Comparison of Statistical Methods for Obtaining Image from Video Frames Based on Development of Quality Metric

Authors : Murat Alparslan GÜNGÖR

Pages : 741-750

Doi:10.16984/saufenbilder.760892

View : 27 | Download : 10

Publication Date : 2021-06-30

Article Type : Research Paper

Abstract :Digital images obtained from the video frames have an important role in different areas. Many image processing techniques have been applied to these images for different purposes such as edge detection. For a better image processing application, it is very important to obtain images with less oscillation from the video. Depending on the camera and environmental conditions, there are differences between consecutive frames. This means images with oscillation. Multiple frames can be used with different statistical methods to obtain images with less oscillation. In this paper, we developed a quality metric to compare the frames or images according to the amount of oscillation. Then a comparative study of statistical methods used to obtain the images with less oscillation from the video frames was presented. Images were obtained using four statistical methods for the different numbers of frames. This study also aims to evaluate how the choice of statistical method affects the oscillation of images using the developed quality metric and to compare the processing times of the methods.
Keywords : Video frame, Statistics, Image Quality Assessment