Connectionists: Call for Papers: Special Issue of Signal Processing on Machine Learning in Intelligent Image Processing

[Jun Li]

We apologise if you have received multiple copies of this message.

[Special Issue on Machine Learning in Intelligent Image Processing]
Research on intelligent image processing has a long history, and a lot of algorithms have been developed to address different problems, such as image quality enhancement & evaluation, astronomical image analysis, biometrics, texture analysis, scene modelling, and controlled environment surveillance. In these problems, machine learning plays an important role for visual information processing.

With the increasing attention in recent years, of interest to this special issue is research that demonstrates how machine learning algorithms have contributed, and are contributing to the research and applications of intelligent image processing. It is not difficult to enumerate a large number of successful examples of using machine learning in intelligent image processing, e.g., structured sparsity has been successfully applied to image and video modeling; human machine interactions significantly improve the performance of large scale image retrieval; sparse linear and multilinear subspace methods dramatically enhance the recognition rates in human behavior analysis and face synthesis; random fields and probabilistic graphical models show promising advantages in image and video analysis; graph cut and spectral clustering are widely applied to image segmentation; kernel machines, such as the support vector machines, are successfully used in visual tracking and handwriting recognition; and reinforcement learning is applied to visual texture synthesis.

It is the time to motivate image processing researchers and machine learning researchers to work together and pay more attention to each other’s field. Therefore, there is a chance to obtain significant performance improvement for practical utilizations of intelligent image processing by developing particular learning algorithms, and to bring in interesting utilizations of machine learning algorithms for particular intelligent image processing. The editors expect to gather a set of recent research outputs together, to report the progress of what is going on, and to build a forum for researchers to exchange their innovative ideas on machine learning in intelligent image processing.
 To summarize, this special issue welcomes a broad range of submissions developing and using machine learning algorithms for intelligent image processing. We are especially interested in 1) theoretical advances as well as algorithm developments in machine learning techniques for particular intelligent image processing problems, 2) reports of practical applications and system innovations in intelligent image processing, and 3) novel data sets as test bed for new developments, preferably with implemented standard benchmarks. The following list contains topics of interest (but not limited to):
* Compressed sensing for visual recognition and information compression

* Intelligent image analysis and understanding

* Intelligent object and event recognition

* Intelligent visual surveillance

* Intelligent visual information retrieval

* Kernel machines and tensor machines for visual data modeling

* Learning methods in image-based modeling

* Manifold learning for visual recognition

* Matrix completion and decomposition for image analysis

* Probabilistic graphical models for image analysis and modeling

* Sparse learning and structured sparsity for visual analysis

* Statistical methods and learning for intelligent image processing

* Subspace learning for intelligent visual information compression
* Visual learning and cognitive vision

[Important dates]

Manuscript submission: January 25, 2012 R1 Version: April 25, 2012 Acceptance notification: May 15, 2012 Final manuscripts due: June 25, 2012 Anticipated publication: October 25, 2012

[Submission]

Manuscripts (6-15 pages in the Elsevier Signal Processing publishing format) should be submitted via the Electronic Editorial System, Elsevier: http://ees.elsevier.com/sigpro/

Guide for authors can be found at:
http://support.elsevier.com/app/answers/detail/a_id/116

[Guest Editors]

Dacheng Tao University of Technology, Sydney Australia dacheng.tao at uts.edu.au

Dianhui Wang La Trobe University Australia dh.wang at latrobe.edu.au

Fionn Murtagh Royal Holloway University of London United Kingdom fmurtagh at acm.org

UTS CRICOS Provider Code: 00099F
DISCLAIMER: This email message and any accompanying attachments may contain confidential information.
If you are not the intended recipient, do not read, use, disseminate, distribute or copy this message or
attachments. If you have received this message in error, please notify the sender immediately and delete
this message. Any views expressed in this message are those of the individual sender, except where the
sender expressly, and with authority, states them to be the views of the University of Technology Sydney.
Before opening any attachments, please check them for viruses and defects.

Think. Green. Do.

Please consider the environment before printing this email.