Document Type

Article

Journal/Book Title/Conference

Expert Systems with Applications

Volume

127

Publisher

Elsevier

Publication Date

8-1-2019

First Page

1

Last Page

22

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Abstract

In this paper, we present two approaches to extract discriminative features for color image retrieval. The proposed local texture descriptors, based on Radial Mean Local Binary Pattern (RMLBP), are called Color RMCLBP (CRMCLBP) and Prototype Data Model (PDM). RMLBP is a robust to noise descriptor which has been proposed to extract texture features of gray scale images for texture classification.

For the first descriptor, the Radial Mean Completed Local Binary Pattern is applied to channels of the color space, independently. Then, the final descriptor is achieved by concatenating the histogram of the CRMCLBP_S/M/C component of each channel. Moreover, to enhance the performance of the proposed method, the Particle Swarm Optimization (PSO) algorithm is used for feature weighting.

The second proposed descriptor, PDM, uses the three outputs of CRMCLBP (CRMCLBP_S, CRMCLBP_M, CRMCLBP_C) as discriminative features for each pixel of a color image. Then, a set of representative feature vectors are selected from each image by applying k-means clustering algorithm. This set of selected prototypes are compared by means of a new similarity measure to find the most relevant images. Finally, the weighted versions of PDM is constructed using PSO algorithm.

Our proposed methods are tested on Wang, Corel-5k, Corel-10k and Holidays datasets. The results show that our proposed methods makes an admissible tradeoff between speed and retrieval accuracy. The first descriptor enhances the state-of-the-art color texture descriptors in both aspects. The second one is a very fast retrieval algorithm which extracts discriminative features.

Share

COinS