Paper Info
Title
Image Classification via Object-Aware Holistic Superpixel Selection
Abstract
In this paper, we propose an object-aware holistic superpixel selection (HPS) method to automatically select the discriminative superpixels of an image for image classification purpose. Through only considering the selected superpixels, the interference of cluttered background on the object can be alleviated effectively and thus the classification performance is significantly enhanced. In particular, for an image, HPS first selects the discriminative superpixels for the characteristics of certain class, which can together match the object template of this class well. In addition, these superpixels compose a class-specific matching region. Through performing such superpixel selection for several most probable classes, respectively, HPS generates multiple class-specific matching regions for a single image. Then, HPS merges these matching regions into an integral object region through exploiting their pixel-level intersection information. Finally, such object region instead of the original image is used for image classification. An appealing advantage of HPS is the ability to alleviate the interference of cluttered background yet not require the object to be segmented out accurately. We evaluate the proposed HPS on four challenging image classification benchmark datasets: Oxford-IIIT PET 37, Caltech-UCSD Birds 200, Caltech 101, and PASCAL VOC 2011. The experimental results consistently show that the proposed HPS can remarkably improve the classification performance.
Year
DOI
Venue
2013
10.1109/TIP.2013.2272514
IEEE Transactions on Image Processing
Keywords
Field
DocType
pascal voc 2011,holistic superpixel selection,object-aware,region mergence,image matching,object-aware holistic superpixel selection method,caltech 101,caltech-ucsd birds 200,cluttered background interference,object template,hps,oxford-iiit pet 37,pixel-level intersection information,image classification,clutter,multiple class-specific image matching region,interference,image classification benchmark dataset,image discriminative superpixel
Computer vision,Caltech 101,Pattern recognition,Image matching,Clutter,Computer science,Feature extraction,Image segmentation,Artificial intelligence,Interference (wave propagation),Contextual image classification,Discriminative model
Journal
Volume
Issue
ISSN
22
11
1941-0042
Citations 
PageRank 
References 
5
0.42
22
Authors
4
Name
Order
Citations
PageRank
Zilei Wang1788.06
Jiashi Feng22165140.81
Shuicheng Yan376725.71
Hongsheng Xi435738.39