Handwritten-Digit-Recognition

A Handwritten Digit Recognition System to evaluate the effectiveness of various types of classifiers such as MLP classifier, K Nearest Neighbour Classifier, SVC, Decision Tree Classifier, Random Forest Classifier, AdaBoost Classifier and GaussianNB in recognising handwritten digits. The aim of this project was to evaluate the effectiveness of various types of classifiers in recognizing handwritten digits. It has been shown in pattern recognition that no single classifier performs the best for all pattern classification problems consistently. So the goal of the project was to experiment with different classifiers and combination methods and evaluate their performance in this particular problem of handwritten digit recognition. This report discusses the different classifiers used in the project, the rationale for their choices and the results obtained by their individual and combined performances. We are also doing the comparative study of few classifiers and their accuracy and time taken has been analysed.