State of the art in shape matching

RC Veltkamp, M Hagedoorn - Principles of visual information retrieval, 2001 - Springer
Large image databases are used in an extraordinary number of multimedia applications in
fields such as entertainment, business, art, engineering, and science. Retrieving images by …

Object recognition in the geometric era: A retrospective

JL Mundy - Toward category-level object recognition, 2006 - Springer
Recent advances in object recognition have emphasized the integration of intensity-derived
features such as affine patches with associated geometric constraints leading to impressive …

Seeing 3d chairs: exemplar part-based 2d-3d alignment using a large dataset of cad models

M Aubry, D Maturana, AA Efros… - Proceedings of the …, 2014 - openaccess.thecvf.com
This paper poses object category detection in images as a type of 2D-to-3D alignment
problem, utilizing the large quantities of 3D CAD models that have been made publicly …

[图书][B] Image and brain: The resolution of the imagery debate

SM Kosslyn - 1996 - books.google.com
This long-awaited work by prominent Harvard psychologist Stephen Kosslyn integrates a
twenty-year research program on the nature of high-level vision and mental imagery. Image …

On-line fingerprint verification

A Jain, L Hong, R Bolle - IEEE transactions on pattern analysis …, 1997 - ieeexplore.ieee.org
Fingerprint verification is one of the most reliable personal identification methods. However,
manual fingerprint verification is incapable of meeting today's increasing performance …

An identity-authentication system using fingerprints

AK Jain, L Hong, S Pankanti, R Bolle - Proceedings of the IEEE, 1997 - ieeexplore.ieee.org
Fingerprint verification is an important biometric technique for personal identification. We
describe the design and implementation of a prototype automatic identity-authentication …

[PDF][PDF] Fitting parameterized three-dimensional models to images

DG Lowe - IEEE transactions on pattern analysis and machine …, 1991 - faculty.nps.edu
Abstract Model-based recognition and motion tracking depends upon the ability to solve for
projection and model parameters that will best fit a 3-D model to matching 2-D image …

A tensor-based algorithm for high-order graph matching

O Duchenne, F Bach, IS Kweon… - IEEE transactions on …, 2011 - ieeexplore.ieee.org
This paper addresses the problem of establishing correspondences between two sets of
visual features using higher order constraints instead of the unary or pairwise ones used in …

Nondeterministic space is closed under complementation

N Immerman - SIAM Journal on computing, 1988 - SIAM
In this paper we show that nondeterministic space s(n) is closed under complementation for
s(n) greater than or equal to \logn. It immediately follows that the context-sensitive …

Visual object recognition

I Biederman - 1995 - direct.mit.edu
Try this experiment. Turn on your television with the sound off. Now change channels with
your eyes closed. At each new channel, blink quickly. As the picture appears, you will …