SIA OpenIR  > 光电信息技术研究室
An improved multi-scale autoconvolution transform
Shao CY(邵春燕); Ding QH(丁庆海); Luo HB(罗海波)
Department光电信息技术研究室
Conference NameInternational Symposium on Optoelectronic Technology and Application 2014
Conference DateMay 13-15, 2014
Conference PlaceBeijing, China
Source PublicationProc. Of SPIE 9301, International Symposium on Optoelectronic Technology and Application
PublisherSPIE
Publication PlaceBellingham, WA
2014
Pages1-7
Indexed ByEI ; CPCI(ISTP)
EI Accession number20150800551721
WOS IDWOS:000349327100071
Contribution Rank1
ISSN0277-786X
KeywordAffine Invariant Feature Multi-scale Autoconvolution N-domain Vectors Included Angle Map N-domain Vectors Angle Map
AbstractAffine invariant feature computing method is an important part of statistical pattern recognition due to the robustness, repeatability, distinguishability and wildly applicability of affine invariant feature. Multi-Scale Autoconvolution (MSA) is a transformation proposed by Esa Rathu which can get complete affine invariant feature. Rathu proved that the linear relationship of any four non-colinear points is affine invariant. The transform is based on a probabilistic interpretation of the image function. The performance of MSA transform is better on image occlusion and noise, but it is sensitive to illumination variation. Aim at this problem, an improved MSA transform is proposed in this paper by computing the map of included angle between N-domain vectors. The proposed method is based on the probabilistic interpretation of N-domain vectors included angle map. N-domain vectors included angle map is built through computing the vectors included angle where the vectors are composed of the image point and its N-domain image points. This is due to that the linear relationship of included angles between vectors composed of any four non-colinear points is an affine invariance. This paper proves the method can be derived in mathematical aspect. The transform values can be used as descriptors for affine invariant pattern classification. The main contribution of this paper is applying the N-domain vectors included angle map while taking the N-domain vector included angle as the probability of the pixel. This computing method adapts the illumination variation better than taking the gray value of the pixel as the probability. We illustrate the performance of improved MSA transform in various object classification tasks. As shown by a comparison with the original MSA transform based descriptors and affine invariant moments, the proposed method appears to be better to cope with illumination variation, image occlusion and image noise.
Language英语
Citation statistics
Cited Times:1[WOS]   [WOS Record]     [Related Records in WOS]
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/15335
Collection光电信息技术研究室
Affiliation1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China
2.University of Chinese Academy of Sciences, Beijing, China
3.Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Science, Shenyang, China
4.Research Institute of General Development and Demonstration of Equipment, Equipment of Air Force, Bejing, China
5.Key Lab of Image Understanding and Computer Vision, Liaoning province, Shenyang, China
Recommended Citation
GB/T 7714
Shao CY,Ding QH,Luo HB. An improved multi-scale autoconvolution transform[C]. Bellingham, WA:SPIE,2014:1-7.
Files in This Item: Download All
File Name/Size DocType Version Access License
An improved Multi-Sc(688KB) 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
[Shao CY(邵春燕)]'s Articles
[Ding QH(丁庆海)]'s Articles
[Luo HB(罗海波)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shao CY(邵春燕)]'s Articles
[Ding QH(丁庆海)]'s Articles
[Luo HB(罗海波)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shao CY(邵春燕)]'s Articles
[Ding QH(丁庆海)]'s Articles
[Luo HB(罗海波)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: An improved Multi-Scale Autoconvolution transform.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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