Evaluation of Supervised Machine Learning Models for Handwritten Digit Recognition
Rohit Chandra Joshi, Vivek Raj Patel, Anjali Goyal · 2022
In the processing of information, handwriting recognition is crucial. The handwritten documents are large and the cost of their processing is also quite high. In the process of handwritten document processing, digits form an important component. Digits are used in large numbers in any document. This paper deals with the concept of recognition of handwritten digits using machine learning techniques. Various application areas of handwritten digit recognition are vehicle license-plate recognition, postal letter-sorting services, Cheque truncation system, etc. The core problem is that it is really difficult to distinguish handwritten numbers because everyone writes in their style. This paper presents an empirical analysis to compare the different supervised machine learning techniques for handwritten digit recognition and evaluate them using various evaluation measures such as accuracy, F1-Score, etc. the objectibe of this paper is to analyse the algorithms and find the best algorithms for handwritten digit recognition by improving the performance of different supervised machine learning techniques namely, Naive Bayes, k-Nearest Neighbor, Logistic Regression, Support Vector Machine, Random Forest, Gradient Boosting, Convolution Neural Network, and Decision Tree.