A novel method for image retrieval based on structure elements’ descriptor

• Published in: Journal of visual communication and image representation Vol. 24; no. 1; pp. 63 - 74
• Main Authors: Wang, Xingyuan, Wang, Zongyu
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier Inc 01.01.2013; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Color descriptor; Computer science; control theory; systems; Content based image retrieval; Exact sciences and technology; HSV color space; Pattern recognition. Digital image processing. Computational geometry; Quantization color space; Structure elements’ descriptor; Structure elements’ histogram; Texton detection; Texture descriptor; Content based image retrieval; Texture descriptor; Structure elements’ descriptor; Texton detection; Quantization color space; Color descriptor; Structure elements’ histogram; HSV color space; Computer vision; Histogram; Statistical analysis; Image processing; Image retrieval; Spatial correlation; Structure elements' histogram; Structure elements' descriptor; Information retrieval; Texture; Color image; Image analysis; Signal quantization; Color space; Content-based retrieval
• ISSN: 1047-3203; 1095-9076
• DOI: 10.1016/j.jvcir.2012.10.003

► Structure elements’ descriptor (SED), a novel texture descriptor, is proposed. ► The image local features can effectively represented by SED. ► SED can extracting and describing color and texture features simultaneously. ► The image’s structure elements’ histogram (SEH) is proposed and computed by SED. ► SEH integrates the statistical and structural texture description method. In this paper, structure elements’ descriptor (SED) – a novel texture descriptor, is proposed. SED can effectively describe images and represent image local features. Moreover, SED can extract and describe color and texture features. The image structure elements’ histogram (SEH) is computed by SED, and HSV color space is used (it has been quantized to 72 bins). SEH integrates the advantages of both statistical and structural texture description methods, and it can represent the spatial correlation of color and texture. The results demonstrate that the method has a better performance than other image retrieval methods in the experiments.