Papers › TextCaps : Handwritten Character Recognition with Very Small Datasets

TextCaps : Handwritten Character Recognition with Very Small Datasets

17 Apr 2019arXiv:1904.08095archive 2025-07-28

Vinoj Jayasundara, Sandaru Jayasekara, Hirunima Jayasekara, Jathushan Rajasegaran, Suranga Seneviratne, Ranga Rodrigo

Many localized languages struggle to reap the benefits of recent advancements in character recognition systems due to the lack of substantial amount of labeled training data. This is due to the difficulty in generating large amounts of labeled data for such languages and inability of deep learning techniques to properly learn from small number of training samples. We solve this problem by introducing a technique of generating new training samples from the existing samples, with realistic augmentations which reflect actual variations that are present in human hand writing, by adding random controlled noise to their corresponding instantiation parameters. Our results with a mere 200 training samples per class surpass existing character recognition results in the EMNIST-letter dataset while achieving the existing results in the three datasets: EMNIST-balanced, EMNIST-digits, and MNIST. We also develop a strategy to effectively use a combination of loss functions to improve reconstructions. Our system is useful in character recognition for localized languages that lack much labeled training data and even in other related more general contexts such as object recognition.

PaperPDFCode

Code

vinojjayasundara/textcaps officialmentioned in papertf report
kubantjan/fast-form mentioned on GitHub report
milanzongor/unihack_2020 mentioned on GitHub 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

Few-Shot Image ClassificationImage ClassificationImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification EMNIST-Letters TextCaps Accuracy 95.39 #6 of 11 Archive leaderboard report
Image Classification Fashion-MNIST TextCaps Percentage error 6.29 #8 of 34 Archive leaderboard report
Image Classification MNIST TextCaps Accuracy 99.71 #15 of 81 Archive leaderboard report
Image Classification MNIST TextCaps Percentage error 0.29 #15 of 81 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