Proc. SPIE. 4301, Machine Vision Applications in Industrial Inspection IX
KEYWORDS: Principal component analysis, Statistical analysis, Error analysis, 3D modeling, Feature extraction, Performance modeling, Solid modeling, 3D image processing, Canonical correlation analysis, Simulation of CCA and DLA aggregates
We propose a new approach to building appearance models of 3D objects which is based on Canonical Correlation Analysis (CCA). In appearance based modeling, instead of building an explicit object model (e.g., 3D geometrical object model), a low dimensional object representation is obtained from a set of images. In standard appearance models typically Principal Component Analysis (PCA) is used for feature extraction. In our experiments we compare the performance of standard appearance models based on PCA and models based on CCA for 3D pose estimation. Results indicate that, while getting by with a smaller number linear features, CCA-based models perform consistently better.