A Machine Learning and Deep Learning Approach for Malayalam Handwritten Character Recognition

Handwritten character recognition is an important research area in pattern recognition and computer vision with applications in document digitization and automated information processing. Recognition of Malayalam handwritten characters is particularly challenging due to the complex structure of the script, the presence of curves and loops, and variations in individual handwriting styles. This paper presents a system for recognizing isolated Malayalam handwritten characters using two classification approaches: Support Vector Machine (SVM) and Convolutional Neural Network (CNN). In the SVM-based approach, Histogram of Oriented Gradients (HOG) is used to extract discriminative features from character images before classification. In contrast, the CNN model learns feature representations automatically from the image data during the training process. A dataset consisting of handwritten samples of Malayalam characters is used to train and evaluate the models. The study focuses on analyzing the effectiveness of traditional machine learning and deep learning approaches for Malayalam handwritten character recognition.