Recognition of printed Oriya script using gradient based features

Development of Optical Character Recognition (OCR) system for Indian script is an active area of research today. In this paper, 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 which includes similar looking and compound characters. This paper presents the gradient features based approaches for character recognition of printed Oriya script. For this, Histogram of Oriented Gradient (HOG) and Scale Invariant Feature Transform (SIFT) have been used to extract features from each individual character to uniquely identify it. Support Vector Machine (SVM) classifier, Brute Force (BF) Matcher and the Artificial Neural Network (ANN) have been used for efficient recognition. The performance of each approach for character recognition is discussed based on their input parameters and performance metric. It was found that when HOG features were classified using ANN, it outperforms over other approaches.