DocumentCode :
535475
Title :
Voting conditional random fields for multi-label image classification
Author :
Wang, Xishun ; Liu, Xi ; Shi, Zhiping ; Shi, Zhongzhi ; Sui, Hongjian
Author_Institution :
Key Lab. of Intell. Inf. Process., Chinese Acad. of Sci., Beijing, China
Volume :
4
fYear :
2010
fDate :
16-18 Oct. 2010
Firstpage :
1984
Lastpage :
1988
Abstract :
In our real world, there usually exist several different objects in one image, which brings intractable challenges to the traditional pattern recognition methods to classify the images. In this paper, we introduce a Conditional Random Fields (CRFs) model to deal with the Multi-label Image Classification problem. Considering the correlations of the objects, a second-order CRFs is constructed to capture the semantic associations between labels. Different initial feature weights are set to introduce the voting techniques for a better performance. We evaluate our methods on MSRC dataset and demonstrate high precision, recall and F1 measure, showing that our method is competitive.
Keywords :
image classification; pattern recognition; random processes; CRF model; multilabel image classification; pattern recognition methods; voting conditional random fields; voting techniques; Buildings; Correlation; Image classification; Image segmentation; Semantics; Training; Visualization; Bag-of-Feature; Conditional Random Fields; Multi-label Classification; Voting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image and Signal Processing (CISP), 2010 3rd International Congress on
Conference_Location :
Yantai
Print_ISBN :
978-1-4244-6513-2
Type :
conf
DOI :
10.1109/CISP.2010.5648193
Filename :
5648193
Link To Document :
بازگشت