Please use this identifier to cite or link to this item: https://doi.org/10.1109/TIP.2012.2218826
Title: Linear distance coding for image classification
Authors: Wang, Z.
Feng, J.
Yan, S. 
Xi, H.
Keywords: Image classification
image-to-class distance
linear distance coding (LDC)
Issue Date: 2013
Source: Wang, Z., Feng, J., Yan, S., Xi, H. (2013). Linear distance coding for image classification. IEEE Transactions on Image Processing 22 (2) : 537-548. ScholarBank@NUS Repository. https://doi.org/10.1109/TIP.2012.2218826
Abstract: The feature coding-pooling framework is shown to perform well in image classification tasks, because it can generate discriminative and robust image representations. The unavoidable information loss incurred by feature quantization in the coding process and the undesired dependence of pooling on the image spatial layout, however, may severely limit the classification. In this paper, we propose a linear distance coding (LDC) method to capture the discriminative information lost in traditional coding methods while simultaneously alleviating the dependence of pooling on the image spatial layout. The core of the LDC lies in transforming local features of an image into more discriminative distance vectors, where the robust image-to-class distance is employed. These distance vectors are further encoded into sparse codes to capture the salient features of the image. The LDC is theoretically and experimentally shown to be complementary to the traditional coding methods, and thus their combination can achieve higher classification accuracy. We demonstrate the effectiveness of LDC on six data sets, two of each of three types (specific object, scene, and general object), i.e., Flower 102 and PFID 61, Scene 15 and Indoor 67, Caltech 101 and Caltech 256. The results show that our method generally outperforms the traditional coding methods, and achieves or is comparable to the state-of-the-art performance on these data sets. © 1992-2012 IEEE.
Source Title: IEEE Transactions on Image Processing
URI: http://scholarbank.nus.edu.sg/handle/10635/56496
ISSN: 10577149
DOI: 10.1109/TIP.2012.2218826
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

SCOPUSTM   
Citations

39
checked on Jan 17, 2018

WEB OF SCIENCETM
Citations

26
checked on Dec 5, 2017

Page view(s)

24
checked on Jan 14, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.