The primary focus of the conference is on new and original research results in the areas of theoretical findings, design, implementation, and applications. Both theoretical paper and simulation (experimental) results are welcome. Topics of interest include, but are not limited to, the following:

Computer Vision and Recognition:

Active and Robot Vision
Biometric Authentication
Camera Networks and Vision
Cognitive and Biologically Inspired Vision
Fuzzy and Neural Techniques in Vision
Face and Gesture Recognition
Image Feature Extraction
Novel Vision Application and Case Studies
Machine Learning Technologies for Vision
Object Recognition
Sensors and Early Vision

Image Processing and Analysis:

Optical imaging
3D Imaging
Enhancement Techniques
Image Compression, Coding, and Encryption
Image Generation, Acquisition, and Processing
Image Geometry and Multi-view Geometry
Image Restoration
Image-based Modeling and Algorithms
Mathematical Morphology
Multi-resolution Imaging Techniques

Multimedia and Applications:

Multimedia Systems and Applications
Novel Image Processing Applications
Video Analysis
Industrial Inspection
Nondestructive Evaluation
Watermarking Methods and Protection + Wavelet Methods
	
Techniques and Tools for Imaging and Vision:

Segmentation Techniques
Software Tools for Imaging
Soft Computing Methods in Image Processing and Vision
Special-purpose Machine Architectures for Vision

Medical and Geospatial Imaging:

Medical Image Processing and Analysis
Novel Document Image Understanding Techniques
Geographic Information System
Remote Sensing

Pattern Recognition and Machine Learning:

Stereo Vision
Bayesian Methods in Pattern Recognition and Matching
Case studies and Emerging technologies
Clustering Techniques
Dimensionality Reduction Methods in Pattern Recognition
Ensemble Learning Algorithms
Invariance in Pattern Recognition
Knowledge-based Recognition
Parsing Algorithms
Statistical Pattern Recognition
Structural and Syntactic Pattern Recognition
Supervised and Un-supervised Classification Algorithms
Symbolic Learning