Integration of wavelet transform,Local Binary Patterns and moments for content-based image retrieval |
| |
| Affiliation: | 1. Department of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, PR China;2. Department of Information Technology, Faculty of Information Technology, Egyptian E-Learning University, Dokki, Giza 12611, Egypt;3. Department of Electronics and Electrical Communications, Faculty of Electronic Engineering, Menoufia University, Menouf 32952, Egypt;1. School of Electrical & Electronic Engineering, Engineering Campus, Universiti Sains Malaysia, 14300 Nibong Tebal, Penang, Malaysia;2. Department of Electronic and Computer Engineering Technology, Faculty of Engineering Technology, Universiti Teknikal Malaysia Melaka, 76100 Durian Tunggal, Melaka, Malaysia;1. Dept. of Mathematics and Computer Science, University of Florence, Firenze, Italy;2. Dept. of Information Engineering, University of Florence, Firenze, Italy;3. FORLAB Multimedia Forensics Laboratory, University of Florence, Prato, Italy |
| |
| Abstract: | The proliferation of large number of images has made it necessary to develop systems for indexing and organizing images for easy access. This has made Content-Based Image Retrieval (CBIR) an important area of research in Computer Vision. This paper proposes a combination of features in multiresolution analysis framework for image retrieval. In this work, the concept of multiresolution analysis has been exploited through the use of wavelet transform. This paper combines Local Binary Pattern (LBP) with Legendre Moments at multiple resolutions of wavelet decomposition of image. First, LBP codes of Discrete Wavelet Transform (DWT) coefficients of images are computed to extract texture feature from image. The Legendre Moments of these LBP codes are then computed to extract shape feature from texture feature for constructing feature vectors. These feature vectors are used to search and retrieve visually similar images from large database. The proposed method has been tested on five benchmark datasets, namely, Corel-1K, Olivia-2688, Corel-5K, Corel-10K, and GHIM-10K, and performance of the proposed method has been measured in terms of precision and recall. The experimental results demonstrate that the proposed method outperforms some of the other state-of-the-art methods in terms of precision and recall. |
| |
| Keywords: | Image retrieval Discrete wavelet transform Local Binary Pattern Legendre moments |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
