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.…
Verfasserangaben: | Christian BartzORCiD, Haojin YangGND, Christoph MeinelORCiDGND |
---|---|
ISBN: | 978-1-57735-800-8 |
Titel des übergeordneten Werks (Englisch): | 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 |
Verlag: | ASSOC Association for the Advancement of Artificial Intelligence |
Verlagsort: | Palo Alto |
Publikationstyp: | Sonstiges |
Sprache: | Englisch |
Jahr der Erstveröffentlichung: | 2018 |
Erscheinungsjahr: | 2018 |
Datum der Freischaltung: | 21.02.2022 |
Band: | 10 |
Seitenanzahl: | 8 |
Erste Seite: | 6674 |
Letzte Seite: | 6681 |
Organisationseinheiten: | Digital Engineering Fakultät / Hasso-Plattner-Institut für Digital Engineering GmbH |
DDC-Klassifikation: | 0 Informatik, Informationswissenschaft, allgemeine Werke / 00 Informatik, Wissen, Systeme / 000 Informatik, Informationswissenschaft, allgemeine Werke |
Peer Review: | Referiert |