TY - JOUR
T1 - Consumer photo management and browsing facilitated by near-duplicate detection with feature filtering
AU - Chu, Wei Ta
AU - Lin, Chia Hung
N1 - Funding Information:
This work was partially supported by the National Science Council of ROC under NSC 96-2218-E-194-005 and NSC 97-2221-E-194-050. The authors would like to thank anonymous reviewers for giving valuable comments.
PY - 2010/4
Y1 - 2010/4
N2 - Near-duplicate detection techniques are exploited to facilitate representative photo selection and region-of-interest (ROI) determination, which are important functionalities for efficient photo management and browsing. To make near-duplicate detection module resist to noisy features, three filtering approaches, i.e., point-based, region-based, and probabilistic latent semantic (pLSA), are developed to categorize feature points. For the photos taken in travels, we construct a support vector machine classifier to model matching patterns between photos and determine whether photos are near-duplicate pairs. Relationships between photos are then described as a graph, and the most central photo that best represents a photo cluster is selected according to centrality values. Because matched feature points are often located in the interior or at the contour of important objects, the region that compactly covers the matched feature points is determined as the ROI. We compare the proposed approaches with conventional ones and demonstrate their effectiveness.
AB - Near-duplicate detection techniques are exploited to facilitate representative photo selection and region-of-interest (ROI) determination, which are important functionalities for efficient photo management and browsing. To make near-duplicate detection module resist to noisy features, three filtering approaches, i.e., point-based, region-based, and probabilistic latent semantic (pLSA), are developed to categorize feature points. For the photos taken in travels, we construct a support vector machine classifier to model matching patterns between photos and determine whether photos are near-duplicate pairs. Relationships between photos are then described as a graph, and the most central photo that best represents a photo cluster is selected according to centrality values. Because matched feature points are often located in the interior or at the contour of important objects, the region that compactly covers the matched feature points is determined as the ROI. We compare the proposed approaches with conventional ones and demonstrate their effectiveness.
UR - http://www.scopus.com/inward/record.url?scp=77950050598&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77950050598&partnerID=8YFLogxK
U2 - 10.1016/j.jvcir.2010.01.006
DO - 10.1016/j.jvcir.2010.01.006
M3 - Article
AN - SCOPUS:77950050598
VL - 21
SP - 256
EP - 268
JO - Journal of Visual Communication and Image Representation
JF - Journal of Visual Communication and Image Representation
SN - 1047-3203
IS - 3
ER -