Robust fusion of color and local descriptors for image retrieval and classification

A. Alzu'bi, A. Amira, N. Ramzan, T. Jaber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)


This paper introduces an optimized image descriptor that combines both global and local features for image retrieval and classification. Color histograms in HSV space are extracted and quantized as global features, while root scale-invariant feature transform (rootSIFT) descriptors are densely extracted as local features. The extracted features are fused and reduced to obtain a lower-dimensional descriptor and discriminate the underlying variances of data. Image descriptors are encoded by the visual locally aggregated features (VLAD) approach. The Corel image dataset is used for evaluation and benchmarking. The experimental results show that the proposed descriptor improves the classification accuracy by 5% as well as the retrieval accuracy by 10% and 20% over rootSIFT and HSV, respectively. Additionally, the retrieval model outperforms many state-of-the-art approaches.
Original languageEnglish
Title of host publicationInternational Conference on Systems, Signals and Image Processing (IWSSIP), 2015
Number of pages4
ISBN (Print)9781467383530
Publication statusPublished - 2015


  • feature extraction
  • image classification
  • image colour analysis
  • image fusion
  • image retrieval
  • transforms
  • VLAD
  • color fusion
  • color histogram extraction
  • image descriptor
  • root scale-invariant feature transform
  • rootSIFT descriptor
  • visual locally aggregated feature
  • Accuracy
  • Histograms
  • Image color analysis
  • Kernel
  • Visualization
  • Color SIFT
  • Content-based image retrieval
  • Support vector machines
  • Vector of locally aggregated descriptors


Dive into the research topics of 'Robust fusion of color and local descriptors for image retrieval and classification'. Together they form a unique fingerprint.

Cite this