Scanned Document Retrieval System using Optical Character Recognition
Keywords:
Optical Character Recognition, Document Retrieval System, Tesseract, EasyOCRAbstract
In document management, especially in Thailand, the persistence of physical documents poses challenges for efficient information retrieval. This paper introduces a Scanned Document Retrieval System employing Optical Character Recognition (OCR) technology. The system allows users to retrieve specific pages of documents through keyword searches across all documents in the system. The study evaluates the performance of different OCR settings. From the usability test, Tesseract demonstrates superior accuracy and speed compared to EasyOCR. Additionally, the impact of prompt interpretation on document retrieval is explored, highlighting the need for flexibility in handling varied user prompts while emphasizing the effectiveness of literal and specific wordings. The paper identifies key considerations for future systems, including the compromise between flexibility and specificity.
References
S. Mori, C. Y. Suen, and K. Yamamoto, ‘Historical review of OCR research and development’, Proceedings of the IEEE, vol. 80, no. 7, pp. 1029–1058, 1992.
H. Zhang, D. Liu, and Z. Xiong, ‘Cnn-based text image super-resolution tailored for ocr’, in 2017 IEEE Visual Communications and Image Processing (VCIP), 2017, pp. 1–4.
J. Ye et al., ‘Ureader: Universal ocr-free visually-situated language understanding with multimodal large language model’, arXiv preprint arXiv:2310. 05126, 2023.
R. Smith, ‘An overview of the Tesseract OCR engine’, in Ninth international conference on document analysis and recognition (ICDAR 2007), 2007, vol. 2, pp. 629–633.
A. S. Agbemenu, J. Yankey, and E. O. Addo, ‘An automatic number plate recognition system using opencv and tesseract ocr engine’, International Journal of Computer Applications, vol. 180, no. 43, pp. 1–5, 2018.
T. G. N. Singh, ‘Automatic Gate Authentication System for RFID Tags and Thai ID Cards’, Asian Institute of Technology, School of Engineering and Technology Thailand, 2017.
D. P. Van Hoai, H.-T. Duong, and V. T. Hoang, ‘Text recognition for Vietnamese identity card based on deep features network’, International Journal on Document Analysis and Recognition (IJDAR), vol. 24, pp. 123–131, 2021.
A. Tsimpiris, D. Varsamis, and G. Pavlidis, ‘Tesseract OCR Evaluation on Greek Food Menus Datasets’, International Journal of Computing and Optimization, vol. 9, no. 1, 2022.
Q. M. Aljelawy and T. M. Salman, ‘Detecting license plate number using OCR technique and Raspberry Pi 4 with camera’, in 2022 2nd International Conference on Computing and Machine Intelligence (ICMI), 2022, pp. 1–5.
D. R. Vedhaviyassh, R. Sudhan, G. Saranya, M. Safa, and D. Arun, ‘Comparative Analysis of EasyOCR and TesseractOCR for Automatic License Plate Recognition using Deep Learning Algorithm’, in 2022 6th International Conference on Electronics, Communication and Aerospace Technology, 2022, pp. 966–971.
T. Hegghammer, ‘OCR with Tesseract, Amazon Textract, and Google Document AI: a benchmarking experiment’, Journal of Computational Social Science, vol. 5, no. 1. Springer, pp. 861–882, 2022.
C. Irimia, F. Harbuzariu, I. Hazi, and A. Iftene, ‘Official Document Identification and Data Extraction using Templates and OCR’, Procedia Computer Science, vol. 207, pp. 1571–1580, 2022.
P. Chakraborty and A. Mallik, ‘An open source tesseract based tool for extracting text from images with application in braille translation for the visually impaired’, International Journal of Computer Applications, vol. 68, no. 16, 2013
L. Floridi and M. Chiriatti, ‘GPT-3: Its nature, scope, limits, and consequences’, Minds and Machines, vol. 30, pp. 681–694, 2020.
H. Touvron et al., ‘Llama: Open and efficient foundation language models’, arXiv preprint arXiv:2302. 13971, 2023.
V. Rawte, A. Sheth, and A. Das, ‘A survey of hallucination in large foundation models’, arXiv preprint arXiv:2309. 05922, 2023.
