Image Retrieval Using Spatial Dominant Color Descriptor
Imen Ben Rejeb, Sonia Ouni, Ezzeddine Zagrouba · 2017
Color is one of the most important and widely used low-level features in content analysis and retrieval. However, most proposed color descriptors lack the spatial information about color distribution. The majorities of proposed solutions, which incorporate spatial information to color descriptors, are pixel based approach and adopt the static quantization. To alleviate these aforementioned drawbacks, we propose a top-down descriptor called the Spatial Dominant Color Descriptor (SDCD). In the extraction of dominant colors, we adopt a dynamic quantization by Gaussian Mixture Models (GMMs). The number of dominant colors is determined automatically using the Bayesian Information Criterion (BIC). The spatial proprieties of each color are described by the dispersion factor. we adopt the penalty trio-model in order to compare images during retrieval. The experimental results prove the high effectiveness and feasibility of the proposed descriptor, through Corel database.