Writer based handwritten document image retrieval using contourlet transform

Abstract

Many techniques have been reported for handwritten based document image retrieval. This paper proposes a novel method by using Contourlet Transform (CT) for feature extraction of document images which achieves high retrieval rate. The handwriting of different people is often visually distinctive; we take a global approach based on texture analysis, where each writer's handwriting is regarded as a different texture. The Canberra distance is used as similarity measure in proposed system. A retrieval result with proposed method is very promising with precision and recall as compared to the existing system. © 2011 Springer-Verlag.