Sciweavers

ICIP
2005
IEEE
14 years 11 months ago
Variable module graphs: a framework for inference and learning in modular vision systems
We present a novel and intuitive framework for building modular vision systems for complex tasks such as surveillance applications. Inspired by graphical models, especially factor...
Amit Sethi, Mandar Rahurkar, Thomas S. Huang
ICIP
2005
IEEE
14 years 11 months ago
Segmenting small regions in the presence of noise
Binary segmentation, a problem of extracting foreground objects from the background, often arises in medical imaging and document processing. Popular existing solutions include Ex...
Rashi Samur, Vitali Zagorodnov
ICIP
2005
IEEE
14 years 11 months ago
Fine spatial scalability in wavelet based image coding
Wavelet transform based image coding algorithms have the two inherent scalable features of SNR scalability and spatial (or resolution) scalability. However, fine scalability is sup...
Donghoon Yu, Jong Beom Ra
ICIP
2005
IEEE
14 years 11 months ago
Nonparametric wavelet based texture synthesis
This paper presents a new algorithm for synthesising image texture. Texture synthesis is an important process in image postproduction. Previous approaches can be classified as eit...
Claire Gallagher, Anil C. Kokaram
ICIP
2005
IEEE
14 years 11 months ago
Embedded image coding with context partitioning and quantization
As a key part of universal source coding, context quantization is very important for improving compression performance. However, in most existing methods, the quantizer is trained...
Hua Cai, Xing San, Jiang Li
ICIP
2005
IEEE
14 years 11 months ago
Statistical restoration for robust and secure steganography
We investigate data hiding techniques that attempt to defeat steganalysis by restoring the statistics of the composite image to resemble that of the cover. The approach is to rese...
Kaushal Solanki, Kenneth Sullivan, Upamanyu Madhow...
ICIP
2005
IEEE
14 years 11 months ago
Complexity/performance trade-offs for robust distributed video coding
In this work, we analytically study the complexity-performance trade-offs associated with video codecs based on the principle of source coding with side information at the decoder...
Abhik Majumdar, Rohit Puri, Prakash Ishwar, Kannan...
ICIP
2005
IEEE
14 years 11 months ago
Blind separation of reflections using the image mixtures ratio
A new method for the blind separation of linear image mixtures is presented in this paper. Such mixtures often occur, when, for example, we photograph a scene through a semireflec...
Konstantinos I. Diamantaras, Theophilos Papadimitr...
ICIP
2005
IEEE
14 years 11 months ago
Multi-view face pose classification by tree-structured classifier
In this paper, a multi-view face pose classification method is introduced. Each face region is normalized by two eye-centers and mouth center, and then multi-class classifiers are...
Zhiguang Yang, Haizhou Ai, Takuya Okamoto, Shihong...
ICIP
2005
IEEE
14 years 11 months ago
Dependent bit allocation in multiview video coding
We consider the bit allocation problem in multiview video coding (MVC). A dependent coding technique using trellis expansion and the Viterbi algorithm (VA) is proposed, which take...
Jae Hoon Kim, Jonathan Garcia, Antonio Ortega