Self-Clustering Symmetry Detection

スポンサーリンク

概要

• 論文の詳細を見る

• This paper presents a self-clustering algorithm to detect symmetry in images. We combine correlations of orientations, scales and descriptors as a triple feature vector to evaluate each feature pair while low confidence pairs are regarded as outliers and removed. Additionally, all confident pairs are preserved to extract potential symmetries since one feature point may be shared by different pairs. Further, each feature pair forms one cluster and is merged and split iteratively based on the continuity in the Cartesian and concentration in the polar coordinates. Pseudo symmetric axes and outlier midpoints are eliminated during the process. Experiments demonstrate the robustness and accuracy of our algorithm visually and quantitatively.

• The Institute of Electronics, Information and Communication Engineersの論文
• 2012-09-01

著者

• WANG Guijin

  the Department of Electronic Engineering, Tsinghua University

• LIN Xinggang

  the Department of Electronic Engineering, Tsinghua University

• HE Bei

  the Dept. of Electronic Engineering, Tsinghua University

• HE Bei

  the Department of Electronic Engineering, Tsinghua University

• SHI Chenbo

  the Department of Electronic Engineering, Tsinghua University

• LIU Bo

  the Dept. of Electronic Engineering, Tsinghua University

• YIN Xuanwu

  the Dept. of Electronic Engineering, Tsinghua University

関連論文

• Partial Derivative Guidance for Weak Classifier Mining in Pedestrian Detection
• Drastic Anomaly Detection in Video Using Motion Direction Statistics
• An Interleaving Updating Framework of Disparity and Confidence Map for Stereo Matching
• Real Time Aerial Video Stitching via Sensor Refinement and Priority Scan
• Person Re-Identification by Spatial Pyramid Color Representation and Local Region Matching
• Self-Clustering Symmetry Detection

スポンサーリンク