A Survey of Feature Extraction and Classification Techniques Used In Character Recognition for Indian Scripts

The Constitution of India, under its Eight Schedule, has recognized Hindi (in Devanagari Script) and English as Official languages of Union Government, along with other 22 languages as Scheduled languages and given status and official encouragement to these Scheduled Languages. Most of the Optical recognition research work has been done on Devanagari, Telugu, and Bangla scripts etc. Development of OCR system for Indian scripts has many application areas like preservation of ancient manuscripts and literature written in different Indian scripts and making these available through digital libraries. Feature extraction and classification are the essential steps in the process of character recognition that affects the overall accuracy of the recognition system. This paper gives a detailed overview of feature extraction and classification techniques for the character recognition process of Indian scripts done in over past few decades.