File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: Line correspondences between two images using local affine moment invariant
Title | Line correspondences between two images using local affine moment invariant |
---|---|
Authors | |
Keywords | Affine transformation Line matching Local affine moment invariant (AMI) |
Issue Date | 2005 |
Citation | 13Th International Conference In Central Europe On Computer Graphics, Visualization And Computer Vision 2005, Wscg'2005 - In Co-Operation With Eurographics, Full Papers, 2005, p. 129-132 How to Cite? |
Abstract | This paper proposes an algorithm for matching line segments between two images which are related by affine transformations using local affine moment invariant (AMI). Instead of using traditional methods for objection recognition in which each object is globally represented by a vector of affine moment invariants, here each pair of line segments extracted from each image is locally represented by an affine moment invariant. This algorithm is suitable for line correspondences with multi-planes and occlusion. Matches are determined through comparing invariant values and voting. Experimental results are given for both synthetic and real images. The noise model of affine moment invariant is also presented. Copyright UNION Agency - Science Press. |
Persistent Identifier | http://hdl.handle.net/10722/99820 |
References |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Chan, CH | en_HK |
dc.contributor.author | Hung, YS | en_HK |
dc.contributor.author | Leung, CH | en_HK |
dc.date.accessioned | 2010-09-25T18:45:28Z | - |
dc.date.available | 2010-09-25T18:45:28Z | - |
dc.date.issued | 2005 | en_HK |
dc.identifier.citation | 13Th International Conference In Central Europe On Computer Graphics, Visualization And Computer Vision 2005, Wscg'2005 - In Co-Operation With Eurographics, Full Papers, 2005, p. 129-132 | en_HK |
dc.identifier.uri | http://hdl.handle.net/10722/99820 | - |
dc.description.abstract | This paper proposes an algorithm for matching line segments between two images which are related by affine transformations using local affine moment invariant (AMI). Instead of using traditional methods for objection recognition in which each object is globally represented by a vector of affine moment invariants, here each pair of line segments extracted from each image is locally represented by an affine moment invariant. This algorithm is suitable for line correspondences with multi-planes and occlusion. Matches are determined through comparing invariant values and voting. Experimental results are given for both synthetic and real images. The noise model of affine moment invariant is also presented. Copyright UNION Agency - Science Press. | en_HK |
dc.language | eng | en_HK |
dc.relation.ispartof | 13th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision 2005, WSCG'2005 - In Co-operation with EUROGRAPHICS, Full Papers | en_HK |
dc.subject | Affine transformation | en_HK |
dc.subject | Line matching | en_HK |
dc.subject | Local affine moment invariant (AMI) | en_HK |
dc.title | Line correspondences between two images using local affine moment invariant | en_HK |
dc.type | Conference_Paper | en_HK |
dc.identifier.email | Hung, YS:yshung@eee.hku.hk | en_HK |
dc.identifier.email | Leung, CH:chleung@eee.hku.hk | en_HK |
dc.identifier.authority | Hung, YS=rp00220 | en_HK |
dc.identifier.authority | Leung, CH=rp00146 | en_HK |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.scopus | eid_2-s2.0-33645685687 | en_HK |
dc.identifier.hkuros | 101323 | en_HK |
dc.relation.references | http://www.scopus.com/mlt/select.url?eid=2-s2.0-33645685687&selection=ref&src=s&origin=recordpage | en_HK |
dc.identifier.spage | 129 | en_HK |
dc.identifier.epage | 132 | en_HK |
dc.identifier.scopusauthorid | Chan, CH=7404813577 | en_HK |
dc.identifier.scopusauthorid | Hung, YS=8091656200 | en_HK |
dc.identifier.scopusauthorid | Leung, CH=7402612415 | en_HK |