Unsupervised Joint Alignment of Complex Images
- 1 January 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Many recognition algorithms depend on careful positioning of an object into a canonical pose, so the position of features relative to a fixed coordinate system can be examined. Currently, this positioning is done either manually or by training a class-specialized learning algorithm with samples of the class that have been hand-labeled with parts or poses. In this paper, we describe a novel method to achieve this positioning using poorly aligned examples of a class with no additional labeling. Given a set of unaligned examplars of a class, such as faces, we automatically build an alignment mechanism, without any additional labeling of parts or poses in the data set. Using this alignment mechanism, new members of the class, such as faces resulting from a face detector, can be precisely aligned for the recognition process. Our alignment method improves performance on a face recognition task, both over unaligned images and over images aligned with a face alignment algorithm specifically developed for and trained on hand-labeled face images. We also demonstrate its use on an entirely different class of objects (cars), again without providing any information about parts or pose to the learning algorithm.Keywords
This publication has 11 references indexed in Scilit:
- Discriminative Training of Hyper-feature Models for Object IdentificationPublished by British Machine Vision Association and Society for Pattern Recognition ,2006
- Many Heads Are Better Than One: Jointly Removing Bias from Multiple MRIs Using Nonparametric Maximum LikelihoodPublished by Springer Nature ,2005
- Efficient Population Registration of 3D DataPublished by Springer Nature ,2005
- Names and faces in the newsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Face alignment under variable illuminationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Real-time view-based face alignment using active wavelet networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Multi-view face alignment using direct appearance modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Face recognition using eigenfacesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Learning from one example through shared densities on transformsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Eigenfaces vs. Fisherfaces: recognition using class specific linear projectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997