Research area
My research area is Computer Vision (Artificial Intelligence).
Research interests
Structural Indexing Using Local Image Features
The problem of object recognition is one of the most challenging and important problems in computer vision. Today's recognition systems typically extract a sparse set of local
features, each of which characterizes a small patch of distinctive image data that is invariant to minor changes in lighting and viewpoint. The most popular such
feature, called a SIFT (scale invariant feature transform) feature, specifies the position, scale, orientation, and low-order description of the image data contained in the patch.
When such features are extracted from an image, they vote for objects that contain them (a process called indexing), using an efficient nearest-neighbour search algorithm.
Objects that receive a significant number of votes represent promising candidates for explaining the image. However, since each such feature votes independently, two different
candidates consisting of the same set of features but in very different configurations will receive the same number of votes. Therefore, a costly geometric consistency check must
be applied to each model candidate in order to determine the best matching model. As the database grows to contain millions of images, the ambiguity of a single image feature may
grow to the point where each feature is a member of a large number of objects, leading to a potentially intractable number of candidates that must be verified. Ambiguity is further
compounded when the number of object features is small or represents a small fraction of the total number of image features (i.e., the target object is embedded in a cluttered scene).
Instead of invoking strong geometric constraints at verification time, my research is exploring ways to incorporate these constraints at indexing time, leading to far fewer candidates
that need to be verified.
More on motivation, methods and impact, as well as references and
documents to download can be found under the side links.
I was also involved in the OME project:
Extending the OME requirements analysis tool to support formal analysis using ConGolog and CASL
Requirements specification and analysis, as well as requirements linking to
system/process design are becoming more and more important in software
engineering and business process reengineering. Open OME (Organization
Modeling Environment) is an open-source requirements engineering tool. It is a
goal-oriented and/or agent-oriented modeling and analysis tool that provides users
with a graphical interface to develop models. It also provides a clear link between
the requirements, specification and architectural design phases of development. OME primarily
uses the i* graphical notation for specifying models. i* is a relatively informal notation
with a limited expressiveness. This drawback limits the kinds of analysis that can be done.
Nevertheless, i* graphical notation can be employed together with the formal agent-oriented
specifications language such as ConGolog
to better specify the goals and processes that are being modeled and to perform
formal analysis, verification, and simulation.
This project focuses on extending the Open OME to obtain a tool that can
support better expressiveness of i* and more varied and thorough analysis of the
built systems.
On this project I was working with Professor Yves Lesperance
from York University
and Dr. Yijun Yu
from The Open University (UK).
More on my project can be found in the project report .