table Detect...

引用

18th International Conference on Document Analysis and Recognition (ICDAR)

作者： Polewczyk, Marek Spinaci, Marco SAP Business AI Alpharetta GA 30022 USA

ISBN: (纸本)9783031705489;9783031705496

table detection and recognition consists of locating tables within a given document and identifying the exact location of its pieces, such as rows, columns, and headers. We present a novel deep-learning-based method to cluster words in documents which we apply to detect and recognize tables given the OCR output. We interpret table structure bottom-up as a graph of relations between pairs of words (belonging to the same row, column, header, as well as to the same table) and use a transformer encoder model to predict its adjacency matrix. We demonstrate the performance of our method on the Pubtables-1M dataset introduced in [17] as well as PubTabNet and FinTabNet datasets. Compared to the current state-of-the-art detection methods such as DETR [1] and Faster R-CNN [15], our method achieves similar or better accuracy, while requiring a significantly smaller model. The code is released at https://***/SAP- samples/clustertabnet.

关键词： table detection table recognition Supervised clustering Transformers

来源：评论

学校读者我要写书评

暂无评论

tableSegNet: a fully convolutional network for table detection and segmentation in document images

引用

INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION 2022年第1期25卷 1-14页

作者： Nguyen, Duc-Dung VAST Inst Informat Technol Dept Pattern Recognit & Knowledge Engn 18 Hoang Quoc Viet Hanoi 10000 Vietnam

Advances in image object detection lead to applying deep convolution neural networks in the document image analysis domain. Unlike general colorful and pattern-rich objects, tables in document images have properties that limit the capacity of deep learning structures. Significant variation in size and aspect ratio and the local similarity among document components are the main challenges that require both global features for detection and local features for the separation of nearby objects. To deal with these challenges, we present tableSegNet, a compact architecture of a fully convolutional network to detect and separate tables simultaneously. tableSegNet consists of a deep convolution path to detect table regions in low resolution and a shallower path to locate table locations in high resolution and split the detected regions into individual tables. To improve the detection and separation capacity, tableSegNet uses convolution blocks of wide kernel sizes in the feature extraction process and an additional table-border class in the main output. With only 8.1 million parameters and trained purely on document images from the beginning, tableSegNet has achieved state-of-the-art F1 score at the IoU threshold of 0.9 on the ICDAR2019 and the highest number of correctly detected tables on the ICDAR2013 table detection datasets.

关键词： Document analysis and recognition Page segmentation table detection Semantic segmentation Convolution neural network

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：