Augmentation of base classifier performance via HMMs on a handwritten character data set

TL;DR

This study investigates how Hidden Markov Models (HMMs) and Viterbi error correction can improve handwritten Latin alphabet character recognition, achieving up to 89.8% accuracy.

Contribution

The paper demonstrates that integrating HMMs with base classifiers significantly enhances handwritten character recognition performance.

Findings

Best accuracy achieved was 89.8%.

Average recognition accuracy was 68.1%.

HMM-based correction improves classifier performance.

Abstract

This paper presents results of a study of the performance of several base classifiers for recognition of handwritten characters of the modern Latin alphabet. Base classification performance is further enhanced by utilizing Viterbi error correction by determining the Viterbi sequence. Hidden Markov Models (HMMs) models exploit relationships between letters within a word to determine the most likely sequence of characters. Four base classifiers are studied along with eight feature sets extracted from the handwritten dataset. The best classification performance after correction was 89.8%, and the average was 68.1%