Handwriting Recognition Using HOG and Gabor Features

This work describes an efficient method for offline handwriting, Arabic word recognition, and digit recognition. The system employs a global recognition method, wherein segmentation of words is not used and the image is identified as a whole. To create this system, a preprocessing operation is applied to images of words or digits, which includes size normalization and the removal of diacritical marks and white spaces in columns and rows. The words or digits to be identified were subjected to feature extraction using the Gabor filter and histogram of oriented gradients (HOG). The KNN classifier used these features as descriptors. The proposed technique was evaluated utilizing both the IFN/ENIT databases and the standard MNIST database, and positive outcomes were attained.