Clustering appearances of objects under varying illumination conditions
We introduce two appearance-based methods for clustering a set of images of 3D (three-
dimensional) objects, acquired under varying illumination conditions, into disjoint subsets …
dimensional) objects, acquired under varying illumination conditions, into disjoint subsets …
Object mining using a matching graph on very large image collections
J Philbin, A Zisserman - … on Computer Vision, Graphics & Image …, 2008 - ieeexplore.ieee.org
Automatic organization of large, unordered image collections is an extremely challenging
problem with many potential applications. Often, what is required is that images taken in the …
problem with many potential applications. Often, what is required is that images taken in the …
Color clustering techniques for color-content-based image retrieval from image databases
J Wang, WJ Yang, R Acharya - Proceedings of IEEE …, 1997 - ieeexplore.ieee.org
Image retrieval based on color content is an auxiliary function for traditional text-annotated
image databases. Most color-based image retrieval systems adopt color histograms as the …
image databases. Most color-based image retrieval systems adopt color histograms as the …
Interactive visual clustering of large collections of trajectories
One of the most common operations in exploration and analysis of various kinds of data is
clustering, ie discovery and interpretation of groups of objects having similar properties …
clustering, ie discovery and interpretation of groups of objects having similar properties …
Image browsing using hierarchical clustering
S Krishnamachari… - … Symposium on Computers …, 1999 - ieeexplore.ieee.org
Digital images and video clips are becoming popular due to the increase in the availability of
consumer devices that capture digital images and video clips. Digital content is also growing …
consumer devices that capture digital images and video clips. Digital content is also growing …
Applying the information bottleneck principle to unsupervised clustering of discrete and continuous image representations
Greenspan, Goldberger - Proceedings Ninth IEEE International …, 2003 - ieeexplore.ieee.org
We present a method for unsupervised clustering of image databases. The method is based
on a recently introduced information-theoretic principle, the information bottleneck (IB) …
on a recently introduced information-theoretic principle, the information bottleneck (IB) …
Spatially coherent clustering using graph cuts
R Zabih, V Kolmogorov - … of the 2004 IEEE Computer Society …, 2004 - ieeexplore.ieee.org
Feature space clustering is a popular approach to image segmentation, in which a feature
vector of local properties (such as intensity, texture or motion) is computed at each pixel. The …
vector of local properties (such as intensity, texture or motion) is computed at each pixel. The …
Affine invariance revisited
E Begelfor, M Werman - 2006 IEEE Computer Society …, 2006 - ieeexplore.ieee.org
This paper proposes a Riemannian geometric framework to compute averages and
distributions of point configurations so that different configurations up to affine …
distributions of point configurations so that different configurations up to affine …
Detection of buildings using perceptual grouping and shadows
Lin, Huertas, Nevatia - … of IEEE Conference on Computer Vision …, 1994 - ieeexplore.ieee.org
We describe a system for detection and description of buildings in aerial scenes. This is a
difficult task as the aerial images contain a variety of objects. Low-level segmentation …
difficult task as the aerial images contain a variety of objects. Low-level segmentation …
Mutual illumination
D Forsyth, A Zisserman - Proceedings CVPR'89: IEEE …, 1989 - ieeexplore.ieee.org
The authors report theoretical and experimental results which underline the importance of
mutual illumination to visual modules dealing with shape and with surface lightness. The …
mutual illumination to visual modules dealing with shape and with surface lightness. The …