Italic font recognition using stroke pattern analysis on wavelet decomposed word images

This work describes an italic font recognition method using stroke pattern analysis on wavelet decomposed word images. The word images are extracted from scanned text documents containing word objects in various fonts and styles. Earlier font recognition methods mainly focus on slanted texture or pattern analysis on single character or large text blocks, which are sensitive to noise and subject to font and style variations such as size, serifness, boldness, etc. Our method takes advantage of 2-D wavelet decomposition on each word image and performs statistical analysis on stroke patterns obtained from wavelet decomposed sub-images. Experiments are carried out with 22,384 frequently used word images in both normal and italic styles of four different fonts. On average, a recognition accuracy of 95.76% for normal style and 96.49% for italic style is achieved. Experiments conducted on word images extracted from scanned documents with scattered italic words also show an encouraging result.