131
Voted
ICIP
2007
IEEE
16 years 4 months ago
2007
IEEE
Abstract - The proposed algorithm in this work provides superresolution for color images by using a learning based technique that utilizes both generative and discriminant approach...
ICIP
2007
IEEE
16 years 4 months ago
2007
IEEE
We show that using a nonconvex penalty term to regularize image reconstruction can substantially improve the preservation of object shapes. The commonly-used total-variation regul...
96
Voted
ICIP
2007
IEEE
16 years 4 months ago
2007
IEEE
141
Voted
ICIP
2007
IEEE
16 years 4 months ago
2007
IEEE
Interest in face recognition systems has increased significantly due to the emergence of significant commercial opportunities in surveillance and security applications. In this pa...
128
Voted
ICIP
2007
IEEE
16 years 4 months ago
2007
IEEE
In image retrieval scenarios, many methods use interest point detection at an early stage to find regions in which descriptors are calculated. Finding salient locations in image d...
121
Voted
ICIP
2007
IEEE
16 years 4 months ago
2007
IEEE
This paper presents a probabilistic framework for computing correspondences and fundamental matrix in the structure from motion problem. Inspired by Moisan and Stival [1], we sugg...
117
click to vote
ICIP
2007
IEEE
16 years 4 months ago
2007
IEEE
A novel extension of phase correlation to subspace correlation is proposed, in which 2-D translation is decomposed into two 1-D motions thus only 1-D Fourier transform is used to ...
119
click to vote
ICIP
2007
IEEE
16 years 4 months ago
2007
IEEE
In this paper, we discuss the application of the two-dimensio- nal paired representation for processing medical images. This representation leads to the effective solution of the ...
125
Voted
ICIP
2007
IEEE
16 years 4 months ago
2007
IEEE
We propose a framework to learn statistical shape models for faces as piecewise linear models. Specifically, our methodology builds upon primitive active shape models(ASM) to hand...
157
click to vote
ICIP
2007
IEEE
16 years 4 months ago
2007
IEEE
The problem of human activity recognition via visual stimuli can be approached using manifold learning, since the silhouette (binary) images of a person undergoing a smooth motion...