TY - JOUR
T1 - Image stitching using chaos-inspired dissimilarity measure
AU - Song, Taeyup
AU - Jeon, Changwon
AU - Ko, Hanseok
N1 - Publisher Copyright:
© The Institution of Engineering and Technology 2015.
Copyright:
Copyright 2015 Elsevier B.V., All rights reserved.
PY - 2015/2/5
Y1 - 2015/2/5
N2 - A novel image-stitching algorithm is proposed that uses the chaosinspired dissimilarity measure. Previous approaches to image stitching generally employed invariant local features and random sample consensus (RANSAC), to verify image matches. In panoramic stitching, however, RANSAC is highly sensitive to illumination difference between the pair of images stemming from two different exposures, which essentially results in mismatched pairs, leading to poor stitching performance. By applying chaos theory, the contextual change of an image becomes chaos-like, and results in a complex fractal trajectory in phase space. The specific chaos behaviour between a pair of images is exploited, whereby the resulting phase space exhibits strong invariance to illumination changes. Accordingly, the chaosinspired dissimilarity between images is measured, thereby the matched pairs are robustly found under the presence of illumination difference. Representative performance experiments demonstrate significant improvements over the conventional method.
AB - A novel image-stitching algorithm is proposed that uses the chaosinspired dissimilarity measure. Previous approaches to image stitching generally employed invariant local features and random sample consensus (RANSAC), to verify image matches. In panoramic stitching, however, RANSAC is highly sensitive to illumination difference between the pair of images stemming from two different exposures, which essentially results in mismatched pairs, leading to poor stitching performance. By applying chaos theory, the contextual change of an image becomes chaos-like, and results in a complex fractal trajectory in phase space. The specific chaos behaviour between a pair of images is exploited, whereby the resulting phase space exhibits strong invariance to illumination changes. Accordingly, the chaosinspired dissimilarity between images is measured, thereby the matched pairs are robustly found under the presence of illumination difference. Representative performance experiments demonstrate significant improvements over the conventional method.
UR - http://www.scopus.com/inward/record.url?scp=84922463490&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84922463490&partnerID=8YFLogxK
U2 - 10.1049/el.2014.0981
DO - 10.1049/el.2014.0981
M3 - Article
AN - SCOPUS:84922463490
SN - 0013-5194
VL - 51
SP - 232
EP - 234
JO - Electronics Letters
JF - Electronics Letters
IS - 3
ER -