Prof. Fernand Meyer, MINES ParisTech, PSL Research University, France

Title: A course on mathematical morphology

Date: January 4, 2015   Time: 9:00-10:15 and 10:30-11:45 Hrs   Venue: Platinum Jubilee Auditorium



Abstract: Setting up a course on mathematical morphology for an audience mixing different levels of expertise is rather challenging. Rather to develop one topic in depth, I chose to organize a longitudinal traversal of the subject:
• Presenting the elementary bricks: erosion and dilations, as minima and maxima of translated sets.
• Introducing the adjunction between operators, which couple all erosions and dilations.
• Present the openings and closings derived from the adjunction.
• Extend to algebraic openings and closings.
• Present the floodings and razings as connected openings and closings preserving the contours.
• Set up the basics of the theory of morphology filtering, as combinations of openings and closings.
• Present the levelings, commutative product of floodings and razings.
• Introduce the important watershed transform, for segmenting images.
• Combine the watershed with increasing floodings in order to produce size driven hierarchical segmentations.
Each of these topics would deserve an extensive course in itself. With many illustrations, it is possible to understand the rationale of each tool and the logical articulations between the various branches of mathematical morphology.

Short Biography: Fernand Meyer got an engineer degree from the Mines-ParisTech in 1975. He works since 1975 at the Centre de Morphologie Mathematique (CMM) of Mines-ParisTech (member of PSL Research University). His first research area was ''Early and Automatic Detection of Cervical Cancer on Cytological Smears'', subject of his PhD thesis, obtained in 1979. He participated actively to the development of mathematical morphology: reconstruction openings, top-hat transform, the morphological segmentation paradigm based on the watershed transform and markers, the theory of digital skeleton, the introduction of hierarchical queues for high speed watershed computations, morphological interpolations, the theory of levelings, hierarchical segmentation. His current subject of interest is the extension of mathematical morphology to node and/or edge weighted graphs.

---

• Prof. Dong Xu, School of Computer Engineering, Nanyang Technological University, Singapore

  Title: SVM based approaches for visual domain adaptation

  Date: January 4, 2015   Time: 11:45-13:00 Hrs and 14:00-15:15 Hrs   Venue: Platinum Jubilee Auditorium



Abstract: Domain adaptation (also called transfer learning) is an emerging research topic in computer vision. In some vision applications, the domain of interest (i.e., the target domain) contains very few or even no labeled samples, while an existing domain (i.e., the auxiliary domain) is often available with a large number of labeled examples. For example, millions of loosely labeled Flickr photos or YouTube videos can be readily obtained by using keywords based search. On the other hand, users may be interested in retrieving and organizing their own multimedia collections of images and videos at the semantic level, but may be reluctant to put forth the effort to annotate their photos and videos by themselves. This problem becomes furthermore challenging because the feature distributions of training samples from the web domain and consumer domain may differ tremendously in statistical properties. To explicitly cope with the feature distribution mismatch for the samples from different domains, in this talk I will describe our SVM based approaches for domain adaptation under different settings as well as their interesting applications in computer vision.

Short Biography: Dr. Dong Xu is currently an associate professor in the School of Computer Engineering, Nanyang Technological University, Singapore. His research focuses on new theories, algorithms and systems for intelligent processing and understanding of visual data such as images and videos. One of his co-authored works on domain adaptation for video event recognition won the Best Student Paper Award in CVPR 2010. He is on the editorial boards of IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Neural Networks and Learning Systems, and Machine Vision and Applications (Springer).

---

• Prof. Amit Konar, Department of Electronics and Tele-Communication Engineering, Jadavpur University, Kolkata, INDIA

  Title: Feature Selection and Classification of Brain Signals for Rehabilitative Applications

  Date: January 4, 2015   Time: 15:25-16:40Hrs and 17:00-18:15 Hrs   Venue: Platinum Jubilee Auditorium



Abstract: Brain-computer interfacing (BCI) is currently gaining popularity for its increasing importance in bio-medical and rehabilitative applications. This tutorial aims at offering an introduction to design and development issues of BCI systems for neuro-prosthetic applications. Special emphasis would be given to EEG (electroencephalography) and fNIRs (functional Near Infrared spectroscopy) based system design with a focus to pre-processing, feature extraction, feature selection, classification and control aspects of the design. Feature selection algorithms to be covered include Principal Component Analysis (PCA), Independent Component Analysis (ICA), Common Spatial Patterns (CSP) and evolutionary techniques. Pattern recognition techniques to be offered includes Naïve Bayes, support vector machines, feed-forward neural classifiers and recurrent neural topologies. Main attraction of this tutorial lies in the practical perspectives of system design for upper limb prosthesis and rehabilitation, cognitive load detection in human subjects during complex problem solving, detection of cognitive failures in driving, and movement control of artificial limbs for patients with brain injury during his/her participation in tennis games.

Short Biography: Prof. Amit Konar is currently a Professor in the department of Electronics and Tele-Communication Engineering, Jadavpur University, Calcutta, India, and Joint Coordinator, Center for Cognitive Science, Jadavpur University. He is also the founding coordinator of a regular M.Tech. program on Intelligent Automation and Robotics, offered by Jadavpur University.

Dr. Konar has been teaching and carrying out research work at this university for the past 23 years. Jadavpur University is one of the top three universities in India. The faculty of Engineering and Technology, with more than 100 externally funded research projects, earned recognition as a "Center for Excellence" from the Government of India, and the university got the “Five Star” rating. The doctoral, master’s, and bachelor’s programs offered by the university are acknowledged as one of the very best in the country.

---

For Camera Ready submission, click here: https://www.easychair.org/conferences/?conf=icapr2015