Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Saliency Map-based Image Retrieval using Invariant Krawtchouk Moments

Ashkan Nejad, Mohammad Reza Faraji, Xiaojun Qi

TL;DR

A saliency map-based image retrieval approach using invariant Krawtchouk moments (SM-IKM) to enhance retrieval speed and accuracy, and demonstrates that SM-IKM outperforms recent state-of-the-art retrieval methods.

Abstract

With the widespread adoption of digital devices equipped with cameras and the rapid development of Internet technology, numerous content-based image retrieval systems and novel image feature extraction techniques have emerged in recent years. This paper introduces a saliency map-based image retrieval approach using invariant Krawtchouk moments (SM-IKM) to enhance retrieval speed and accuracy. The proposed method applies a global contrast-based salient region detection algorithm to create a saliency map that effectively isolates the foreground from the background. It then combines multiple orders of invariant Krawtchouk moments (IKM) with local binary patterns (LBPs) and color histograms to comprehensively represent the foreground and background. Additionally, it incorporates LBPs derived from the saliency map to improve discriminative power, facilitating more precise image differentiation. A bag-of-visual-words (BoVW) model is employed to generate a codebook for classification and discrimination. By using compact IKMs in the BoVW framework and integrating a range of region-based feature-including color histograms, LBPs, and saliency map-enhanced LBPs, our proposed SM-IKM achieves efficient and accurate image retrieval. Extensive experiments on publicly available datasets, such as Caltech 101 and Wang, demonstrate that SM-IKM outperforms recent state-of-the-art retrieval methods. The source code for SM-IKM is available at github.com/arnejad/SMIKM.

Saliency Map-based Image Retrieval using Invariant Krawtchouk Moments

TL;DR

A saliency map-based image retrieval approach using invariant Krawtchouk moments (SM-IKM) to enhance retrieval speed and accuracy, and demonstrates that SM-IKM outperforms recent state-of-the-art retrieval methods.

Abstract

With the widespread adoption of digital devices equipped with cameras and the rapid development of Internet technology, numerous content-based image retrieval systems and novel image feature extraction techniques have emerged in recent years. This paper introduces a saliency map-based image retrieval approach using invariant Krawtchouk moments (SM-IKM) to enhance retrieval speed and accuracy. The proposed method applies a global contrast-based salient region detection algorithm to create a saliency map that effectively isolates the foreground from the background. It then combines multiple orders of invariant Krawtchouk moments (IKM) with local binary patterns (LBPs) and color histograms to comprehensively represent the foreground and background. Additionally, it incorporates LBPs derived from the saliency map to improve discriminative power, facilitating more precise image differentiation. A bag-of-visual-words (BoVW) model is employed to generate a codebook for classification and discrimination. By using compact IKMs in the BoVW framework and integrating a range of region-based feature-including color histograms, LBPs, and saliency map-enhanced LBPs, our proposed SM-IKM achieves efficient and accurate image retrieval. Extensive experiments on publicly available datasets, such as Caltech 101 and Wang, demonstrate that SM-IKM outperforms recent state-of-the-art retrieval methods. The source code for SM-IKM is available at github.com/arnejad/SMIKM.

Paper Structure

This paper contains 14 sections, 21 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Salient Region Detection
  4. Invariant Krawtchouk Moments (IKMs)
  5. Saliency-based Multi-Feature Modeling (SMFM) Method
  6. Proposed Method
  7. Saliency Map and LBP Feature Extraction
  8. Patch Extraction Using SIFT and Invariant Krawtchouk Descriptor
  9. Multi-order SM-IKM and Its Two Variants
  10. Experimental Results
  11. Datasets
  12. Comparison of Several State-of-the-art CBIR methods
  13. Comparison of Computational Runtime
  14. Conclusion

Figures (3)

  • Figure 1: The focus zones of the multi-order IKM description on the Cameraman image, whose size is resized from 512x512 to 52x52 to better demonstrate the effect of the weight function on the small patches.
  • Figure 2: Data pipeline of the proposed SM-IKM method.
  • Figure 3: Comparison of the retrieval time (in minutes) of the top three methods for all 1000 images in the Wang dataset, which includes the feature description computation time (shown in blue) and the clustering time (shown in orange) into 100 vocabularies of the BoVM model.