Open AccessDESIGN OF MACHINE LEARNING MODEL FOR CHARACTER RECOGNITION
Author(s) -
Rituraj Jain
Publication year - 2021
Publication title -
information technology in industry/information technology in industry
Language(s) - English
Resource type - Journals
eISSN - 2204-0595
pISSN - 2203-1731
DOI - 10.17762/itii.v9i2.358
Subject(s) - character (mathematics) , artificial intelligence , computer science , feature selection , feature (linguistics) , identification (biology) , pattern recognition (psychology) , selection (genetic algorithm) , logistic regression , process (computing) , feature extraction , machine learning , natural language processing , mathematics , linguistics , philosophy , botany , geometry , biology , operating system
Hand written character recognition or text recognition is the ability of the system to identify character or text automatically. Documents can be in any form such as documents, photographs, touch-screens or other devices. Each character will have its own feature sets. The classification or identification of characters are done based on proper selection of feature sets. Feature selection is the major step for any classification process. The machine learning model is created based on feature sets. Logistic regression model is used in this model to identify different characters. 97.33% accuracy is achieved using logistic regression model compared to existing work.