International Journal on Document Analysis and Recognition最新文献

AIKON: a modular computer vision platform for historical corpora. AIKON：历史语料库的模块化计算机视觉平台。

IF 1.7 4区计算机科学

International Journal on Document Analysis and Recognition Pub Date : 2026-01-01 Epub Date: 2026-06-30 DOI: 10.1007/s10032-026-00581-x

Ségolène Albouy, Somkeo Norindr, Paul Kervegan, Fouad Aouinti, Rémy Delanaux, Clara Grometto, Robin Champenois, Stavros Lazaris, Alexandre Guilbaud, Matthieu Husson, Mathieu Aubry

{"title":"AIKON: a modular computer vision platform for historical corpora.","authors":"Ségolène Albouy, Somkeo Norindr, Paul Kervegan, Fouad Aouinti, Rémy Delanaux, Clara Grometto, Robin Champenois, Stavros Lazaris, Alexandre Guilbaud, Matthieu Husson, Mathieu Aubry","doi":"10.1007/s10032-026-00581-x","DOIUrl":"https://doi.org/10.1007/s10032-026-00581-x","url":null,"abstract":"Historical document analysis has progressed to a point where the main bottleneck for many historical applications is not algorithms, but relevant interfaces, that can support historians' workflow. While specialized tools exist for text processing and image search, we argue the community lacks a versatile collaborative platform enabling historians to analyze their own corpora from a particular perspective. As a step in this direction, we present aikon , a modular web-platform designed to empower historians with computer vision tools. aikon implements a complete workflow for historical document analysis, from corpus constitution to ai outputs validation and interpretation. It provides a comprehensive research environment combining source management tools with automated processing capabilities as well as multi-user validation and visualization interfaces. We showcase the potential of aikon by presenting modules enabling the investigation of graphical content transmission across large and diverse corpora, a problem for which few modern tools exist, and which is of key interest, for example in History of Science.","PeriodicalId":50277,"journal":{"name":"International Journal on Document Analysis and Recognition","volume":"29 3","pages":"801-814"},"PeriodicalIF":1.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658341/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149185626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Data rescue of historical tables through semi-supervised table structure recognition. 基于半监督表结构识别的历史表数据抢救。

IF 1.7 4区计算机科学

International Journal on Document Analysis and Recognition Pub Date : 2026-01-01 Epub Date: 2025-12-01 DOI: 10.1007/s10032-025-00562-6

Loitongbam Gyanendro Singh, Stuart E Middleton

{"title":"Data rescue of historical tables through semi-supervised table structure recognition.","authors":"Loitongbam Gyanendro Singh, Stuart E Middleton","doi":"10.1007/s10032-025-00562-6","DOIUrl":"10.1007/s10032-025-00562-6","url":null,"abstract":"This study uses a novel semi-supervised learning framework to explore Tabular Structure Recognition (TSR) for digitizing historical documents, specifically employing the CascadeTabNet model. TSR is crucial for transforming archival tabular data into digital formats, enhancing accessibility and analysis across various research fields. Challenges like physical degradation, inconsistent lighting, and non-standard handwriting hinder the generation of high-quality annotations of historical documents needed for effective model training. To address these issues, this research explores two research questions: (i) Can a semi-supervised training approach reduce the need for expensive data annotations? and (ii) Does semi-supervised training improve model robustness? We applied our methodology across three datasets: the GloSAT and ICDAR-2019 datasets based on historical documents, and the predominantly modern documents PubTabNet dataset. Our results indicate that semi-supervised learning substantially increases TSR accuracy and decreases dependency on extensive labelled datasets, providing a robust solution for large-scale digitization initiatives and contributing to the preservation and improved accessibility of historical data. All code from this paper is freely available on GitHub (https://github.com/stuartemiddleton/glosat_table_dataset).","PeriodicalId":50277,"journal":{"name":"International Journal on Document Analysis and Recognition","volume":"29 2","pages":"429-445"},"PeriodicalIF":1.7,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13283156/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148303899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Tabular context-aware optical character recognition and tabular data reconstruction for historical records. 表格上下文感知光学字符识别和历史记录的表格数据重建。

