TY  - JOUR
TT  - Performance Comparison Between OpenCV Built in CPU and GPU Functions on Image Processing Operations
AU  - Hangün, Batuhan
AU  - Eyecioğlu, Önder
PY  - 2017
DA  - June
JF  - International Journal of Engineering Science and Application
JO  - IJESA
PB  - Nisantasi University
WT  - DergiPark
SN  - 2548-1185
SP  - 34
EP  - 41
VL  - 1
IS  - 2
KW  - Image Processing
KW  - CUDA
KW  - Parallel Processing
KW  - OpenCV
KW  - GPU
N2  - Image Processing is a specialized area of DigitalSignal Processing which contains various mathematical and algebraic operationssuch as matrix inversion, transpose of matrix, derivative, convolution, FourierTransform etc. Operations like those require higher computational capabilitiesthan daily usage purposes of computers. At that point, with increased imagesizes and more complex operations, CPUs may be unsatisfactory since they useSerial Processing by default. GPUs are the solution that come up with greaterspeed compared to CPUs because of their Parallel Processing/Computation nature.A parallel computing platform and programming model named CUDA was created byNVIDIA and implemented by the graphics processing units (GPUs) which wereproduced by them. In this paper, computing performance of some commonly usedImage Processing operations will be compared on OpenCV's built in CPU and GPUfunctions that use CUDA.
CR  - [1] Alan V. Oppenheim, Alan S. Willsky, S. Hamid, Signals and Systems (2nd Edition), Pearson 1996
CR  - [2] Alan V. Oppenheim, Alan S. Willsky, S. Hamid, Signals and Systems (2nd Edition), Pearson 1996
CR  - [3] SMITH, W, STEVEN, A Scientist’s and Engineers’s Guide to DSP. 1997
UR  - https://dergipark.org.tr/en/pub/ijesa/issue//312905
L1  - https://dergipark.org.tr/en/download/article-file/320019
ER  -