skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models

Document Analysis and Recognition - ICDAR 2023, 2023, p.384-401 [Peer Reviewed Journal]

The Author(s), under exclusive license to Springer Nature Switzerland AG 2023 ;ISSN: 0302-9743 ;ISBN: 9783031416781 ;ISBN: 3031416783 ;EISSN: 1611-3349 ;EISBN: 3031416791 ;EISBN: 9783031416798 ;DOI: 10.1007/978-3-031-41679-8_22

Digital Resources/Online E-Resources

Citations Cited by
  • Title:
    WordStylist: Styled Verbatim Handwritten Text Generation with Latent Diffusion Models
  • Author: Nikolaidou, Konstantina ; Retsinas, George ; Christlein, Vincent ; Seuret, Mathias ; Sfikas, Giorgos ; Smith, Elisa Barney ; Mokayed, Hamam ; Liwicki, Marcus
  • Subjects: Data Augmentation ; Diffusion Models ; Handwriting Generation ; Handwriting Text Recognition ; Machine Learning ; Maskininlärning ; Synthetic Image Generation ; Text Content Generation
  • Is Part Of: Document Analysis and Recognition - ICDAR 2023, 2023, p.384-401
  • Description: Text-to-Image synthesis is the task of generating an image according to a specific text description. Generative Adversarial Networks have been considered the standard method for image synthesis virtually since their introduction. Denoising Diffusion Probabilistic Models are recently setting a new baseline, with remarkable results in Text-to-Image synthesis, among other fields. Aside its usefulness per se, it can also be particularly relevant as a tool for data augmentation to aid training models for other document image processing tasks. In this work, we present a latent diffusion-based method for styled text-to-text-content-image generation on word-level. Our proposed method is able to generate realistic word image samples from different writer styles, by using class index styles and text content prompts without the need of adversarial training, writer recognition, or text recognition. We gauge system performance with the Fréchet Inception Distance, writer recognition accuracy, and writer retrieval. We show that the proposed model produces samples that are aesthetically pleasing, help boosting text recognition performance, and get similar writer retrieval score as real data. Code is available at: https://github.com/koninik/WordStylist.
  • Publisher: Cham: Springer Nature Switzerland
  • Language: English
  • Identifier: ISSN: 0302-9743
    ISBN: 9783031416781
    ISBN: 3031416783
    EISSN: 1611-3349
    EISBN: 3031416791
    EISBN: 9783031416798
    DOI: 10.1007/978-3-031-41679-8_22
  • Source: SWEPUB Freely available online
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait