Title :
A fast retrieval method for image features
Author :
Lee, Jae Yeon ; Jeong, Se-Yoon ; Kim, Kyu Heon ; Chun, Byung Tae ; Bae, Younglae J.
Author_Institution :
Dept. of Image Process., ETRI-Comput. & Software Technol. Lab., Taejon, South Korea
Abstract :
With a very large size image database, there should be a way to search for the similar images efficiently. However, the traditional approaches that have been adopted to retrieve text or scalar values cannot be used because of the multi-dimensionality of the image feature vectors. A new retrieval method that uses one or more scalar values induced from the image vector is proposed. In the proposed method, the scalar values are independently stored as indices to the target feature vectors. With the proposed method, the searching speed is improved approximately 25 times compared to the sequential searching
Keywords :
content-based retrieval; feature extraction; search problems; visual databases; content-based retrieval; fast retrieval method; image database; image feature vectors; image features; scalar values; searching speed; sequential searching; similar images; Content based retrieval; Electronic mail; Image databases; Image processing; Image recognition; Image retrieval; Information retrieval; Laboratories; Spatial databases; Tree data structures;
Conference_Titel :
TENCON 99. Proceedings of the IEEE Region 10 Conference
Conference_Location :
Cheju Island
Print_ISBN :
0-7803-5739-6
DOI :
10.1109/TENCON.1999.818480
