AI-Driven Classification of Bangla Handwritten Digits: A Machine Learning Approach

Nowadays, machine learning is playing an important role in the field of image classification. In this project three different machine learning classifier algorithms, Convolutional Neural Networks, K-Nearest Neighbor and Decision Tree, have been used to recognize Bangla hand- written digits. Two Python libraries known as Keras and Scikit-learn have been used in the models. The training of the models is optimized using Adam Optimizer. This paper gives an overview of multi-class classification of the dataset images using the three models and their performance evaluation. In the categorization of handwritten digits, Convolutional Neural Networks are found to be more accurate than K-Nearest Neighbor and Decision Tree. The core motivation of this work is to make a significant impact in the field of Computer Vision in the context of Bangla digits recognition.