Special Sessions
Shape Analysis and Deformable Modeling - SADM 2012
Chair
 |
Xianghua Xie Swansea University U.K. Web |
|
All papers accepted in Special Sessions will be included in the conference proceedings and indexed.
|
|
Scope
Deformable modeling is a powerful tool in extracting object shape, structure, and motion patterns. It is particularly suitable for non-rigid objects and has been widely used to measure and model, for instance, biological shape and shape evolution in medical data where shape extraction and analysis have shown enormous promise in understanding biological function and disease progression. Its application has a wide reach in all areas of computer vision.
This special session is devoted to the discussion of recent advances in shape analysis and deformable modeling, in particular, for non rigid objects. Contributions presenting recent work on shape representation, extraction, learning, classification and dynamic modeling are particularly welcome.
Deformable modeling is a powerful tool in extracting object shape, structure, and motion patterns. It is particularly suitable for non-rigid objects and has been widely used to measure and model, for instance, biological shape and shape evolution in medical data where shape extraction and analysis have shown enormous promise in understanding biological function and disease progression. Its application has a wide reach in all areas of computer vision.
This special session is devoted to the discussion of recent advances in shape analysis and deformable modeling, in particular, for non rigid objects. Contributions presenting recent work on shape representation, extraction, learning, classification and dynamic modeling are particularly welcome.
Pattern Recognition Applications in Remotely Sensed Hyperspectral Image Analysis - PRARSHIA 2012
Chair
 |
Antonio Plaza University of Extremadura Spain Web |
|
All papers accepted in Special Sessions will be included in the conference proceedings and indexed.
|
|
Scope
Hyperspectral imaging is concerned with the measurement, analysis and interpretation of spectra acquired from a given scene by an airborne or satellite imaging spectrometer providing information in narrow wavelengths.
The special characteristics of remotely sensed hyperspectral images pose different processing problems which must be necessarily tackled under specific mathematical formalisms, such as classification and segmentation, or spectral unmixing. For instance, several machine learning techniques are now actively being applied to extract relevant information (in supervised, semi-supervised or unsupervised fashion) from remotely sensed hyperspectral data. This special session aims at providing an overview of recent advances in the use of pattern recognition and machine learning techniques for hyperspectral data interpretation, with particular attention to specific aspects of hyperspectral image analysis such as the presence of mixed pixels or the high computational requirements introduced by the processing of data sets provided by the latest generation of imaging instruments.
Hyperspectral imaging is concerned with the measurement, analysis and interpretation of spectra acquired from a given scene by an airborne or satellite imaging spectrometer providing information in narrow wavelengths.
The special characteristics of remotely sensed hyperspectral images pose different processing problems which must be necessarily tackled under specific mathematical formalisms, such as classification and segmentation, or spectral unmixing. For instance, several machine learning techniques are now actively being applied to extract relevant information (in supervised, semi-supervised or unsupervised fashion) from remotely sensed hyperspectral data. This special session aims at providing an overview of recent advances in the use of pattern recognition and machine learning techniques for hyperspectral data interpretation, with particular attention to specific aspects of hyperspectral image analysis such as the presence of mixed pixels or the high computational requirements introduced by the processing of data sets provided by the latest generation of imaging instruments.
Interactive and Adaptive Techniques for Machine Learning, Recognition and Perception - IATMLRP 2012
Co-chairs
 |
Luisa Mico University of Alicante Spain Web |
 |
Francesc J. Ferri University of Valencia Spain Web |
|
All papers accepted in Special Sessions will be included in the conference proceedings and indexed.
|
|
Scope
Human interaction is a very active field that is receiving increasing attention in the pattern recognition and machine learning community.
In this new paradigm the systems do not perform only in an automatic way but also in an interactive fashion.
The main reason for this is that automatic systems are not free from errors and, being high quality results the principal objective, a kind of supervision is needed. On the other hand, as time goes by, intrinsic interactive applications are more important and frequent.The use of the interactive paradigm in Pattern Recognition opens the door to new challenges in order to make convenient use of a number of emerging methods for supporting learning and data analysis in dynamics contexts: active and adaptive learning, hypothesis generation, data managed techniques, combining classifier techniques, probabilistic learning, interactive transduction, etc. Moreover, another challenge is the application of these ideas to interesting real-word tasks, as human behavior analysis, text transcription, content-based image retrieval, handwriting recognition, surveillance, biometric systems and many others.
This special session welcomes articles on advances on all the aforementioned hot topics.
Human interaction is a very active field that is receiving increasing attention in the pattern recognition and machine learning community.
In this new paradigm the systems do not perform only in an automatic way but also in an interactive fashion.
The main reason for this is that automatic systems are not free from errors and, being high quality results the principal objective, a kind of supervision is needed. On the other hand, as time goes by, intrinsic interactive applications are more important and frequent.The use of the interactive paradigm in Pattern Recognition opens the door to new challenges in order to make convenient use of a number of emerging methods for supporting learning and data analysis in dynamics contexts: active and adaptive learning, hypothesis generation, data managed techniques, combining classifier techniques, probabilistic learning, interactive transduction, etc. Moreover, another challenge is the application of these ideas to interesting real-word tasks, as human behavior analysis, text transcription, content-based image retrieval, handwriting recognition, surveillance, biometric systems and many others.
This special session welcomes articles on advances on all the aforementioned hot topics.
