Research on preprocessing and feature extraction methods for handwriting images based on Gabor texture learning

• Published in: 2023 IEEE 4th International Conference on Pattern Recognition and Machine Learning (PRML) pp. 259 - 262
• Main Authors: Amrurla, Guzalnur, Yadikar, Nurbiya, Ubul, Kurban
• Format: Conference Proceeding
• Language: English
• Published: IEEE 04.08.2023
• Subjects: Computer vision; Data integration; Feature extraction; Handwriting identification; Handwriting recognition; Machine learning; Preprocessing; Texture extraction; Transforms; Uyghur script; Writing
• DOI: 10.1109/PRML59573.2023.10348291

Handwriting recognition is a science and technology that uses machines to analyze the differences in handwriting styles to determine the identity of the writer. In the fields of computer vision and pattern recognition, handwriting recognition technology has also received increasing attention and research from experts and scholars. At the same time, the Uyghur handwriting recognition technology is still in its early stages, and the research on Uyghur handwriting recognition methods is of great significance. In this paper, research work was mainly concened with off-line Uyghur handwriting identification method, with special attention is given basically in handwriting image preprocessing and feature extraction concerning special handwriting character structure using Gabor transform method. Main objective is to evaluate and achieves Uyghur handwriting identification related algorithms and techniques and promote automation of the process.