International Conference on Machine Learning and Cybernetics (ICMLC)
Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826)
DOI: 10.1109/ICMLC.2004
26-29 Aug. 2004
Showing 1-25 of 88
Sort By
IEEE Proceedings of 2004 International Conference on Machine Learning and Cybernetics - Cover
Publication Year: 2004,Page(s):0_1 - 0_1
IEEE Proceedings of 2004 International Conference on Machine Learning and Cybernetics - Cover
[Blank page]
IEEE Proceedings of 2004 International Conference on Machine Learning and Cybernetics - Title Page
Publication Year: 2004,Page(s):0_3 - 0_3
IEEE Proceedings of 2004 International Conference on Machine Learning and Cybernetics - Title Page
Copyright
The Third International Conference on Machine Learning and Cybernetics - Organization Committee
Publication Year: 2004,Page(s):iii - iv
Acknowledgements
[Blank page]
Contents
Fast algorithm and application of Hough transform in iris segmentation
Publication Year: 2004,Page(s):3977 - 3980 vol.7
Hough transform is a common algorithm used to detect geometry shape of objects in computer image processing, some points satisfied lines, circles and other curves can be detected easily by using Hough transform in image. In iris recognition system, both the inner boundary and the outer boundary of a typical iris can approximately be taken as circles, so the two circles of iris can be obtained by u...Show More
Linear feature detection is very important in computer vision, image segmentation and pattern recognition. Traditional linear feature detectors based on pixel processing each by each may fail to detect out lines in image with low SNR. A fast discrete beamlet transform and an adaptive method of linear feature detection are proposed, which can detect lines with any orientation, location and length. ...Show More
Nonseparable biorthogonal wavelet packets in L/sup 2/(R/sup 2/)
Publication Year: 2004,Page(s):3985 - 3989 vol.7
The notion of univariate and multivariate orthogonal wavelet packets has been generalized. First, the definition for nonseparable biorthogonal bivariate wavelet packets is given and a procedure of constructing them is described. Second, the biorthogonality property for biorthogonal bivariate wavelet packets is studied.Show More
A variable depth LSB data hiding technique in images
Publication Year: 2004,Page(s):3990 - 3994 vol.7
Cited by: Papers (19)
In this paper, a data hiding technique by variable depth LSB substitution is proposed. Firstly, pixels of cover-image are grouped according to themselves luminance values. Then the occurrence of pixel-values in each group is counted and sorted in monotone increasing. Finally, a bitplane-wise data hiding method is used to hide data in cover image. The worst-square-error between the stego-image and ...Show More
Frontal motion tracking based on image features analysis and particle filter
Publication Year: 2004,Page(s):3995 - 3998 vol.7
This work presents a method that integrates the image feature analysis into standard particle filter for monocular frontal human body motion tracking. The scaled prismatic models are taken as human body models and a state vector is used to represent human body pose. The image feature analysis applies the trained back propagation neural networks to locate some key joints such as elbow joints and kn...Show More
Bayesian structural content abstraction for image authentication
Publication Year: 2004,Page(s):3999 - 4003 vol.7
Cited by: Papers (1)
An ideal authentication approach should be able to tolerate "content preserving" operations (e.g. compression and rotation) robustly, while detecting "content altering" (e.g. object removing and replacement) modifications sensitively. Although the numerous existing algorithms can detect and locate malicious alterations to the protected image, unfortunately, most are still too fragile to resist var...Show More
Efficient motion estimation using two-phase algorithm
Publication Year: 2004,Page(s):4004 - 4008 vol.7
Cited by: Papers (1)
This work introduces a fast block-based motion estimation algorithm named two-phase motion estimation algorithm (TPMEA). The idea of the algorithm is to divide motion estimation procedure into two-phase: in the first phase, the sum of pixels in a line (or a column) is used as the 1D vector; In the second phase, a filtering threshold is deduced from the 1D vector matching, as Minkowski inequality h...Show More
Analyzing fMRI data based on multi-resolution factorial kriging
