Khmer Optical Character Recognition Using Zernike Moment
Porchourng Chuor, Michel Verleysen, Dona Valy · Digital Access to Libraries (Université catholique de Louvain (UCL), l'Université de Namur (UNamur) and the Université Saint-Louis (USL-B)) · 2015
In this paper, we focus on an Optical Character Recognition (OCR) system for printed text documents in Khmer language by using Zernike Moment. The Zernike Moment method is used as a feature extraction method to solve the recognition problem. We compute the moments from sub-characters to extract their feature vectors. The final recognition result is achieved by employing a classifier based on the Nearest Neighbor method. The method is experimented on 5 documents with font size of 12, 15, and 36 respectively.