@inProceedings{
 title = {Multiscale autoconvolution histograms for affine invariant pattern recognition},
 type = {inProceedings},
 year = {2006},
 pages = {1059-1068},
 volume = {3},
 city = {Edinburgh, UK},
 id = {ddd746ba-869a-3b47-857a-aa10fef9bc57},
 created = {2019-11-19T13:01:14.433Z},
 file_attached = {false},
 profile_id = {bddcf02d-403b-3b06-9def-6d15cc293e20},
 group_id = {17585b85-df99-3a34-98c2-c73e593397d7},
 last_modified = {2019-11-19T13:46:35.516Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {mvg:738},
 source_type = {inproceedings},
 private_publication = {false},
 abstract = {In this paper we present a new way of producing affine invariant histograms
from images. The approach is based on a probabilistic interpretation of the
image function as in the multiscale autoconvolution (MSA) transform, but
the histograms extract much more information of the image than traditional
MSA. The new histograms can be considered as generalizations of the image
gray scale histogram, encoding also the spatial information. It turns out
that the proposed method can be efficiently computed using the Fast Fourier
Transform, and it will be shown to have essentially the same computational
load as MSA. The experiments performed indicate that the new invariants are
capable of reliable classification of complex patterns, outperforming MSA
and many other methods.},
 bibtype = {inProceedings},
 author = {Rahtu E, Salo M & Heikkilä J},
 booktitle = {Proc. the 16th British Machine Vision Conference (BMVC 2006)}
}

{"_id":"B2nHaPP3aAJjXwuS8","bibbaseid":"rahtue-multiscaleautoconvolutionhistogramsforaffineinvariantpatternrecognition-2006","authorIDs":[],"author_short":["Rahtu E, S., M., &., H., J."],"bibdata":{"title":"Multiscale autoconvolution histograms for affine invariant pattern recognition","type":"inProceedings","year":"2006","pages":"1059-1068","volume":"3","city":"Edinburgh, UK","id":"ddd746ba-869a-3b47-857a-aa10fef9bc57","created":"2019-11-19T13:01:14.433Z","file_attached":false,"profile_id":"bddcf02d-403b-3b06-9def-6d15cc293e20","group_id":"17585b85-df99-3a34-98c2-c73e593397d7","last_modified":"2019-11-19T13:46:35.516Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"mvg:738","source_type":"inproceedings","private_publication":false,"abstract":"In this paper we present a new way of producing affine invariant histograms\nfrom images. The approach is based on a probabilistic interpretation of the\nimage function as in the multiscale autoconvolution (MSA) transform, but\nthe histograms extract much more information of the image than traditional\nMSA. The new histograms can be considered as generalizations of the image\ngray scale histogram, encoding also the spatial information. It turns out\nthat the proposed method can be efficiently computed using the Fast Fourier\nTransform, and it will be shown to have essentially the same computational\nload as MSA. The experiments performed indicate that the new invariants are\ncapable of reliable classification of complex patterns, outperforming MSA\nand many other methods.","bibtype":"inProceedings","author":"Rahtu E, Salo M & Heikkilä J","booktitle":"Proc. the 16th British Machine Vision Conference (BMVC 2006)","bibtex":"@inProceedings{\n title = {Multiscale autoconvolution histograms for affine invariant pattern recognition},\n type = {inProceedings},\n year = {2006},\n pages = {1059-1068},\n volume = {3},\n city = {Edinburgh, UK},\n id = {ddd746ba-869a-3b47-857a-aa10fef9bc57},\n created = {2019-11-19T13:01:14.433Z},\n file_attached = {false},\n profile_id = {bddcf02d-403b-3b06-9def-6d15cc293e20},\n group_id = {17585b85-df99-3a34-98c2-c73e593397d7},\n last_modified = {2019-11-19T13:46:35.516Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {mvg:738},\n source_type = {inproceedings},\n private_publication = {false},\n abstract = {In this paper we present a new way of producing affine invariant histograms\nfrom images. The approach is based on a probabilistic interpretation of the\nimage function as in the multiscale autoconvolution (MSA) transform, but\nthe histograms extract much more information of the image than traditional\nMSA. The new histograms can be considered as generalizations of the image\ngray scale histogram, encoding also the spatial information. It turns out\nthat the proposed method can be efficiently computed using the Fast Fourier\nTransform, and it will be shown to have essentially the same computational\nload as MSA. The experiments performed indicate that the new invariants are\ncapable of reliable classification of complex patterns, outperforming MSA\nand many other methods.},\n bibtype = {inProceedings},\n author = {Rahtu E, Salo M & Heikkilä J},\n booktitle = {Proc. the 16th British Machine Vision Conference (BMVC 2006)}\n}","author_short":["Rahtu E, S., M., &., H., J."],"bibbaseid":"rahtue-multiscaleautoconvolutionhistogramsforaffineinvariantpatternrecognition-2006","role":"author","urls":{},"downloads":0},"bibtype":"inProceedings","creationDate":"2019-11-19T13:17:06.493Z","downloads":0,"keywords":[],"search_terms":["multiscale","autoconvolution","histograms","affine","invariant","pattern","recognition","rahtu e"],"title":"Multiscale autoconvolution histograms for affine invariant pattern recognition","year":2006}