Title :
Image Auto-annotation with Graph Learning
Author :
Guo, Yu Tang ; Luo, Bin
Author_Institution :
Dept. of Comput. Sci. & Technol., Hefei Normal Univ., Hefei, China
Abstract :
It is important to integrate contextual information in order to improve the performance of automatic image annotation. Graph based representations allow incorporation of such information. In this paper, we propose a graph-based approach to automatic image annotation which models both feature similarities and semantic relations in a single graph. The annotation quality is enhanced by introducing graph link weighting techniques based on inverse document frequent and the similarity of the word based on Co-occurrence relation in the training set . According to the characteristics of in ear correlation, block-wise and community-like structure in the modeled graph, we divide the graph into several sub graphs and approximate high rank adjacent matrix of the graph by using low rank matrix. Thus, we can achieve image annotation quickly. Experimental results on the Corel image dabasets show the effectiveness of the proposed approach in terms of performance.
Keywords :
correlation methods; graphs; image classification; image retrieval; knowledge representation; learning (artificial intelligence); matrix algebra; automatic image annotation; contextual information; cooccurrence relation; corel image dabaset; graph based representation; graph learning; image auto annotation; inverse document; linear correlation; rank adjacent matrix; semantic relation; training set; weighting technique; Accuracy; Algorithm design and analysis; Complexity theory; Equations; Mathematical model; Semantics; Training; Random walk with restart; fast solution; graph learning; image annotation;
Conference_Titel :
Artificial Intelligence and Computational Intelligence (AICI), 2010 International Conference on
Conference_Location :
Sanya
Print_ISBN :
978-1-4244-8432-4
DOI :
10.1109/AICI.2010.171