IF 2.5 4区计算机科学

International Journal on Document Analysis and Recognition Pub Date : 2025-01-01 Epub Date: 2025-07-01 DOI: 10.1007/s10032-025-00543-9

Loitongbam Gyanendro Singh, Stuart E Middleton

{"title":"Tabular context-aware optical character recognition and tabular data reconstruction for historical records.","authors":"Loitongbam Gyanendro Singh, Stuart E Middleton","doi":"10.1007/s10032-025-00543-9","DOIUrl":"10.1007/s10032-025-00543-9","url":null,"abstract":"Digitizing historical tabular records is essential for preserving and analyzing valuable data across various fields, but it presents challenges due to complex layouts, mixed text types, and degraded document quality. This paper introduces a comprehensive framework to address these issues through three key contributions. First, it presents UoS_Data_Rescue, a novel dataset of 1,113 historical logbooks with over 594,000 annotated text cells, designed to handle the complexities of handwritten entries, aging artifacts, and intricate layouts. Second, it proposes a novel context-aware text extraction approach (TrOCR-ctx) to reduce cascading errors during table digitization. Third, it proposes an enhanced end-to-end OCR pipeline that integrates TrOCR-ctx with ByT5, combining OCR and post-OCR correction in a unified training framework. This framework enables the system to produce both the raw OCR output and a corrected version in a single pass, improving recognition accuracy, particularly for multilingual and degraded text, within complex table digitization tasks. The model achieves superior performance with a 0.049 word error rate and a 0.035 character error rate, outperforming existing methods by up to 41% in OCR tasks and 10.74% in table reconstruction tasks. This framework offers a robust solution for large-scale digitization of tabular documents, extending its applications beyond climate records to other domains requiring structured document preservation. The dataset and implementation are available as open-source resources.","PeriodicalId":50277,"journal":{"name":"International Journal on Document Analysis and Recognition","volume":"28 3","pages":"357-376"},"PeriodicalIF":2.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12450121/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145126180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Redacted text detection using neural image segmentation methods. 编辑文本检测使用神经图像分割方法。

IF 2.5 4区计算机科学

International Journal on Document Analysis and Recognition Pub Date : 2025-01-01 Epub Date: 2025-01-30 DOI: 10.1007/s10032-025-00513-1

Ruben van Heusden, Kaj Meijer, Maarten Marx

{"title":"Redacted text detection using neural image segmentation methods.","authors":"Ruben van Heusden, Kaj Meijer, Maarten Marx","doi":"10.1007/s10032-025-00513-1","DOIUrl":"https://doi.org/10.1007/s10032-025-00513-1","url":null,"abstract":"The redaction of sensitive information in documents is common practice in specific types of organizations. This happens for example in court proceedings or in documents released under the Freedom of Information Act (FOIA). The ability to automatically detect when information has been redacted has several practical applications, such as the gathering of statistics on the amount of redaction present in documents, enabling a critical view on redaction practices. It can also be used to further investigate redactions, and whether or not the used techniques provide sufficient anonymization. The task is particularly challenging because of the large variety of redaction methods and techniques, from software for automatic redaction to manual redactions by pen. Any detection system must be robust to a large variety of inputs, as it will be run on many documents that might not even contain redactions. In this study, we evaluate two neural methods for the task, namely a Mask R-CNN model and a Mask2Former model, and compare them to a rule-based model based on optical character recognition and morphological operations. The best performing, the Mask R-CNN model, has a recall of .94 with a precision of .96 over a challenging data set containing several redaction types. Adding many pages without redaction barely lowers this score (precision drops to .90, recall drops to .92). The Mask2Former model is most robust to inputs without redactions, producing the least false positives of all models.","PeriodicalId":50277,"journal":{"name":"International Journal on Document Analysis and Recognition","volume":"28 4","pages":"597-607"},"PeriodicalIF":2.5,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12662892/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145649770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A survey on artificial intelligence-based approaches for personality analysis from handwritten documents 基于人工智能的手写文件个性分析方法调查

IF 2.3 4区计算机科学

International Journal on Document Analysis and Recognition Pub Date : 2024-08-27 DOI: 10.1007/s10032-024-00496-5

