Document Image Analysis

While Optical Character Recognition (OCR) techniques have made significant strides, they often fall short when dealing with non-text elements in documents. This gap highlighted the need for comprehensive solutions that recognize text and accurately detect and reconstruct tables and other graphical components. Our collaborative research efforts, extensive experiments, and continuous learning have culminated in developing the algorithms presented in this book, a testament to the power of teamwork in overcoming challenges.

The book is structured to provide a thorough understanding of the problem domain, existing techniques, and our proposed solutions. We begin with an introduction to the challenges of digitizing printed documents, highlighting the limitations of current OCR methods and the need for advanced table detection and recognition algorithms. Subsequent chapters delve into detailed surveys of existing techniques, followed by a comprehensive presentation of our algorithms. We also explore the application of our enhanced algorithm in various scenarios, showcasing its robustness and effectiveness.

Dr. Akmal Jahan M. A. C. is an academic in Computer Science, serving as a Senior Lecturer at the Department of Computer Science, Faculty of Applied Sciences, South Eastern University of Sri Lanka. She completed her Ph.D at Queensland University of Technology, Australia, and received her M.Sc. in Computer Science from the University of Peradeniya, Sri Lanka. Driven by a passion for exploring the fields of Artificial Intelligence, Machine Learning, Computer Vision, Image Processing, and Data Science, Dr. Akmal Jahan is committed to advancing knowledge and fostering innovation through her research and has published many articles in indexed journals and at IEEE conferences.

Prof. Roshan G. Ragel is a prominent computer engineering academic, serving as a professor at the University of Peradeniya since 2017. With a deep expertise in the fields of Internet of Things, Wearable Computing, Bioinformatics, and Artificial Intelligence and Machine Learning, he has co-authored over 200 peer-reviewed articles. Prof. Ragel's outstanding contributions to computer science have been recognized multiple times, being named the top scientist in computer science in Sri Lanka by the AD Scientific Index in 2021 and 2022 and the best computer scientist in the country in 2023 and 2024.