CASIA OpenIR  > 09年以前成果
Local interaction fields and adaptive regularizers for surface reconstruction and image relaxation
Yang, ZY; Ma, SD
Source PublicationNETWORK-COMPUTATION IN NEURAL SYSTEMS
1998-02-01
Volume9Issue:1Pages:19-37
SubtypeArticle
AbstractA set of novel local interaction fields associated with input point data and adaptive regularizers are introduced for some problems in image processing and early-middle vision. The local interaction field is used to take the place of the delta-error term in conventional approaches. It consists of two parts; one is the usual error term, the other is a window function whose shape, size and orientation can be adapted to local structures in specific applications. Unlike the usual delta-error term, local interaction fields favour local flatness and thus impose smoothing implicitly. Several adaptive regularizers are introduced to keep discontinuities while smoothing. In finding solutions, even the simplest gradient descent algorithm is efficient in many examples. The results are stable under varying parameters and quite robust against noise.
WOS HeadingsScience & Technology ; Technology ; Life Sciences & Biomedicine
WOS KeywordRESTORATION
Indexed BySCI
Language英语
WOS Research AreaComputer Science ; Engineering ; Neurosciences & Neurology
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Neurosciences
WOS IDWOS:000072810100002
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/9776
Collection09年以前成果
AffiliationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100080, Peoples R China
Recommended Citation
GB/T 7714
Yang, ZY,Ma, SD. Local interaction fields and adaptive regularizers for surface reconstruction and image relaxation[J]. NETWORK-COMPUTATION IN NEURAL SYSTEMS,1998,9(1):19-37.
APA Yang, ZY,&Ma, SD.(1998).Local interaction fields and adaptive regularizers for surface reconstruction and image relaxation.NETWORK-COMPUTATION IN NEURAL SYSTEMS,9(1),19-37.
MLA Yang, ZY,et al."Local interaction fields and adaptive regularizers for surface reconstruction and image relaxation".NETWORK-COMPUTATION IN NEURAL SYSTEMS 9.1(1998):19-37.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yang, ZY]'s Articles
[Ma, SD]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yang, ZY]'s Articles
[Ma, SD]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yang, ZY]'s Articles
[Ma, SD]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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