Title :
A Region-Interactive Retrieval Model Based on IRM Algorithm
Author :
Tian, Yumin ; Wu, Zili ; Meng, Lina
Author_Institution :
Sch. of Comput. Sci., Xidian Univ., Xi´´an
Abstract :
In order to narrow the gap between the user´s implied concept and the low-level visual features, many region-based retrieval methods have been proposed. This paper describes a RBIR system. The system matches images based on user´s requirement with an improved integrated region similarity. To improve the retrieval performance, relevance feedback is introduced
Keywords :
feature extraction; image matching; image retrieval; relevance feedback; IRM algorithm; RBIR system; image matching; integrated region matching; region-interactive retrieval model; relevance feedback; user implied concept; visual feature; Clustering algorithms; Computer science; Content based retrieval; Feedback; Image retrieval; Image segmentation; Information retrieval; Iterative algorithms; Partitioning algorithms; Shape measurement; image segmentation; integrated region similarity; region matching; user´s interaction;
Conference_Titel :
Information, Communications and Signal Processing, 2005 Fifth International Conference on
Conference_Location :
Bangkok
Print_ISBN :
0-7803-9283-3
DOI :
10.1109/ICICS.2005.1689136
