CONTENT BASED IMAGE RETRIEVAL USING LOCAL TETRA PATTERN

摘要

Local tetra pattern (LTrP) is used for creating a new retrieval algorithm for managing the large databasc.It is necessary to develop appropriate information systems to efficiently manage these collections. The most relevant method to manage the large database is Content Based Image Retrieval (CBIR) system. The standard local binary pattern (LBP) and local ternary pattern (LTP) encode the relationship between the referenced pixel and its surrounding neighbors by computing gray-level difference. LTrP encodes the relationship between the referenced pixel and its neighbor pixel based on the directions that are calculated using the first-order derivatives in vertical and horizontal directions. It present a statistical view of the texture retrieval problem by combining the two related tasks, namely feature extraction (FE) and similarity measurement (SM). And also compute the nth order local tetra pattern using (n-1)th order in horizontal and vertical derivatives for efficient CBIR. The performance of the proposed method is compared with the LBP, the local derivative patterns, and the LTP based on the results obtained using benchmark image database. Performance analysis shows that the proposed method improves the retrieval result from 70.34% to 75.9% in terms of average precision and from 44.9% to 48.7% in terms of average recall and from 79.97% to 85.30% in terms of average retrieval rate respectively, as compared with the standard LBP.