PCA-SIFT: A more distinctive representation for local image descriptors
Y Ke, R Sukthankar - Proceedings of the 2004 IEEE Computer …, 2004 - ieeexplore.ieee.org
Stable local feature detection and representation is a fundamental component of many
image registration and object recognition algorithms. Mikolajczyk and Schmid (June 2003) …
image registration and object recognition algorithms. Mikolajczyk and Schmid (June 2003) …
Appearance-based face recognition and light-fields
Arguably the most important decision to be made when developing an object recognition
algorithm is selecting the scene measurements or features on which to base the algorithm …
algorithm is selecting the scene measurements or features on which to base the algorithm …
Statistical symmetric shape from shading for 3D structure recovery of faces
R Dovgard, R Basri - Computer Vision-ECCV 2004: 8th European …, 2004 - Springer
In this paper, we aim to recover the 3D shape of a human face using a single image. We use
a combination of symmetric shape from shading by Zhao and Chellappa and statistical …
a combination of symmetric shape from shading by Zhao and Chellappa and statistical …
Learning distance functions for image retrieval
Image retrieval critically relies on the distance function used to compare a query image to
images in the database. We suggest learning such distance functions by training binary …
images in the database. We suggest learning such distance functions by training binary …
Estimating intrinsic images from image sequences with biased illumination
We present a method for estimating intrinsic images from a fixed-viewpoint image sequence
captured under changing illumination directions. Previous work on this problem reduces the …
captured under changing illumination directions. Previous work on this problem reduces the …
Video based face recognition using multiple classifiers
The main advantage of the video based face recognition method is that more information is
available in a video sequence than in a single image. In order to take advantage of the large …
available in a video sequence than in a single image. In order to take advantage of the large …
Exploring face space
T Sim, S Zhang - 2004 Conference on Computer Vision and …, 2004 - ieeexplore.ieee.org
Face recognition is a difficult problem, whether using still images or video. A robust solution
is still elusive after 30 years of research. The main reason postulated for this is that two …
is still elusive after 30 years of research. The main reason postulated for this is that two …
[PDF][PDF] Image normalization by mutual information.
Image normalization refers to eliminating image variations (such as noise, illumination, or
occlusion) that are related to conditions of image acquisition and are irrelevant to object …
occlusion) that are related to conditions of image acquisition and are irrelevant to object …
An efficient illumination compensation scheme for face recognition
X Xie, KM Lam - … 2004 8th Control, Automation, Robotics and …, 2004 - ieeexplore.ieee.org
This paper proposes a novel illumination compensation algorithm, which can compensate
for the uneven illuminations on human faces and reconstruct face images of normal lighting …
for the uneven illuminations on human faces and reconstruct face images of normal lighting …
Whitening for photometric comparison of smooth surfaces under varying illumination
We consider the problem of image comparison in order to match smooth surfaces under
varying illumination. In a smooth surface nearby surface normals are highly correlated. We …
varying illumination. In a smooth surface nearby surface normals are highly correlated. We …