CASIA OpenIR  > 空天信息研究中心
Invariant representation for blur and down-sampling transformations
Gu HX(谷鹄翔)1; Leibo Joel2; Anselmi Fabio2; Chunhong Pan1; Tomaso Poggio2
2016
Conference NameIEEE International Conference on Image Processing
Source Publication2016 IEEE International Conference on Image Processing, 10.1109/ICIP.2016.7533029
Conference Date2016.09.25-2016.09.28
Conference PlacePhonex, Arizona, USA
AbstractInvariant representations of images can significantly reduce
the sample complexity of a classifier performing object identification
or categorization as shown in a recent analysis of
invariant representations for object recognition. In the case
of geometric transformations of images the theory [1] shows
how invariant signatures can be learned in a biologically plausible
way from unsupervised observations of the transformations
of a set of randomly chosen template images. Here we
extend the theory to non-geometric transformations such as
blur and down-sampling. The proposed algorithm achieve an
invariant representation via two simple biologically-plausible
steps: 1. compute normalized dot products of the input with
the stored transformations of each template, and 2. for each
template compute the statistics of the resulting set of values
such as the histogram or moments. The performance of our
system on challenging blurred and low resolution face matching
tasks exceeds the previous state-of-the-art by a large margin
which grows with increasing image corruption.
KeywordInvariance Representation Down-samppling
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/12034
Collection空天信息研究中心
Corresponding AuthorTomaso Poggio
Affiliation1.CASIA
2.MIT
Recommended Citation
GB/T 7714
Gu HX,Leibo Joel,Anselmi Fabio,et al. Invariant representation for blur and down-sampling transformations[C],2016.
Files in This Item: Download All
File Name/Size DocType Version Access License
blurInvariance_ICIP2(1180KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Gu HX(谷鹄翔)]'s Articles
[Leibo Joel]'s Articles
[Anselmi Fabio]'s Articles
Baidu academic
Similar articles in Baidu academic
[Gu HX(谷鹄翔)]'s Articles
[Leibo Joel]'s Articles
[Anselmi Fabio]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Gu HX(谷鹄翔)]'s Articles
[Leibo Joel]'s Articles
[Anselmi Fabio]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: blurInvariance_ICIP2016.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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