File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1007/978-3-030-20890-5_13
- Scopus: eid_2-s2.0-85067349428
- WOS: WOS:000492902300013
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: SAFE: Scale Aware Feature Encoder for Scene Text Recognition
Title | SAFE: Scale Aware Feature Encoder for Scene Text Recognition |
---|---|
Authors | |
Keywords | Scale aware feature encoder Scene text recognition |
Issue Date | 2019 |
Publisher | Springer. The Proceedings' web site is located at https://link.springer.com/book/10.1007/978-3-030-20890-5 |
Citation | Proceedings of the 14th Asian Conference on Computer Vision (ACCV), Perth, Australia, 2-6 December 2018. In Computer Vision – ACCV 2018, pt. 2, p. 196-211. Cham: Springer, 2019 How to Cite? |
Abstract | In this paper, we address the problem of having characters with different scales in scene text recognition. We propose a novel scale aware feature encoder (SAFE) that is designed specifically for encoding characters with different scales. SAFE is composed of a multi-scale convolutional encoder and a scale attention network. The multi-scale convolutional encoder targets at extracting character features under multiple scales, and the scale attention network is responsible for selecting features from the most relevant scale(s). SAFE has two main advantages over the traditional single-CNN encoder used in current state-of-the-art text recognizers. First, it explicitly tackles the scale problem by extracting scale-invariant features from the characters. This allows the recognizer to put more effort in handling other challenges in scene text recognition, like those caused by view distortion and poor image quality. Second, it can transfer the learning of feature encoding across different character scales. This is particularly important when the training set has a very unbalanced distribution of character scales, as training with such a dataset will make the encoder biased towards extracting features from the predominant scale. To evaluate the effectiveness of SAFE, we design a simple text recognizer named scale-spatial attention network (S-SAN) that employs SAFE as its feature encoder, and carry out experiments on six public benchmarks. Experimental results demonstrate that S-SAN can achieve state-of-the-art (or, in some cases, extremely competitive) performance without any post-processing. |
Description | Revised Selected Papers Poster Session P1 |
Persistent Identifier | http://hdl.handle.net/10722/272012 |
ISBN | |
ISSN | 2023 SCImago Journal Rankings: 0.606 |
ISI Accession Number ID | |
Series/Report no. | Lecture Notes in Computer Science (LNCS), v. 11362 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, W | - |
dc.contributor.author | Chen, C | - |
dc.contributor.author | Wong, KKY | - |
dc.date.accessioned | 2019-07-20T10:33:57Z | - |
dc.date.available | 2019-07-20T10:33:57Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Proceedings of the 14th Asian Conference on Computer Vision (ACCV), Perth, Australia, 2-6 December 2018. In Computer Vision – ACCV 2018, pt. 2, p. 196-211. Cham: Springer, 2019 | - |
dc.identifier.isbn | 978-3-030-20889-9 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | http://hdl.handle.net/10722/272012 | - |
dc.description | Revised Selected Papers | - |
dc.description | Poster Session P1 | - |
dc.description.abstract | In this paper, we address the problem of having characters with different scales in scene text recognition. We propose a novel scale aware feature encoder (SAFE) that is designed specifically for encoding characters with different scales. SAFE is composed of a multi-scale convolutional encoder and a scale attention network. The multi-scale convolutional encoder targets at extracting character features under multiple scales, and the scale attention network is responsible for selecting features from the most relevant scale(s). SAFE has two main advantages over the traditional single-CNN encoder used in current state-of-the-art text recognizers. First, it explicitly tackles the scale problem by extracting scale-invariant features from the characters. This allows the recognizer to put more effort in handling other challenges in scene text recognition, like those caused by view distortion and poor image quality. Second, it can transfer the learning of feature encoding across different character scales. This is particularly important when the training set has a very unbalanced distribution of character scales, as training with such a dataset will make the encoder biased towards extracting features from the predominant scale. To evaluate the effectiveness of SAFE, we design a simple text recognizer named scale-spatial attention network (S-SAN) that employs SAFE as its feature encoder, and carry out experiments on six public benchmarks. Experimental results demonstrate that S-SAN can achieve state-of-the-art (or, in some cases, extremely competitive) performance without any post-processing. | - |
dc.language | eng | - |
dc.publisher | Springer. The Proceedings' web site is located at https://link.springer.com/book/10.1007/978-3-030-20890-5 | - |
dc.relation.ispartof | Asian Conference on Computer Vision (ACCV), 2018 | - |
dc.relation.ispartof | Computer Vision – ACCV 2018 | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science (LNCS), v. 11362 | - |
dc.subject | Scale aware feature encoder | - |
dc.subject | Scene text recognition | - |
dc.title | SAFE: Scale Aware Feature Encoder for Scene Text Recognition | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Wong, KKY: kykwong@cs.hku.hk | - |
dc.identifier.authority | Wong, KKY=rp01393 | - |
dc.identifier.doi | 10.1007/978-3-030-20890-5_13 | - |
dc.identifier.scopus | eid_2-s2.0-85067349428 | - |
dc.identifier.hkuros | 299479 | - |
dc.identifier.volume | 2 | - |
dc.identifier.spage | 196 | - |
dc.identifier.epage | 211 | - |
dc.identifier.eissn | 1611-3349 | - |
dc.identifier.isi | WOS:000492902300013 | - |
dc.publisher.place | Cham | - |
dc.identifier.issnl | 0302-9743 | - |