Title :
Saliency Aware Locality-preserving Coding for Image Classification
Author :
Fang, Quan ; Sang, Jitao ; Xu, Changsheng
Author_Institution :
Nat. Lab. of Pattern Recognition, Inst. of Autom., Beijing, China
Abstract :
The Bag-of-Features (BOF) model is widely used for image classification. Most BOF models incorporate a step of maximum pooling to generate the raw image representation, where salient atoms with maximum response are reserved for final representation. However, recent locality-preserving coding schemes do not account for the saliency characteristic during the process of generating the raw image representations. In this paper, we propose a saliency aware locality-preserving coding scheme by explicitly considering saliency into the dictionary creation and feature coding stages. The novel coding scheme guarantees strong response in the pooling operation and thus contributes to a discriminative image representation. Experiments on three benchmark datasets validate the effectiveness of the proposed method.
Keywords :
image classification; image coding; image representation; bag-of-features model; dictionary creation; feature coding; image classification; image representations; maximum response; saliency aware locality-preserving coding; saliency characteristic; Dictionaries; Encoding; Feature extraction; Image coding; Image representation; Kernel; Vectors; Image Representation and Classification; Locality-preserving; Saliency;
Conference_Titel :
Multimedia and Expo (ICME), 2012 IEEE International Conference on
Conference_Location :
Melbourne, VIC
Print_ISBN :
978-1-4673-1659-0
DOI :
10.1109/ICME.2012.164