Skip to content
DSML.KZ
Publications

Talk · International Informatics and Software Engineering Conference · February 5, 2026

Reliable Kazakh Handwritten Text Recognition with Error-Correcting Output Codes and Redundant Ensembles

Abdurakhim Bakytzhan, Dinara Kaibassova

Dinara Kaibassova
Open via DOI

Abstract

Handwritten text recognition systems that serve real users must be more than accurate—they must remain reliable under noise, device constraints, and occasional compute faults. We study reliability-centered Kazakh handwritten text recognition by combining error-correcting output codes with redundant lightweight ensembles and a simple watchdog for selective prediction. Each character is mapped to a structured codeword and the network predicts code bits; inference uses nearest-neighbor Hamming decoding with optional parity checks, converting small logit perturbations into correctable events. We evaluate robustness under controlled corruptions (blur, noise, occlusion), quantization, and bit-flip fault injection. In bit-flip simulations, error-correcting-code decoding reduces misclassification from 78.73% to 2.27% at p = 0.10, and from 90.69% to 23.43% at p = 0.20, while correctly recovering 86.66% of faulted trials at p = 0.10. With three diverse replicas, bit-wise ensemble fusion further lowers error to 0.01% at p = 0.10, outperforming label voting. Finally, the watchdog reduces failure-without-warning to 0.01% at 64.95% coverage, enabling practical coverage–risk trade-offs. Together, these results show that classical redundancy and coding concepts translate naturally to modern deep handwritten text recognition, providing a practical path to robust and deployable recognition for Kazakh and other under-resourced scripts.

Handwritten Text Recognition TechniquesAdversarial Robustness in Machine LearningAdvanced Neural Network Applicationserror-correcting output codesensemble fusionparity check

More by Dinara Kaibassova