Fast writer adaptation with style extractor network for handwritten text recognition.
Saved in:
| Title: | Fast writer adaptation with style extractor network for handwritten text recognition. |
|---|---|
| Authors: | Wang, Zi-Rui1 (AUTHOR) wangzr@cqupt.edu.cn, Du, Jun2 (AUTHOR) |
| Source: | Neural Networks. Mar2022, Vol. 147, p42-52. 11p. |
| Subjects: | Text recognition, Deep learning, Recurrent neural networks, Physiological adaptation |
| Abstract: | Writing style is an abstract attribute in handwritten text. It plays an important role in recognition systems and is not easy to define explicitly. Considering the effect of writing style, a writer adaptation method is proposed to transform a writer-independent recognizer toward a particular writer. This transformation has the potential to significantly increase accuracy. In this paper, under the deep learning framework, we propose a general fast writer adaptation solution. Specifically, without depending on other complex skills, a well designed style extractor network (SEN) trained by identification loss (IDL) is introduced to explicitly extract personalized writer information. The architecture of SEN consists of a stack of convolutional layers followed by a recurrent neural network with gated recurrent units to remove semantic context and retain writer information. Then, the outputs of the GRU are further integrated into a one-dimensional vector that is adopted to represent writing style. Finally, the extracted style information is fed into the writer-independent recognizer to achieve adaptation. Validated on offline handwritten text recognition tasks, the proposed fast sentence-level adaptation achieves remarkable improvements in Chinese and English text recognition tasks. Specifically, in the HETR task, a multi-information fusion network that is equipped with a hybrid attention mechanism and that integrates visual features, context features and writing style is proposed. In addition, under the same condition (only one writer-specific text line used as adaptation data), the proposed solution, without consuming extra time, can significantly outperform the previous multiple-pass decoding method. The code is available at https://github.com/Wukong90/Handwritten-Text-Recognition. [ABSTRACT FROM AUTHOR] |
| Copyright of Neural Networks is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 154948137 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Fast writer adaptation with style extractor network for handwritten text recognition. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Wang%2C+Zi-Rui%22">Wang, Zi-Rui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> wangzr@cqupt.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Du%2C+Jun%22">Du, Jun</searchLink><relatesTo>2</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Neural+Networks%22">Neural Networks</searchLink>. Mar2022, Vol. 147, p42-52. 11p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Text+recognition%22">Text recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Recurrent+neural+networks%22">Recurrent neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Physiological+adaptation%22">Physiological adaptation</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Writing style is an abstract attribute in handwritten text. It plays an important role in recognition systems and is not easy to define explicitly. Considering the effect of writing style, a writer adaptation method is proposed to transform a writer-independent recognizer toward a particular writer. This transformation has the potential to significantly increase accuracy. In this paper, under the deep learning framework, we propose a general fast writer adaptation solution. Specifically, without depending on other complex skills, a well designed style extractor network (SEN) trained by identification loss (IDL) is introduced to explicitly extract personalized writer information. The architecture of SEN consists of a stack of convolutional layers followed by a recurrent neural network with gated recurrent units to remove semantic context and retain writer information. Then, the outputs of the GRU are further integrated into a one-dimensional vector that is adopted to represent writing style. Finally, the extracted style information is fed into the writer-independent recognizer to achieve adaptation. Validated on offline handwritten text recognition tasks, the proposed fast sentence-level adaptation achieves remarkable improvements in Chinese and English text recognition tasks. Specifically, in the HETR task, a multi-information fusion network that is equipped with a hybrid attention mechanism and that integrates visual features, context features and writing style is proposed. In addition, under the same condition (only one writer-specific text line used as adaptation data), the proposed solution, without consuming extra time, can significantly outperform the previous multiple-pass decoding method. The code is available at https://github.com/Wukong90/Handwritten-Text-Recognition. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Neural Networks is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=154948137 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.neunet.2021.12.002 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 11 StartPage: 42 Subjects: – SubjectFull: Text recognition Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Recurrent neural networks Type: general – SubjectFull: Physiological adaptation Type: general Titles: – TitleFull: Fast writer adaptation with style extractor network for handwritten text recognition. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Wang, Zi-Rui – PersonEntity: Name: NameFull: Du, Jun IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 03 Text: Mar2022 Type: published Y: 2022 Identifiers: – Type: issn-print Value: 08936080 Numbering: – Type: volume Value: 147 Titles: – TitleFull: Neural Networks Type: main |
| ResultId | 1 |
