Content uploaded by Fatma Ezahra Sayadi
Author content
All content in this area was uploaded by Fatma Ezahra Sayadi on Jun 10, 2021
Content may be subject to copyright.
A preview of the PDF is not available
Image processing on GPU: Application of integral image
Abstract
In this paper we present an integral image algorithm that can run in real-time on a Graphics Processing Unit (GPU). Our system exploits the parallelisms in computation via the NVIDA CUDA programming model, which is a software platform for solving non-graphics problems in a massively parallel high performance fashion. We compare the performance of the parallel approach running on the GPU with the sequential CPU implementation across a range of image sizes.
ResearchGate has not been able to resolve any citations for this publication.
Semantic Web Technologies enable machines to interpret data published in a machine-interpretable form on the web. At the present time, only human beings are able to understand the product information published online. The emerging semantic Web technologies have the potential to deeply influence the further development of the Internet Economy. In this paper we propose a scenario based research approach to predict the effects of these new technologies on electronic markets and business models of traders and intermediaries and customers. Over 300 million searches are conducted everyday on the Internet by people trying to find what they need. A majority of these searches are in the domain of consumer ecommerce, where a web user is looking for something to buy. This represents a huge cost in terms of people hours and an enormous drain of resources. Agent enabled semantic search will have a dramatic impact on the precision of these searches. It will reduce and possibly eliminate information asymmetry where a better informed buyer gets the best value. By impacting this key determinant of market prices semantic web will foster the evolution of different business and economic models. We submit that there is a need for developing these futuristic models based on our current understanding of e-commerce models and nascent semantic web technologies. We believe these business models will encourage mainstream web developers and businesses to join the "semantic web revolution."
We develop a face recognition algorithm which is insensitive to
large variation in lighting direction and facial expression. Taking a
pattern classification approach, we consider each pixel in an image as a
coordinate in a high-dimensional space. We take advantage of the
observation that the images of a particular face, under varying
illumination but fixed pose, lie in a 3D linear subspace of the high
dimensional image space-if the face is a Lambertian surface without
shadowing. However, since faces are not truly Lambertian surfaces and do
indeed produce self-shadowing, images will deviate from this linear
subspace. Rather than explicitly modeling this deviation, we linearly
project the image into a subspace in a manner which discounts those
regions of the face with large deviation. Our projection method is based
on Fisher's linear discriminant and produces well separated classes in a
low-dimensional subspace, even under severe variation in lighting and
facial expressions. The eigenface technique, another method based on
linearly projecting the image space to a low dimensional subspace, has
similar computational requirements. Yet, extensive experimental results
demonstrate that the proposed “Fisherface” method has error
rates that are lower than those of the eigenface technique for tests on
the Harvard and Yale face databases
