Trainable 3D recognition using stereo matching

TitleTrainable 3D recognition using stereo matching
Publication TypeConference Papers
Year of Publication2011
AuthorsCastillo CD, Jacobs DW
Conference NameComputer Vision Workshops (ICCV Workshops), 2011 IEEE International Conference on
Date Published2011///
Keywords2D, 3D, class, classification, classification;image, data, dataset;CMU, dataset;face, descriptor;occlusion;pose, estimation;solid, image, image;3D, matching;pose, matching;trainable, modelling;stereo, object, PIE, processing;, recognition;face, recognition;image, set;3D, variation;stereo

Stereo matching has been used for face recognition in the presence of pose variation. In this approach, stereo matching is used to compare two 2-D images based on correspondences that reflect the effects of viewpoint variation and allow for occlusion. We show how to use stereo matching to derive image descriptors that can be used to train a classifier. This improves face recognition performance, producing the best published results on the CMU PIE dataset. We also demonstrate that classification based on stereo matching can be used for general object classification in the presence of pose variation. In preliminary experiments we show promising results on the 3D object class dataset, a standard, challenging 3D classification data set.