N
Nic Pillow
Researcher at University of Oxford
Publications - 5
Citations - 239
Nic Pillow is an academic researcher from University of Oxford. The author has contributed to research in topics: Invariant (mathematics) & 3D single-object recognition. The author has an hindex of 5, co-authored 5 publications receiving 235 citations.
Papers
More filters
Journal ArticleDOI
3D object recognition using invariance
TL;DR: The systems and concepts described in this paper document the evolution of the geometric invariance approach to object recognition over the last five years and provide a principled basis for the other stages of the recognition process such as feature grouping and hypothesis verification.
Proceedings ArticleDOI
Class-based grouping in perspective images
Andrew Zisserman,Joseph L. Mundy,David Forsyth,J. Liu,Nic Pillow,Charlie Rothwell,Sven Utcke +6 more
TL;DR: The key idea here is that a geometric class defined in 3D induces relationships in the image which must hold between points on the image outline (the perspective projection of the object) to enable both identification and grouping of image features belonging to objects of that class.
Journal ArticleDOI
Viewpoint-invariant representation of generalized cylinders using the symmetry set
TL;DR: It is demonstrated that viewpoint-invariant representations can be obtained from images for a useful class of 3D smooth object, which includes canal surfaces and surfaces of revolution, and are used as the basis for a model-based object recognition system.
Book ChapterDOI
An Experimental Comparison of Appearance and Geometric Model Based Recognition
Joseph L. Mundy,A. Liu,Nic Pillow,Andrew Zisserman,Samer M. Abdallah,Sven Utcke,Shree K. Nayar,Charlie Rothwell +7 more
TL;DR: An experimental investigation of the recognition performance of two approaches to the representation of objects for recognition by constructing an eigenvector space to compute efficiently the distance between a new image and any image in the database.
Proceedings ArticleDOI
Viewpoint-invariant representation of generalized cylinders using the symmetry set
TL;DR: It is demonstrated that viewpoint-invariant representations can be obtained from images for a useful class of 3D smooth object, which includes canal surfaces and surfaces of revolution, and are used as the basis for a model-based object recognition system.