SEE: Towards semi-supervised end-to-end scene text recognition
- Detecting and recognizing text in natural scene images is a challenging, yet not completely solved task. In recent years several new systems that try to solve at least one of the two sub-tasks (text detection and text recognition) have been proposed. In this paper we present SEE, a step towards semi-supervised neural networks for scene text detection and recognition, that can be optimized end-to-end. Most existing works consist of multiple deep neural networks and several pre-processing steps. In contrast to this, we propose to use a single deep neural network, that learns to detect and recognize text from natural images, in a semi-supervised way. SEE is a network that integrates and jointly learns a spatial transformer network, which can learn to detect text regions in an image, and a text recognition network that takes the identified text regions and recognizes their textual content. We introduce the idea behind our novel approach and show its feasibility, by performing a range of experiments on standard benchmark datasets, where weDetecting and recognizing text in natural scene images is a challenging, yet not completely solved task. In recent years several new systems that try to solve at least one of the two sub-tasks (text detection and text recognition) have been proposed. In this paper we present SEE, a step towards semi-supervised neural networks for scene text detection and recognition, that can be optimized end-to-end. Most existing works consist of multiple deep neural networks and several pre-processing steps. In contrast to this, we propose to use a single deep neural network, that learns to detect and recognize text from natural images, in a semi-supervised way. SEE is a network that integrates and jointly learns a spatial transformer network, which can learn to detect text regions in an image, and a text recognition network that takes the identified text regions and recognizes their textual content. We introduce the idea behind our novel approach and show its feasibility, by performing a range of experiments on standard benchmark datasets, where we achieve competitive results.…
Author details: | Christian BartzORCiD, Haojin YangGND, Christoph MeinelORCiDGND |
---|---|
ISBN: | 978-1-57735-800-8 |
Title of parent work (English): | Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, Thirtieth Innovative Applications of Artificial Intelligence Conference, Eight Symposium on Educational Advances in Artificial Intelligence |
Publisher: | ASSOC Association for the Advancement of Artificial Intelligence |
Place of publishing: | Palo Alto |
Publication type: | Other |
Language: | English |
Year of first publication: | 2018 |
Publication year: | 2018 |
Release date: | 2022/02/21 |
Volume: | 10 |
Number of pages: | 8 |
First page: | 6674 |
Last Page: | 6681 |
Organizational units: | Digital Engineering Fakultät / Hasso-Plattner-Institut für Digital Engineering GmbH |
DDC classification: | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 000 Informatik, Informationswissenschaft, allgemeine Werke |
Peer review: | Referiert |