Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

HWD: A Novel Evaluation Score for Styled Handwritten Text Generation (2310.20316v1)

Published 31 Oct 2023 in cs.CV and cs.DL

Abstract: Styled Handwritten Text Generation (Styled HTG) is an important task in document analysis, aiming to generate text images with the handwriting of given reference images. In recent years, there has been significant progress in the development of deep learning models for tackling this task. Being able to measure the performance of HTG models via a meaningful and representative criterion is key for fostering the development of this research topic. However, despite the current adoption of scores for natural image generation evaluation, assessing the quality of generated handwriting remains challenging. In light of this, we devise the Handwriting Distance (HWD), tailored for HTG evaluation. In particular, it works in the feature space of a network specifically trained to extract handwriting style features from the variable-lenght input images and exploits a perceptual distance to compare the subtle geometric features of handwriting. Through extensive experimental evaluation on different word-level and line-level datasets of handwritten text images, we demonstrate the suitability of the proposed HWD as a score for Styled HTG. The pretrained model used as backbone will be released to ease the adoption of the score, aiming to provide a valuable tool for evaluating HTG models and thus contributing to advancing this important research area.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Adversarial Generation of Handwritten Text Images Conditioned on Sequences. In ICDAR. IEEE Computer Society, 2019.
  2. RIMES evaluation campaign for handwritten mail processing. In IWFHR, 2006.
  3. Handwriting Recognition in Low-Resource Scripts Using Adversarial Learning. In CVPR. IEEE, 2019.
  4. MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition. In CVPR, 2021.
  5. Handwriting Transformers. In ICCV, 2021.
  6. Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillation. In ICCV, 2021.
  7. Demystifying mmd gans. arXiv preprint arXiv:1801.01401, 2018.
  8. Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutions. IJDAR, 25(3):207–217, 2022.
  9. Learning to Read L’Infinito: Handwritten Text Recognition with Synthetic Training Data. In Proceedings of the International Conference on Computer Analysis of Images and Patterns, 2021.
  10. The LAM Dataset: A Novel Benchmark for Line-Level Handwritten Text Recognition. In ICPR, 2022.
  11. Effectively unbiased fid and inception score and where to find them. In CVPR, 2020.
  12. Watch Your Strokes: Improving Handwritten Text Recognition with Deformable Convolutions. In ICPR. IEEE Computer Society, 2021.
  13. Text and Style Conditioned GAN for Generation of Offline Handwriting Lines. In BMVC, 2020.
  14. Transcription alignment of Latin manuscripts using hidden Markov models. In HIP, 2011.
  15. Lexicon-free handwritten word spotting using character HMMs. Pattern Recognition Letters, 33(7):934–942, 2012.
  16. ScrabbleGAN: Semi-Supervised Varying Length Handwritten Text Generation. In CVPR, 2020.
  17. HiGAN: Handwriting Imitation Conditioned on Arbitrary-Length Texts and Disentangled Styles. In AAAI, 2021.
  18. HiGAN+: Handwriting Imitation GAN with Disentangled Representations. ACM Trans. Graphics, 42(1):1–17, 2022.
  19. Generative Adversarial Nets. In NeurIPS, 2014.
  20. My Text in Your Handwriting. ACM Trans. Graphics, 35(3), 2016.
  21. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In Advances in neural information processing systems, 2017.
  22. Distilling content from style for handwritten word recognition. In ICFHR, 2020.
  23. Content and style aware generation of text-line images for handwriting recognition. IEEE Trans. PAMI, pages 1–1, 2021.
  24. GANwriting: Content-Conditioned Generation of Styled Handwritten Word Images. In ECCV, 2020.
  25. Geometry Score: A Method For Comparing Generative Adversarial Networks. In ICML. PMLR, 2018.
  26. CVL-DataBase: An Off-Line Database for Writer Retrieval, Writer Identification and Word Spotting. In ICDAR, 2013.
  27. SLOGAN: Handwriting Style Synthesis for Arbitrary-Length and Out-of-Vocabulary Text. IEEE Trans. Neural Netw. Learn. Syst., 2022.
  28. A comprehensive comparison of open-source libraries for handwritten text recognition in norwegian. In DAS, 2022.
  29. KHATT: An open Arabic offline handwritten text database. Pattern Recognition, 47:1096–1112, 2014.
  30. The IAM-database: an English sentence database for offline handwriting recognition. IJDAR, 5(1):39–46, 2002.
  31. SmartPatch: Improving Handwritten Word Imitation with Patch Discriminators. In ICDAR, 2021.
  32. BanglaWriting: A multi-purpose offline Bangla handwriting dataset. Data in Brief, 34:106633, 2021.
  33. Evaluating synthetic pre-training for handwriting processing tasks. Pattern Recognition Letters, 2023.
  34. Handwritten Text Generation from Visual Archetypes. In CVPR, 2023.
  35. How to Choose Pretrained Handwriting Recognition Models for Single Writer Fine-Tuning. In ICDAR, 2023.
  36. ICFHR2014 competition on handwritten text recognition on transcriptorium datasets (HTRtS). In ICFHR, 2014.
  37. The RODRIGO Database. In LREC, 2010.
  38. Attention is all you need. In NeurIPS, 2017.
  39. Combining Shape and Physical Models for On-line Cursive Handwriting Synthesis. IJDAR, 7(4):219–227, 2005.
  40. Rethinking and Improving the Robustness of Image Style Transfer. In CVPR, 2021.
  41. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR, 2018.
  42. Sequence-to-sequence domain adaptation network for robust text image recognition. In CVPR, 2019.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now