Cai, Zhen (2004) Automatic measurement of video quality using fuzzy logic. Masters thesis, Concordia University.
|PDF - Accepted Version|
Compression of digital video systems introduces artifacts (i.e., typical types of degradations), such as Blocking, Blurring, and Ringing. In this thesis, a new temporal artifact--'Flashing Blocks' is introduced. This new temporal artifact with other spatial artifacts is integrated into an equation to simulate the goodness of subjective ratings. In the past, linear mapping was used for this mapping. However, in this thesis, a non-linear mapping using Fuzzy Logic is proposed to create the mapping. In this thesis, the performance of these automatic metrics is evaluated by measuring the Mean Square Error between the measures predicted by humans and that predicted automatically. The simulation results indicate that the performance of the automatic metric using Fuzzy Logic is significantly better than those automatic metrics using linear mapping for MPEG-2 test video sequences.
|Divisions:||Concordia University > Faculty of Engineering and Computer Science > Electrical and Computer Engineering|
|Item Type:||Thesis (Masters)|
|Pagination:||xv, 111 leaves : ill. ; 29 cm.|
|Degree Name:||M.A. Sc.|
|Program:||Electrical and Computer Engineering|
|Thesis Supervisor(s):||Lynch, William E|
|Deposited By:||Concordia University Libraries|
|Deposited On:||18 Aug 2011 14:24|
|Last Modified:||18 Aug 2011 15:33|
Repository Staff Only: item control page