Development of a Custom Handwritten Kannada Dataset and CNN-BiLSTM-CTC Based OCR System

November 2026
Vol-12, Issue-5
Paper ID: 29022
ISSN: 2395-4396
Downloads: 47
Download PDF

Abstract & Details

Research Area
OCR, Machine learning, Image Processing, CNN, Deep learning
Keywords
Optical character recognition Convolution Neural Networks Bi-directional Long Short Term Memory Connectionist Temporal Classification
Abstract
**Abstract** This project focuses on developing a Kannada Handwritten Text Recognition system using Deep Learning. The system uses a Convolutional Neural Network (CNN) and Bidirectional LSTM with Connectionist Temporal Classification (CTC) to recognize handwritten Kannada text from images. The dataset is preprocessed to improve image quality and reduce handwriting variations before training. The model is trained and evaluated using separate training, validation, and testing datasets. The proposed system aims to make Kannada handwritten text recognition easier and support the digitization of handwritten Kannada documents.

Author Information

# Name Institute / Affiliation
1 Nandini G R S J M Institute of Technology, Chitradurga
2 Brunda G S J M Institute of Technology, Chitradurga
3 Nandini N S J M Institute of Technology, Chitradurga
4 Nithya C R S J M Institute of Technology, Chitradurga
5 Uma Patil G M S J M Institute of Technology, Chitradurga

How to Cite

Use the following formats to cite this article in your research.

APA Style
R, Nandini G, G, Brunda, N, Nandini, R, Nithya C, & M, Uma Patil G (2026). Development of a Custom Handwritten Kannada Dataset and CNN-BiLSTM-CTC Based OCR System. International Journal of Advance Research and Innovative Ideas In Education, 12(5), 933-938.
MLA Style
R, Nandini G, et al. "Development of a Custom Handwritten Kannada Dataset and CNN-BiLSTM-CTC Based OCR System." International Journal of Advance Research and Innovative Ideas In Education, vol. 12, no. 5, 2026, pp. 933-938.
IEEE Style
Nandini G R, Brunda G, Nandini N, Nithya C R, and Uma Patil G M, "Development of a Custom Handwritten Kannada Dataset and CNN-BiLSTM-CTC Based OCR System," International Journal of Advance Research and Innovative Ideas In Education, vol. 12, no. 5, pp. 933-938, 2026.
Vancouver Style
R Nandini G, G Brunda, N Nandini, R Nithya C, M Uma Patil G. Development of a Custom Handwritten Kannada Dataset and CNN-BiLSTM-CTC Based OCR System. International Journal of Advance Research and Innovative Ideas In Education. 2026;12(5):933-938.
Harvard Style
R, Nandini G, G, Brunda, N, Nandini, R, Nithya C, & M, Uma Patil G (2026) 'Development of a Custom Handwritten Kannada Dataset and CNN-BiLSTM-CTC Based OCR System', International Journal of Advance Research and Innovative Ideas In Education, 12(5), pp. 933-938.
Chicago Style
R, Nandini G, et al. "Development of a Custom Handwritten Kannada Dataset and CNN-BiLSTM-CTC Based OCR System." International Journal of Advance Research and Innovative Ideas In Education 12, no. 5 (2026): 933-938.
Turabian Style
R, Nandini G, et al. "Development of a Custom Handwritten Kannada Dataset and CNN-BiLSTM-CTC Based OCR System." International Journal of Advance Research and Innovative Ideas In Education 12, no. 5 (2026): 933-938.

Export Citation

Related Research

AI-Based Smart Waste Segregation and Recycling Assistant
Priyanka Patil et al. 2026 Artificial Intelligence (AI) and Machine Learning
Download PDF
Precision Agriculture Using Computer Vision: A Review of In-Field Disease Detection, Foliar Severity Estimation
Ashlesha Adsul et al. 2026 Precision Agriculture, Computer Vision, AI, Machine Learning
Download PDF
Explainable AI for Classification and Prioritization of QHSE Audit Findings
Dr. Feroz Khan Ismail 2026 Artificial Intelligence, Quality Management, QHSE Auditing, Risk Management and Engineering
Download PDF
CodeCoach AI: A Review of Automated Programming Assessment, Explainable Feedback, and an AI-Assisted Coding Practice Framework
Mr. Pratham Tembhurne et al. 2026 Artificial Intelligence in Education, focusing on automated code assessment and personalized feedback to improve programming skills.
Download PDF