A Histogram Descriptor Based on Co-occurrence Matrix and its Application in Cloud Image Indexing and Retrieval

It becomes an emergent challenge how to retrieve the cloud image from a gigantic cloud image database because of the fast accumulation of digital cloud images in meteorological area. This paper puts forward the histogram descriptor based on gray level co-occurrence matrices to depict the texture characteristics of cloud images, and then applies the histogram descriptor in content-based cloud image retrieval. Our experiment results shows that the proposed histogram descriptor outperforms the state-of-the-art texture features, such as Gabor, local binary pattern and moment descriptor of gray level co-occurrence matrix.