Moment-based symmetry detection for scene modeling and recognition using RGB-D images

• Published in: 2016 23rd International Conference on Pattern Recognition (ICPR) pp. 3621 - 3626
• Main Authors: Jui-Yuan Su, Shyi-Chyi Cheng, Jun-Wei Hsieh, Tzu-Hao Hsu
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2016
• Subjects: Algorithm design and analysis; Classification algorithms; Computational modeling; Detectors; Feature extraction; moment-based symmetry detection; part-based scene modeling; Reflection; RGB-D images; symmetric patch detection; Two dimensional displays; unsupervised feature representation
• DOI: 10.1109/ICPR.2016.7900196

In this paper we present a novel unsupervised feature representation by extracting salient symmetries in RGB-D images using the proposed moment-based symmetric patch detector. A fast indexing structure is also derived to group local symmetric patches into semantically meaningful symmetric parts. Given an RGB-D image, the hash-based symmetric patch indexing speeds up the searches of symmetric patch pairs, which are further grouped into symmetric parts with nearly linear time complexity. In the context of symmetry matching and scene classification, the second part of this work presents a symmetry-based scene modeling, aiming at computing a robust part-based feature set for each image category. To verify the effectiveness of the symmetry detector, based on the pre-learned part-based scene model, a part-based voting scheme is constructed to annotate the scene type of the input RGB-D image. Experimental results show that the proposed approach outperforms the compared methods in terms of detection and recognition accuracy using publicly available datasets.