Printed document layout analysis and optical character recognition system based on deep learning.

Journal: Scientific reports
Published Date: Jul 3, 2025

Abstract

This paper proposes a layout analysis and text recognition system for printed documents based on deep learning. Initially, scanned documents or image files are processed using a layout analysis algorithm based on YOLOv4 and YOLOv8 deep learning to identify the positions of titles, text paragraphs, tables, and images within the document. Each of these categories undergoes specific character segmentation processing. Then, the content is recognized using a text recognition algorithm based on Convolutional Neural Networks (CNN). Finally, the recognized text is integrated and output in editable formats, such as JSON or Microsoft formats. Our proposed method enables convenient, fast, and highly accurate OCR processing on a local computer.

Authors

  • Dong-Lin Li
    Department of electrical engineering, National Taiwan Ocean University, Beining Rd., Keelung City, 202301, Taiwan. ericli@email.ntou.edu.tw.
  • Shih-Kai Lee
    Department of electrical engineering, National Taiwan Ocean University, Beining Rd., Keelung City, 202301, Taiwan.
  • Yin-Ting Liu
    Department of electrical engineering, National Taiwan Ocean University, Beining Rd., Keelung City, 202301, Taiwan.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals