TY - JOUR
T1 - Curved glide-reflection symmetry detection
AU - Lee, Seungkyu
AU - Liu, Yanxi
N1 - Funding Information:
The authors would like to thank Loy and Eklundh [15] and Peng et al. [16] for their respective source code and Dr. K.C. Cheng for the zebrafish images. This work is supported in part by a PSU CTSA grant and a Northrop Grumman Gift grant to Yanxi Liu.
PY - 2012
Y1 - 2012
N2 - We generalize the concept of bilateral reflection symmetry to curved glide-reflection symmetry in 2D euclidean space, such that classic reflection symmetry becomes one of its six special cases. We propose a local feature-based approach for curved glide-reflection symmetry detection from real, unsegmented 2D images. Furthermore, we apply curved glide-reflection axis detection for curved reflection surface detection in 3D images. Our method discovers, groups, and connects statistically dominant local glide-reflection axes in an Axis-Parameter-Space (APS) without preassumptions on the types of reflection symmetries. Quantitative evaluations and comparisons against state-of-the-art algorithms on a diverse 64-test-image set and 1,125 Swedish leaf-data images show a promising average detection rate of the proposed algorithm at 80 and 40 percent, respectively, and superior performance over existing reflection symmetry detection algorithms. Potential applications in computer vision, particularly biomedical imaging, include saliency detection from unsegmented images and quantification of deviations from normality. We make our 64-test-image set publicly available.
AB - We generalize the concept of bilateral reflection symmetry to curved glide-reflection symmetry in 2D euclidean space, such that classic reflection symmetry becomes one of its six special cases. We propose a local feature-based approach for curved glide-reflection symmetry detection from real, unsegmented 2D images. Furthermore, we apply curved glide-reflection axis detection for curved reflection surface detection in 3D images. Our method discovers, groups, and connects statistically dominant local glide-reflection axes in an Axis-Parameter-Space (APS) without preassumptions on the types of reflection symmetries. Quantitative evaluations and comparisons against state-of-the-art algorithms on a diverse 64-test-image set and 1,125 Swedish leaf-data images show a promising average detection rate of the proposed algorithm at 80 and 40 percent, respectively, and superior performance over existing reflection symmetry detection algorithms. Potential applications in computer vision, particularly biomedical imaging, include saliency detection from unsegmented images and quantification of deviations from normality. We make our 64-test-image set publicly available.
UR - http://www.scopus.com/inward/record.url?scp=84055217865&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84055217865&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2011.118
DO - 10.1109/TPAMI.2011.118
M3 - Article
C2 - 21670486
AN - SCOPUS:84055217865
SN - 0162-8828
VL - 34
SP - 266
EP - 278
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 2
M1 - 5871648
ER -