Papers › StackMix and Blot Augmentations for Handwritten Text Recognition

StackMix and Blot Augmentations for Handwritten Text Recognition

26 Aug 2021arXiv:2108.11667archive 2025-07-28

Alex Shonenkov, Denis Karachev, Maxim Novopoltsev, Mark Potanin, Denis Dimitrov

This paper proposes a handwritten text recognition(HTR) system that outperforms current state-of-the-artmethods. The comparison was carried out on three of themost frequently used in HTR task datasets, namely Ben-tham, IAM, and Saint Gall. In addition, the results on tworecently presented datasets, Peter the Greats manuscriptsand HKR Dataset, are provided.The paper describes the architecture of the neural net-work and two ways of increasing the volume of train-ing data: augmentation that simulates strikethrough text(HandWritten Blots) and a new text generation method(StackMix), which proved to be very effective in HTR tasks.StackMix can also be applied to the standalone task of gen-erating handwritten text based on printed text.

PaperPDFCode

Code

sberbank-ai/StackMix-OCR officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationHTRHandwritten Text RecognitionText Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Handwritten Text Recognition Bentham StackMix+Blots CER 1.73 #1 of 1 Archive leaderboard report
Handwritten Text Recognition Digital Peter StackMix+Blots CER 2.5 #1 of 1 Archive leaderboard report
Handwritten Text Recognition HKR StackMix+Blots CER 3.49 #1 of 1 Archive leaderboard report
Handwritten Text Recognition IAM-B StackMix+Blots CER 3.77 #1 of 1 Archive leaderboard report
Handwritten Text Recognition IAM-D StackMix+Blots CER 3.01 #1 of 1 Archive leaderboard report
Handwritten Text Recognition Saint Gall StackMix+Blots CER 3.65 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections