There are currently two active projects. Fast Pattern Matching and the FLCC.
The goal of this project is to develop fast pattern matching algorithms for GPUs.
Currently the research effort is focused on exact and approximate k-nearest neighbors
(knn) search, all-knn search and k-means clustering.The motivation for this work comes
mainly form computer vision applications such as image retrieval. Among the results of
this project is the development two libraries for fast knn and k-mean
(for more information see here).
The FLCC Library (which stands for Fast Local Correlation Coefficients) is a software tool
that provides an interface for the fast computation of two fundamental image processing operations:
the distribution of Correlation Coefficients with Local Normalization (also known as LCCs) and the
sum of Convolution, between an image (or a stream of images) and an image template. Generally speaking,
LCCs and Convolution are basic image-based information processing steps that find numerous applications
in a wide spectrum of areas concerning image processing and computer vision, such as template or pattern
matching, image registration, motion detection and many more. However, these operations (especially LCCs)
have always been considered to be time-consuming and of high arithmetic complexity, particularly for
real-time applications, thus making their usage rather troublesome. This library intends to overcome this
problem and provide users with a simple yet powerful interface for carrying out the computations under
consideration (for more information see here).