Suparna Saha Biswas, Himadri Mukherjee, Ankita Dhar, Obaidullah Sk Md, Kaushik Roy

引用次数: 0

In-domain versus out-of-domain transfer learning for document layout analysis 文件布局分析中的域内与域外迁移学习

IF 2.3 4区计算机科学

International Journal on Document Analysis and Recognition Pub Date : 2024-08-19 DOI: 10.1007/s10032-024-00497-4

Axel De Nardin, Silvia Zottin, Claudio Piciarelli, Gian Luca Foresti, Emanuela Colombi

{"title":"In-domain versus out-of-domain transfer learning for document layout analysis","authors":"Axel De Nardin, Silvia Zottin, Claudio Piciarelli, Gian Luca Foresti, Emanuela Colombi","doi":"10.1007/s10032-024-00497-4","DOIUrl":"https://doi.org/10.1007/s10032-024-00497-4","url":null,"abstract":"Data availability is a big concern in the field of document analysis, especially when working on tasks that require a high degree of precision when it comes to the definition of the ground truths on which to train deep learning models. A notable example is represented by the task of document layout analysis in handwritten documents, which requires pixel-precise segmentation maps to highlight the different layout components of each document page. These segmentation maps are typically very time-consuming and require a high degree of domain knowledge to be defined, as they are intrinsically characterized by the content of the text. For this reason in the present work, we explore the effects of different initialization strategies for deep learning models employed for this type of task by relying on both in-domain and cross-domain datasets for their pre-training. To test the employed models we use two publicly available datasets with heterogeneous characteristics both regarding their structure as well as the languages of the contained documents. We show how a combination of cross-domain and in-domain transfer learning approaches leads to the best overall performance of the models, as well as speeding up their convergence process.\u0000","PeriodicalId":50277,"journal":{"name":"International Journal on Document Analysis and Recognition","volume":"64 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142213548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep learning-based modified-EAST scene text detector: insights from a novel multiscript dataset 基于深度学习的修改后 EAST 场景文本检测器：从新型多脚本数据集中获得的启示

IF 2.3 4区计算机科学

International Journal on Document Analysis and Recognition Pub Date : 2024-07-31 DOI: 10.1007/s10032-024-00491-w

Shilpa Mahajan, Rajneesh Rani, Aman Kamboj

{"title":"Deep learning-based modified-EAST scene text detector: insights from a novel multiscript dataset","authors":"Shilpa Mahajan, Rajneesh Rani, Aman Kamboj","doi":"10.1007/s10032-024-00491-w","DOIUrl":"https://doi.org/10.1007/s10032-024-00491-w","url":null,"abstract":"The field of computer vision has seen significant transformation with the emergence and advancement of deep learning models. Deep learning waves have a significant impact on scene text detection, a vital and active area in computer vision. Numerous scientific, industrial, and academic procedures make use of text analysis. Natural scene text detection is more difficult than document image text detection owing to variations in font, size, style, brightness, etc. The National Institute of Technology Jalandhar-Text Detection dataset (NITJ-TD) is a new dataset that we have put forward in this study for various text analysis tasks including text detection, text segmentation, script identification, text recognition, etc. a deep learning model that seeks to identify the text’s location within the image,which are gathered in an unrestricted setting. The system consists of an NMS to choose the best match and prevent repeated predictions, and a modified EAST to pinpoint the exact ROI in the image. To improve the model’s performance, an enhancement module is added to the fundamental Efficient and Accurate Scene Text detector (EAST). The suggested approach is contrasted in terms of text word detection in the image. Several pre-trained models are used to assign the text word to various intersections over Union (IoU) values. We made use of our NITJ-TD dataset, which is made up of 1500 photos that were gathered from various North Indian sites. Punjabi, English, and Hindi scripts can be seen on the images. We also examined the outcomes of the ICDAR-2013 benchmark dataset. On both the suggested dataset and the benchmarked dataset, our approach performed better.\u0000","PeriodicalId":50277,"journal":{"name":"International Journal on Document Analysis and Recognition","volume":"50 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141868498","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards fully automated processing and analysis of construction diagrams: AI-powered symbol detection 实现施工图的全自动处理和分析：人工智能驱动的符号检测

