IPAL External Competitive Projects


MMedWeb

Multimedia Medical Conceptual Web for Intelligent Information Access

SERC - A*STAR – Science & Engineering Research Council, Agency for Science, Technology and Research – Singapore

Partners: - National University Hospital (NUH, Singapore), - National Healthcare Group (NHG, Singapore) and Singapore General Hospital (SGH, Singapore).

MmedWeb project proposes to develop a framework for the semantic structuring and organization of multimedia medical information, including medical images and medical reportsProposed.
The IVS4NSC Project (Dec 2009-Nov.2012)

IVS4NSC project combines neural stem cell biology, microscopy, image processing and machine learning research to realize an integrated intelligent vision system for systematic studies of neural stem cells. Images generated in the biological laboratories are processed using automated algorithms to extract special image features that will then be analyzed by machine learning techniques to understand the content and context of the image data. Multi-variable statistical analysis and data modelling can then be used to summarize and extract important information to generate new biological hypothesis. These new biological hypothesis will then be tested again in the biological laboratories.
AMUPADH Activity Monitoring and UI Plasticity for supporting Ageing with Mild Dementia at Home (AMUPADH) - A*STAR SERC (2 years - May 2010 – April 2012)
Onco-Media

Ontology and COntext related MEdical image Distributed Intelligent Access

ICT ASIA Project (Ministère des Affaires Étrangères– MAE, France)

Partners: - UNIGE (University Hospitals of Geneva, Switzerland), - CREATIS (Lyon, France), - LIRIS (Lyon, France), - NTU Taiwan, - CASIA (Institute of Automation, Chinese Academy of Sciences, Beijing, China), - Ateneo de Manila University (Philippines), - National Center for Geriatrics and Gerontology (NCGG, Japan), - LIP6 (Laboratory of Computer Sciences, Paris 6, France).

The aim of ONCO-MEDIA project is to deploy a medical image semantic content-based application on a large scale grid tested, by taking into account the context of the user and of the navigation / query and by matching semantic visual concepts extracted from the medical image with those (textual) extracted from the associated medical reports
MoSAIC

Mobile Search and Annotation using Images in Context

ICT ASIA Project (Ministère des Affaires Étrangères – MAE, France)

Partners: - NII (National Institute of Informatics, Tokyo, Japan), - NTU (Dept of Computer Science and Information Engineering National Taiwan University), - MICA (International Research Center MICA, Hanoi, Vietnam), - CLIPS-IMAG (Communication Langagiere et Interaction Personne Systeme, Grenoble France), - LIRIS (Laboratoire d'InfoRmatique en Image et Systèmes d'information, Lyon, France).

The MoSAIC project develop a novel mobile search and annotation framework using images in context. Camera phones are both communication and image capturing devices.
However, unconstrained image recognition is an open research problem. Contextual information such as geospatial cues would help to narrow the search space, return answers with higher relevancy, and provide meaningful annotations to the query logs.
GRASP-IT

 

Merlion Programme,

French Embassy (Aug. 2007- Jul. 2010)

 
Remove Visualization of Large Collections of 3D Data

Merlion Programme,

French Embassy (Aug. 2008 - Jul. 2010)
mCity: Street Scene Indexing and Retrieval

Merlion Programme,

French Embassy (June. 2010 - June. 2013)

 

IPAL Core Projects

 

MICO

Cognitive Virtual Microscopy

The cognitive microscope aims at developing a cognition-driven visual explorer for histopathology. The clinical goal is a realiable breast cancer grading from histopathological images.

Snap2Tell

Mobile Access to Images

This project studies the role of small mobile devices and picture to access information. In this project, we focus on scene identification based on image examples with geospatial cues. This is a challenging problem as image objects are usually multi-scaled, ill-posed, occluded and cluttered, captured with different lighting conditions, focus, exposure and viewing perspectives.