MASTER OF SCIENCE PROJECT DEFENSE BY: Tahera Begum Shaik
When: Tuesday,
January 13, 2015
11:00 AM
-
1:00 PM
Where: Science and Engineering Building 285 Old Westport Road, Dartmouth, MA
Cost: free
Description: TOPIC: QUALITY MODELING OF COMPRESSED IMAGES AND ITS APPLICATIONS IN WIRELESS NETWORKS
LOCATION: Lester W. Cory Conference Room, Science & Engineering Building (Group II), Room 213A
ABSTRACT:
This project intends to create No-Reference (NR) quality estimations for JPEG compressed images. Tuning a NR estimation model towards PSNR may not be suitable in summarizing NR quality measurements. This project investigated a computational and memory proficient NR quality evaluation model for JPEG compressed images; and examined subjective test outcomes to refine the model.
A short survey on existing models are presented at the beginning. An experimental approach was applied to improve identified weaknesses for one of compared models. The second part of the project provides a sophisticated and verified model by considering a group of images. Besides, the project studies the quality performance estimation for image transmissions over wireless networks, and establishes the relationship between the bit error rate and (Peak signal-to-noise ratio) PSNR. The project concludes that the model for NR image quality is feasible in wireless network applications.
NOTE: All ECE Graduate Students are ENCOURAGED to attend.
All interested parties are invited to attend.
Open to the public.
Advisor: Dr. Honggang Wang
Committee Members: Dr. Liudong Xing, Department of Electrical & Computer Engineering and Dr. Xiaoqin "Shelley" Zhang, Department of Computer and Information Science
LOCATION: Lester W. Cory Conference Room, Science & Engineering Building (Group II), Room 213A
ABSTRACT:
This project intends to create No-Reference (NR) quality estimations for JPEG compressed images. Tuning a NR estimation model towards PSNR may not be suitable in summarizing NR quality measurements. This project investigated a computational and memory proficient NR quality evaluation model for JPEG compressed images; and examined subjective test outcomes to refine the model.
A short survey on existing models are presented at the beginning. An experimental approach was applied to improve identified weaknesses for one of compared models. The second part of the project provides a sophisticated and verified model by considering a group of images. Besides, the project studies the quality performance estimation for image transmissions over wireless networks, and establishes the relationship between the bit error rate and (Peak signal-to-noise ratio) PSNR. The project concludes that the model for NR image quality is feasible in wireless network applications.
NOTE: All ECE Graduate Students are ENCOURAGED to attend.
All interested parties are invited to attend.
Open to the public.
Advisor: Dr. Honggang Wang
Committee Members: Dr. Liudong Xing, Department of Electrical & Computer Engineering and Dr. Xiaoqin "Shelley" Zhang, Department of Computer and Information Science
Contact:
ECE: Electrical & Computer Engineering Department 508.999.9164 http://www.umassd.edu/engineering/ece/
Topical Areas: General Public, University Community, Electrical and Computer Engineering