Design and Development of a Framework for Stroke Based Handwritten Gujarati Font Generation

Abstract

Handwritten font generation is important for preserving cultural heritage and creating personalized designs. It adds an authentic and expressive touch to printed materials, making them visually appealing and establishing a stronger connection with the audience. This thesis aims to design a framework for generating handwritten fonts in the Gujarati script, mimicking the variation of human handwriting. newlineThe study begins by examining existing research on handwriting generation and identifying the need for further exploration of the Gujarati script. Due to the unique structure of the Gujarati script, existing resources developed for other scripts cannot be directly applied. The goal is to bridge the gap between traditional handwriting and digital typography by generating a Gujarati handwritten font using stroke-based techniques. newlineThe proposed font generation model consists of a learning phase and a generation phase. In the learning phase, Gujarati scripts are analyzed, and rules for designing each character are formulated. The generation phase involves the user providing a small subset of characters, and the system automatically generates the remaining character glyphs based on extracted strokes and learned rules. An opentype font is generated for use in Gujarati script-compatible text editors. newlineThe Learning phase began by exploring the importance of strokes in capturing the features of Gujarati handwriting and their role in font generation. Based on the analysis, six keystrokes for generating the glyphs of consonants are identified and a comprehensive ruleset is developed. This ruleset involved the concatenation of strokes in a stroke-based manner, ensuring visual consistency in the resulting glyphs. newlineIn the generation phase of the HGFG system, handwritten Gujarati fonts are created. This involved preprocessing the input text document images by converting them to grayscale, removing noise, binarizing the images, and segmenting individual characters.