Indexing of Document Images Based on Nine-Directional Codes

Abstract

In this paper, a new scheme of indexing and retrieval of document images based on B-tree is proposed. A new technique of labeling components in document images and also a document image representation technique based on nine-directional codes (NDC) are proposed. A procedure for classifying the retrieved images and a method of ranking the retrieved document images are also proposed. The retrieval results of the proposed NDC based indexing scheme are compared with the retrieval results of human experts. The experiments are conducted on the MediaTeam document image database that provides diverse collection of document images.