Sciweavers

ICIP
2005
IEEE
15 years 1 months ago
High throughput 2D DCT/IDCT processor for video coding
This paper describes the architecture of an 8x8 2-D DCT/IDCT processor with high throughput, reduced hardware, and a parallel-pipeline scheme. This architecture allows the process...
Gustavo A. Ruiz, Juan A. Michell, Angel M. Buron
ICIP
2005
IEEE
15 years 1 months ago
Custom color enhancements by statistical learning
We consider the problem of automatically learning color enhancements from a small set of sample color pairs, and describing the enhancement by a three-dimensional look-uptable tha...
Maya R. Gupta
ICIP
2005
IEEE
15 years 1 months ago
Quality assessment using data hiding on perceptually important areas
In this paper, we present a no-reference video quality metric that blindly estimates the quality of a video. The proposed approach makes use of a data hiding technique to embed a ...
Marco Carli, Mylene Christine Queiroz de Farias, E...
ICIP
2005
IEEE
15 years 1 months ago
Expression-invariant face recognition via spherical embedding
Recently, it was proven empirically that facial expressions can be modelled as isometries, that is, geodesic distances on the facial surface were shown to be significantly less se...
Alexander M. Bronstein, Michael M. Bronstein, Ron ...
ICIP
2005
IEEE
15 years 1 months ago
Similarity-based and perception-based image segmentation
In this paper, we present a segmentation method that provides perceptually relevant partitions without any a priori knowledge of the image content: first a local homogeneity analy...
Jérémy Huart, Pascal Bertolino
ICIP
2005
IEEE
15 years 1 months ago
Image-based stereoscopic stylization
We present a method to generate stylized stereo imagery that effectively communicates shape and distance of the depicted scene objects. We use computer vision techniques to analyz...
Efstathios Stavrakis, Michael Bleyer, Danijela Mar...
ICIP
2005
IEEE
15 years 1 months ago
Spatial domain analysis on the focus measurement for light field rendering
Light field rendering (LFR) is an image-based rendering method for synthesizing free-viewpoint images from a set of multi-view images. In LFR, no/little knowledge of geometry is r...
Keita Takahashi, Takeshi Naemura
ICIP
2005
IEEE
15 years 1 months ago
Novel likelihood estimation technique based on boosting detector
This paper presents novel likelihood estimation to be used for particle filter based object tracking. The likelihood estimation is built upon cascade object detector trained with ...
Haijing Wang, Peihua Li, Tianwen Zhang
ICIP
2005
IEEE
15 years 1 months ago
Robust and real-time 3D-face model extraction
This article deals with 3D-face model and 3D-pose extraction from a small set of couples of 2D-3D correspondingpoints. Major drawbacks of current 3D model extraction solutions are...
Marc Chaumont, Brice Beaumesnil
ICIP
2005
IEEE
15 years 1 months ago
Rate allocation algorithms for motion compensated embedded video coders
In this paper, we present two rate allocation algorithms for embedded motion compensated video coders. The algorithms are based on the modeling of both the video signal and the co...
Josep Prades-Nebot, Gregory W. Cook, Edward J. Del...