Efficient Text Bounding Box Identification Using Mask R-CNN: Case of Thai Documents

Abstract

Text detection is a fundamental task in computer vision, particularly for Optical Character Recognition (OCR) applications. This study focuses on text detection within an OCR application, encompassing text detection, text recognition, and information extraction, explicitly focusing on text detection. Character-Region Awareness for Text Detection (CRAFT), Pyramid Mask Text Detector (PMTD), and Scene Text Detection with Supervised Pyramid Context Network (SPCNET) have demonstrated promising results in bounding-box detection. However, it faces challenges related to post-processing and multiline text detection. A post-processing problem arises because of the need to reconfigure the model when new documents are introduced, which leads to inefficiencies and complexities. In addition, CRAFT tends to merge bounding boxes from consecutive lines by introducing multiline errors, especially for CRAFT. To address these challenges, this study proposes an adapted approach based on Mask R-CNN, an instance segmentation model that treats each text element as an individual object. By adopting the Mask R-CNN approach, post-processing issues were successfully eliminated. Moreover, the multiline problem is effectively resolved. Comparative experiments demonstrate that the proposed model achieves results comparable to those of these models while surpassing them in accuracy and versatility. The proposed model is extensively evaluated on various document types, including bankbooks, Thai ID cards (both front and back sides), invoices, car registrations, mobile banking slips, passports, Indonesian ID cards, driver licenses, and receipts. The results indicated the model's high performance and potential for real-world applications. Eliminating post-processing and multiline problems ensures the model's adaptability to a wide range of document structures and reduces both time inference and resource utilization.