Pose Invariant Generic Object Recognition with Orthogonal Axis Manifolds in Linear Subspace
This paper addresses the problem of pose invariant Generic Object Recognition by modeling the perceptual capability of human beings. We propose a novel framework using a combination of appearance and shape cues to recognize the object class and viewpoint (axis of rotation) as well as determine its pose (angle of view). The appearance model of the object from multiple viewpoints is captured using Linear Subspace Analysis techniques and is used to reduce the search space to a few rank-ordered candidates. We have used a decision-fusion based combination of 2D PCA and ICA to integrate the complementary information of classifiers and improve recognition accuracy. For matching based on shape features, we propose the use of distance transform based correlation. A decision fusion using ‘Sum Rule’ of 2D PCA and ICA subspace classifiers, and distance transform based correlation is then used to verify the correct object class and determine its viewpoint and pose. Experiments were conducted on COIL-100 and IGOIL (IITM Generic Object Image Library) databases which contain objects with complex appearance and shape characteristics. IGOIL database was captured to analyze the appearance manifolds along two orthogonal axes of rotation.
KeywordsObject Recognition Recognition Rate Recognition Accuracy Appearance Model Orthogonal Axis
Unable to display preview. Download preview PDF.
- 3.Rosin, P.L., Marshall, D.: Object recognition using local affine frames on distinguished regions. In: Proceedings of the British Machine Vision Conference, London, UK, pp. 113–122 (2002)Google Scholar
- 4.Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial Constraints. International Journal of Computer Vision 66 (2006)Google Scholar
- 8.Zhang, H., Berg, A., Mair, M., Malik, J.: SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition. Computer Vision and Pattern Recognition 2, 2126–2136 (2006)Google Scholar
- 10.Bohm, J., Bernner, C., Guhring, J., Fritsch, D.: Automated Extraction of features from CAD models for 3-D object recognition. In: International Society for Photogrammetry and Remote Sensing Congress, Amsterdam, Netherlands, vol. 33 (2000)Google Scholar
- 16.Sanjay, M., Das, S., Yegnanarayana, B.: Robust Template Matching for noisy bitmap images invariant to translation and rotation. In: Indian Conference on Computer Vision, Graphics and Image Processing, New Delhi, India, pp. 82–84 (1998)Google Scholar
- 17.Nene, S.A., Nayar, S.K., Murase, H.: COIL 100 Database (1996), http://www1.cs.columbia.edu/CAVE/research/softlib/coil-100.html
- 18.Kalra, M., Das, S.: IITM Generic Object Image Library (2006), http://vplab.cs.iitm.ernet.in/downloads.html
- 19.Rother, C., Kolomogorov, V., Blake, A.: GrabCut- Interactive Foreground extraction using iterated Graph Cuts. ACM transactions on Graphics (SIGGRAPH), 309–314 (2004)Google Scholar