Recent Advances in Document Image Analysis and Graphics Recognition

Dear Colleagues,

Document image analysis and graphics recognition (DIAGR) is a vital research area in computer vision and pattern recognition, focusing on the automatic processing, understanding, and interpretation of document images and graphical content. With the exponential growth of digitized documents—ranging from historical manuscripts and printed texts to invoices, maps, and technical drawings—advanced DIAGR techniques are essential for efficient information retrieval, archival, and intelligent human–computer interaction. Challenges such as degraded document restoration, layout analysis, text/graphics separation, handwriting recognition, shadow removal, and symbol detection remain critical research frontiers. The integration of deep learning, LLMs, multimodal learning, and domain adaptation has further expanded the potential of DIAGR, enabling robust solutions for real-world applications in education, healthcare, finance, and cultural heritage preservation.

Aim of the Special Issue

This Special Issue of Electronics (ISSN 2079-9292) aims to showcase cutting-edge research and innovative methodologies in DIAGR, fostering discussions on both theoretical advancements and practical implementations. Electronics is a peer-reviewed, SCIE-indexed journal focusing on emerging technologies in electronics and computer science, making it an ideal platform for DIAGR contributions that intersect with hardware acceleration (e.g., FPGA/GPU for document processing), embedded systems, large language models, and AI-driven applications. We invite original research articles and reviews addressing challenges in the accuracy, scalability, and cross-domain adaptability of DIAGR systems, with an emphasis on solutions leveraging modern computational paradigms.

Suggested Themes

Topics of interest include but are not limited to

• Document Image Enhancement: Shadow removal, noise removal, binarization, and super-resolution for degraded documents.
• Layout Analysis: Segmentation of text, graphics, and tables in complex documents.
• Text Recognition: Handwritten/textured OCR, multilingual processing, and adversarial robustness.
• Graphics Recognition: Symbol detection, diagram interpretation, and vectorization.
• Multimodal Document Understanding: Integration of visual, textual, and structural features.
• Historical Document Processing: Restoration and transcription of archival materials.
• AI-Driven Methods: Deep learning, transformers, and few-shot learning for DIAGR tasks.
• Applications: Automated form processing, intelligent editing tools, and educational aids.

We encourage submissions that highlight reproducibility, open datasets, and benchmarks to promote community engagement. Join us in advancing the frontiers of DIAGR for a smarter, more accessible digital future! In this Special Issue, original research articles and reviews are welcome.

We look forward to receiving your contributions.

Dr. Bingshu Wang
Dr. Yongjun Zhang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• document image analysis
• graphics recognition
• image enhancement
• image segmentation
• shadow removal
• layout analysis
• OCR
• LLMs
• deep learning
• tilt correction