IF 2.3 4区计算机科学

International Journal on Document Analysis and Recognition Pub Date : 2024-07-25 DOI: 10.1007/s10032-024-00492-9

Laura Jamieson, Carlos Francisco Moreno-Garcia, Eyad Elyan

{"title":"Towards fully automated processing and analysis of construction diagrams: AI-powered symbol detection","authors":"Laura Jamieson, Carlos Francisco Moreno-Garcia, Eyad Elyan","doi":"10.1007/s10032-024-00492-9","DOIUrl":"https://doi.org/10.1007/s10032-024-00492-9","url":null,"abstract":"Construction drawings are frequently stored in undigitised formats and consequently, their analysis requires substantial manual effort. This is true for many crucial tasks, including material takeoff where the purpose is to obtain a list of the equipment and respective amounts required for a project. Engineering drawing digitisation has recently attracted increased attention, however construction drawings have received considerably less interest compared to other types. To address these issues, this paper presents a novel framework for the automatic processing of construction drawings. Extensive experiments were performed using two state-of-the-art deep learning models for object detection in challenging high-resolution drawings sourced from industry. The results show a significant reduction in the time required for drawing analysis. Promising performance was achieved for symbol detection across various classes, with a mean average precision of 79% for the YOLO-based method and 83% for the Faster R-CNN-based method. This framework enables the digital transformation of construction drawings, improving tasks such as material takeoff and many others.\u0000","PeriodicalId":50277,"journal":{"name":"International Journal on Document Analysis and Recognition","volume":"8 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141782748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GAN-based text line segmentation method for challenging handwritten documents 基于 GAN 的文本行分割方法，适用于具有挑战性的手写文档

IF 2.3 4区计算机科学

International Journal on Document Analysis and Recognition Pub Date : 2024-07-21 DOI: 10.1007/s10032-024-00488-5

İbrahim Özşeker, Ali Alper Demir, Ufuk Özkaya

引用次数: 0

Image quality determination of palm leaf heritage documents using integrated discrete cosine transform features with vision transformer 利用视觉变换器综合离散余弦变换特征确定棕榈叶遗产文件的图像质量

IF 2.3 4区计算机科学

International Journal on Document Analysis and Recognition Pub Date : 2024-07-17 DOI: 10.1007/s10032-024-00490-x

Remya Sivan, Peeta Basa Pati, Made Windu Antara Kesiman

{"title":"Image quality determination of palm leaf heritage documents using integrated discrete cosine transform features with vision transformer","authors":"Remya Sivan, Peeta Basa Pati, Made Windu Antara Kesiman","doi":"10.1007/s10032-024-00490-x","DOIUrl":"https://doi.org/10.1007/s10032-024-00490-x","url":null,"abstract":"Classification of Palm leaf images into various quality categories is an important step towards the digitization of these heritage documents. Manual inspection and categorization is not only laborious, time-consuming and costly but also subject to inspector’s biases and errors. This study aims to automate the classification of palm leaf document images into three different visual quality categories. A comparative analysis between various structural and statistical features and classifiers against deep neural networks is performed. VGG16, VGG19 and ResNet152v2 architectures along with a custom CNN model are used, while Discrete Cosine Transform (DCT), Grey Level Co-occurrence Matrix (GLCM), Tamura, and Histogram of Gradient (HOG) are chosen from the traditional methods. Based on these extracted features, various classifiers, namely, k-Nearest Neighbors (k-NN), multi-layer perceptron (MLP), Support Vector Machines (SVM), Decision Tree (DT) and Logistic Regression (LR) are trained and evaluated. Accuracy, precision, recall, and F1 scores are used as performance metrics for the evaluation of various algorithms. Results demonstrate that CNN embeddings and DCT features have emerged as superior features. Based on these findings, we integrated DCT with a Vision Transformer (ViT) for the document classification task. The result illustrates that this incorporation of DCT with ViT outperforms all other methods with 96% train F1 score and a test F1 score of 90%.","PeriodicalId":50277,"journal":{"name":"International Journal on Document Analysis and Recognition","volume":"49 1","pages":""},"PeriodicalIF":2.3,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141739164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0