Convolutional Neural Network Based on TensorFlow for the Recognition of Handwritten Digits in the Odia

Odia, which is recognized as the official language of the Indian State of Odisha, is one of the many regional languages that people in India use to communicate with one another. Over fifty million people worldwide communicate in the Odia language, which has a history that dates back more than a millennium and a half. Odia digits' complexity arises from each character's intricate design, which features numerous curves. Handwritten scripts exhibit increased complexity due to the unrestricted nature of freeform writing. Odia script is used to write a great deal of historical texts, some of which date back more than a thousand years. A suitable automation technology that makes it simple to convert old paper documents into digital data protects these irreplaceable records. This article investigates the recognition performance of a Convolutional Neural Network model for handwritten Odia numbers. By entering the numerical numbers into Microsoft Paint, we were able to generate data using software. For the CNN model's implementation, we used Python programming. Following the CNN model's training and testing of the dataset, 80% accuracy was noted.