DocumentCode :
2694514
Title :
Object retrieval based on spatially frequent items with informative patches
Author :
Gao, Ke ; Lin, Shouxun ; Guo, Junbo ; Zhang, Dongming ; Zhang, Yongdong ; Wu, Yufeng
Author_Institution :
Key Lab. of Intell. Inf. Process., Chinese Acad. of Sci., Beijing
fYear :
2008
fDate :
June 23 2008-April 26 2008
Firstpage :
1305
Lastpage :
1308
Abstract :
Spatial relation of local image patches plays an important role in object-based image retrieval. An approach called spatial frequent items is proposed as an extension of Bag-of-Words method by introducing spatial relations between patches. Spatial frequent items are defined as frequent pairs of adjacent local image patches in polar coordinates, and exploited using data mining. Based on these frequent configurations, we develop a method to encode patches and their spatial relations for image indexing and retrieval. Besides, to avoid the interference of background patches, informative patches are filtrated based on their local entropy and self-similarity in the preprocess stage. Experimental results demonstrate that our method can be 8.6% more effective than the state-of-art object retrieval methods.
Keywords :
data mining; database indexing; entropy codes; filtering theory; image coding; image retrieval; object detection; visual databases; Bag-of-Words method; data mining; filtering theory; image coding; image indexing; image retrieval; local entropy; local image patch; object retrieval; spatial frequent item; spatial relation; Computers; Content based retrieval; Data mining; Image retrieval; Image segmentation; Information processing; Information retrieval; Laboratories; Object detection; Vocabulary; Informative patches; Object retrieval; Spatial frequent items;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo, 2008 IEEE International Conference on
Conference_Location :
Hannover
Print_ISBN :
978-1-4244-2570-9
Electronic_ISBN :
978-1-4244-2571-6
Type :
conf
DOI :
10.1109/ICME.2008.4607682
Filename :
4607682
Link To Document :
بازگشت