Xian-Chuan Yu;Chen Yu;Xiao-Chun Cheng;Shao-Chun Zhong;Ting Zhang
Publication Year: 2004,Page(s):4009 - 4014 vol.7
Functional magnetic resonance imaging (fMRI) is a harmless technology for studying the human brain functions that has been developed recently. Multi-resolution analysis, which is applied to fMRI, is a new dealing method. In statistical analysis, many statistical algorithms identify whether each pixel is activated by counting the serial time of them dependently, or by taking the spatial relativity ...Show More
A novel image content protection method
Publication Year: 2004,Page(s):4015 - 4020 vol.7
Cited by: Papers (1)
A novel image content protection (ICP) method is proposed in this paper. To satisfy the fundamental requirement for ICP, i.e. being robust to non-content operations and sensitive to content tampers simultaneously, a pixel-level image content map (PICM) is extracted by dynamic weighted averaging. Then, a regional image content map (RICM) is derived through segmentation of PICM and its invariant mom...Show More
Noise reduction for quadrature Doppler ultrasound signal based on the adapted local cosine transform
Publication Year: 2004,Page(s):4021 - 4026 vol.7
The spectral analysis of the Doppler ultrasound signal based on the spectrogram has been widely used in medicine for the assessment of blood flow in vessels. The additional frequency components arising from noise produces an adverse effect on the subjective study of the spectrogram and its quantitative analysis. A novel approach using the adapted local cosine transform, combined with the non-negat...Show More
In the process of switching arc image acquisition, because of the strong radiation of arc, the weak reflection of contacts and the shake of apparatus due to the impact of mechanical motion, the arc image was polluted by noise. The weak feature of the contacts and chamber cannot be observed clearly. In order to enhance the weak feature, a method based on gray level transformation and pattern matchi...Show More
3-D non-rigid motion estimation from image sequence based on Makov random field [Makov read Markov]
Publication Year: 2004,Page(s):4032 - 4036 vol.7
We propose an approach to 3-D non-rigid motion estimation from image sequence in this paper. First, with the establishment of feature point correspondence between consecutive image frames, the affine motion model and the central projection model are presented for local non-rigid motion. Then, in order to obtain the global motion parameters and overcome the ill-posed 3-D estimation problem, a frame...Show More
Particle swarm optimization-based texture synthesis and texture transfer
Publication Year: 2004,Page(s):4037 - 4042 vol.7
Cited by: Papers (1)
In this paper, a fast texture synthesis algorithm-swarm intelligence-based texture synthesis is presented. The algorithm uses an intelligent particle swarm optimization (PSO) algorithm to search the best matching patch from the input sample textures and paste it onto the output texture. After a series of experiments, it is proved that the algorithm is effective to a variety of textures, and high q...Show More
A fast algorithm for image analogy using particle swarm optimization
Publication Year: 2004,Page(s):4043 - 4048 vol.7
This work employs particle swarm optimization (PSO) based texture synthesis approaches, it differs from the pixel-based texture synthesis method, in this way, and the synthesis speed is increased. We apply particle swarm optimization (PSO) to improve the process of searching and matching in patch-based texture synthesis, change the throughout search method of the original algorithm; speed up the p...Show More
Self-adaptive image fusion based on multi-resolution decomposition using wavelet packet analysis
Publication Year: 2004,Page(s):4049 - 4053 vol.7
A self-adaptive image fusion method using multi-resolution analysis is proposed, in which multi-spectral (TM) and SAR images are fused. Firstly, we convert TM images from RGB to IHS colour space. Then, the I component in TM images are fused with SAR images using quadtree decomposition of images by wavelet packet analysis. The final results are obtained through inverse wavelet and IHS transforms, r...Show More
IEEE Account
Purchase Details
Profile Information
Need Help?
- US & Canada: +1 800 678 4333
- Worldwide: +1 732 981 0060
- Contact & Support
- About IEEE Xplore
- Contact Us
- Help
- Accessibility
- Terms of Use
- Nondiscrimination Policy
- Sitemap
- Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.