Local Tetra Patterns: A New Feature Descriptor for Content-Based Image Retrieval

• Published in: IEEE transactions on image processing Vol. 21; no. 5; pp. 2874 - 2886
• Main Authors: Murala, S., Maheshwari, R. P., Balasubramanian, R.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.05.2012; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied sciences; Content-based image retrieval (CBIR); Data mining; Derivatives; Documentation - methods; Exact sciences and technology; Face recognition; Feature extraction; Gabor transform (GT); Heating; Horizontal; Image Enhancement - methods; Image Interpretation, Computer-Assisted - methods; Image processing; Image retrieval; Information Storage and Retrieval - methods; Information theory; Information, signal and communications theory; local binary pattern (LBP); local tetra patterns (LTrPs); Pattern Recognition, Automated - methods; Reproducibility of Results; Retrieval; Sensitivity and Specificity; Shape; Signal processing; Studies; Telecommunications and information theory; Texture; Performance evaluation; Content based retrieval; Image processing; Image retrieval; Gabor transformation; Image databank; local tetra patterns (LTrPs); Information retrieval; Algorithm; Texture; N order; Content-based image retrieval (CBIR); First order; Database; local binary pattern (LBP); Gabor transform (GT); Indexing
• ISSN: 1057-7149; 1941-0042; 1941-0042
• DOI: 10.1109/TIP.2012.2188809

In this paper, we propose a novel image indexing and retrieval algorithm using local tetra patterns (LTrPs) for content-based image retrieval (CBIR). 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. The proposed method encodes the relationship between the referenced pixel and its neighbors, based on the directions that are calculated using the first-order derivatives in vertical and horizontal directions. In addition, we propose a generic strategy to compute nth-order LTrP using (n - 1)th-order horizontal and vertical derivatives for efficient CBIR and analyze the effectiveness of our proposed algorithm by combining it with the Gabor transform. 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 databases viz., Corel 1000 database (DB1), Brodatz texture database (DB2), and MIT VisTex database (DB3). Performance analysis shows that the proposed method improves the retrieval result from 70.34%/44.9% to 75.9%/48.7% in terms of average precision/average recall on database DB1, and from 79.97% to 85.30% and 82.23% to 90.02% in terms of average retrieval rate on databases DB2 and DB3, respectively, as compared with the standard LBP.