INTERNATIONAL JOURNAL of ENGINEERING SCIENCE AND APPLICATION Hangun and Eyecioglu, Vol.1, No.2, 2017 Performance Comparison Between OpenCV Built in CPU and GPU Functions on Image Processing Operations Batuhan Hangün* ‡ , Önder Eyecioğlu** *Department of Electrical and Electronics Engineering, Nişantaşı University, ISTANBUL ** Department of Computer Engineering, Nişantaşı University, ISTANBUL (batuhan.hangun, onder.eyecioglu {@nisantasi.edu.tr}) ‡ Hangun Batuhan, Department of Electrical and Electronics Engineerinig, Nisantasi University, Istanbul, Turkey, Tel: +90 530 972 20 31, batuhan.hangun@nisantasi.edu.tr Received: 15.05.2017 Accepted:23.06.2017 Abstract- Image Processing is a specialized area of Digital Signal Processing which contains various mathematical and algebraic operations such as matrix inversion, transpose of matrix, derivative, convolution, Fourier Transform etc. Operations like those require higher computational capabilities than daily usage purposes of computers. At that point, with increased image sizes and more complex operations, CPUs may be unsatisfactory since they use Serial Processing by default. GPUs are the solution that come up with greater speed compared to CPUs because of their Parallel Processing/Computation nature. A parallel computing platform and programming model named CUDA was created by NVIDIA and implemented by the graphics processing units (GPUs) which were produced by them. In this paper, computing performance of some commonly used Image Processing operations will be compared on OpenCV's built in CPU and GPU functions that use CUDA. Keywords- Image Processing, CUDA, Parallel Processing, OpenCV, GPU 1. Introduction A signal is a function that indicates how a variable change depending on another variable or variables. There are many physical phenomena which may be called as signals such as variation over time in capacitor voltage at an RLC circuit or human voice that attenuate with time or a room temperature at a particular spot etc. [1]. As it was said before, signals are defined mathematically as functions of one or more independent or dependent variables. An audio signal can be represented mathematically by amplitude as a function of time [2]. Concept of DSP is originated at 1960s and 1970s. Since computers were expensive at this period, applications of DSP were limited to some crucial areas. These areas were:  Radar and sonar  Oil Exploration  Medical Imaging  Discovery of Space