Speaker: Surendar Chandra, Computer Science, Duke University
In this talk, I will present image transcoding as an application level
technique to dynamically customize content. First, I analyze characteristics
of Web images to choose appropriate transcoding technologies. Next,
I quantify the quality versus size trade-off characteristics of a promising
transcoding algorithm. I then use this informed technique in a Web service
for providing bandwidth consumption control, while providing differentiated
Quality of Service. This technology also allows Web services to customize
objects for clients accessing the Web using various network technologies.
By understanding the image characteristics, informed transcoding avoids
unnecessary operations that lose quality as well as place unnecessary loads
on the infrastructure. Through an implementation of informed transcoding
in a popular Web server, I demonstrate how it achieves these goals.
Short Bio: Surendar
Chandra is an Experimental Computer Science student at Duke University.
His research interests lie in the areas of mobile computing, distributed
systems, operating systems, computer networks and WWW issues. He received
his undergraduate degree in Computer Science from Anna University, India
in 1988. He received the M.S degree in Computer Science from Worcester
Polytechnic Institute, Worcester MA in 1993. He is a student member of
ACM (SIGOPS and SIGMOBILE), USENIX and IEEE.
Host: Edward
Gehringer, Computer Science, NCSU