—The subject of character recognition has received considerable attention in recent years. Character recognition is a process of converting handwritten or printed text images into machine readable code or text. Optical character recognition is used for many applications such as 1) Handwriting recognition systems, 2) Number plate recognition systems, 3) text recognition systems, 4) Data entry for business documents. In this, we are concerned with the recognition of printed Oriya script a popular Indian script. The development of OCR for this script is challenging as number of identified classes are more than 380. In the proposed approach, the digitized document image is first passed through preprocessing modules. The preprocessed data is segmented to the symbol level using horizontal and_ vertical projection profiling. The proposed approach use HOG feature extraction technique and SVM (Support Vector Machine) is used as a classifier. This approach is able to distinguishing between characters that have very similar shapes. A prototype of the system has been tested on a variety of printed Oriya material, and currently achieves 97.2% character level accuracy on average.
展开▼
