Abstract

Bridging the semantic gap between automated low-level image 
indexing and subjective high-level user query is an open problem
in content-based image retrieval (CBIR). In this talk, we will
present two recent research efforts in capturing the semantics in
images for indexing, retrieval, and recognition.

In the first project, we present a new conceptual indexing and 
retrieval approach, applied to the medical image retrieval task in 
the international benchmarks ImageCLEF 2005 and 2006. Using medical 
concepts from the Unified Medical Language System meta-thesaurus
of the National Library of Medicine to represent both image and
text allows our system to work at a higher semantic level and to 
standardize the semantic index of medical data. We will discuss
different indexing and fusion attempts, some of which top the
benchmarking results (Mean Average Precision) in both years.

Camera phones present new opportunities and challenges for mobile
information association and retrieval. The visual input in the
real environment is a new and rich interaction modality between
a mobile user and vast information base connected to a user's 
device via rapidly advancing communication infrastructure. In the
second project, we have developed a system for tourist information
access to provide scene description based on an image taken of the
scene. We describe the working system, the STOIC 101 database, and 
a new pattern discovery algorithm to learn image patches that are 
recurrent within a scene class and discriminative across others. 

Biography:

LIM Joo Hwee received his B.Sc. (Hons I) and M.Sc. (by research)
degrees in Computer Science from the National University of 
Singapore and his Ph.D. degree in Computer Science & Engineering
from the University of New South Wales. He has joined Institute
for Infocomm Research (I2R) and its predecessors, Singapore since
Oct 1990. He has conducted research in connectionist expert 
systems, neural-fuzzy systems, handwriting recognition, 
multi-agent systems, and content-based retrieval. He was a key
researcher in two international research collaborations, namely 
the Real World Computing Partnership funded by METI, Japan and the 
Digital Image/Video Album project with CNRS, France and School of 
Computing, National University of Singapore. 
He also contributed technical solutions to a few industrial 
projects involving pattern-based diagnostic tools for aircraft and 
battleship navigation systems and knowledge-based post-processing
for automatic fax/form recognition. He has nine patents (awarded 
and pending) and published more than one hundred and twenty refereed
international journal and conference papers in his research areas.
He is currently the Department Head of the Computer Vision & Image 
Understanding Department, with staff strength of fifty research 
scientists and engineers, at I2R, Singapore. He is also the 
co-Director of IPAL (Image Perception, Access and Language), a 
French-Singapore Joint Lab (UMI 2955, Jan 2007 to Dec 2010). He is 
bestowed the title of 'Chevallet dans l’ordre des Palmes 
Academiques' by the French Government in 2008.