A Hybrid U-Net–GAN Framework for Restoring Broken Kannada Handwritten Characters
Bibliographic record
Abstract
Restoring broken or degraded handwritten characters is a major obstacle in optical character recognition (OCR) and the digital preservation of historical manuscripts.In this paper, we propose a hybrid framework named U-Net + Generative Adversarial Network (GAN) for Kannada Restoration (UNGAN-KR) for broken handwritten characters.It integrates the best of both encoder-decoder structural reconstruction and adversarial refinement to ensure both pixel-level fidelity and perceptual realism.The U-Net restores broken strokes while ensuring preservation of character structure and the GAN discriminator promotes natural handwritten textures.We evaluated the framework on a dataset of 71,149 handwritten Kannada characters using multiple metrics of accuracy.The experimental results show that our proposed framework achieves an accuracy of 97.8% with improvements in perceptual quality, and outperforms benchmarks like Convolutional Neural Network (CNN) autoencoders, standard U-Net, and GAN-based inpainting.Ablation studies show that the integration of U-Net and GAN provides hybrid enhancements that are important for reconstruction accuracy.Thus, the framework is suitable for pre-processing data and digital sustainable archiving and the automated restoration of degraded Kannada manuscripts.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".