A Novel Technique for Fast Content-Based Image Retrieval using Dual-Cross Patterns

Abstract

This proposed work introduces a novel technique for Fast Content-Based Image Retrieval (CBIR) using Dual-Cross Patterns (DCP). DCP encodes second order information in the vertical, horizontal and diagonal direction, by performing the encoding of sample points in the local surrounding region of every center pixel in an image. The local binary pattern (LBP), an efficient visual texture descriptor, performs a comparison between the center pixel and its neighboring pixel. Local tetra patterns (LTrP) is a method which acquires more detailed information by using four possible directions of every center pixel in an image, and is calculated from firstorder derivatives in horizontal and vertical directions. To analyze its effectiveness, the proposed technique, LBP, and LTrP are compared. Our extensive simulation on Corel database shows that the proposed technique has better time complexity compared to these methods.