RFBTD: RFB Text Detector
Christen M, AB Saravanan

TL;DR
This paper introduces RFBTD, a text detector capable of identifying individual words or text lines of arbitrary orientations in scene images, emphasizing dense text detection with improved receptive field techniques.
Contribution
It proposes a novel text detection method leveraging Receptive Field Blocks to enhance detection of dense, arbitrarily oriented text in scene images.
Findings
Achieved an F-score of 47.09 on ICDAR2015 dataset.
Demonstrated the effectiveness of RFB in improving text segment detection.
Focused on detecting individual words in dense scene text environments.
Abstract
Text detection plays a critical role in the whole procedure of textual information extraction and understanding. On a high note, recent years have seen a surge in the high recall text detectors in scene text images, however text boxes for individual words is still a challenging when dense text is present in the scene. In this work, we propose an elegant solution that promotes prediction of words or text lines of arbitrary orientations and directions, providing emphasis on individual words. We also investigate the effects of Receptive Field Blocks(RFB) and its impact in receptive fields for text segments. Experiments were done on the ICDAR2015 and achieves an F-score of 47.09 at 720p
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHandwritten Text Recognition Techniques · Music and Audio Processing · Image Retrieval and Classification Techniques
