A new color-texture feature descriptor for image retrieval

• Main Authors: Pei-Shan Tsai, 蔡佩珊
• Other Authors: Chung-Ming Kuo
• Format: Others
• Language: zh-TW
• Published: 2010
• Online Access: http://ndltd.ncl.edu.tw/handle/64949700314529962371

碩士 === 義守大學 === 資訊工程學系碩士班 === 98 === As the growing image database, to manage the database effectively is more and more important. CBIR (content-based image retrieval) is the well known systems with content-based image retrieval, and it has been widely adopted in Multimedia database. For imaging features, color and texture those are the most compatible feature with human vision. Therefore, they are usually selected as descriptors to retrieve image in multimedia database. In this thesis, we proposed a method to combine color and texture feature for image retrieval. The color feature is extracted by Linear Block Algorithm (LBA), which is obtained by modifying of MPEG-7 dominant color quantization. Texture descriptor is extracted by using Wavelet Transform. The texture feature is in high frequency band and corresponding to dominant colors in low-low band. According to the simulation results, the new descriptor achieves satisfactory performance in image retrieval.