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

Digital images obtained from the video frames have an important role in different areas. Many image processing techniques have been applied to digital 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. However, the factors such as camera and environment cause differences among the consecutive frames. These differences cause images with oscillation. Statistical methods can be used to obtain images with less oscillation from multiple frames. In this paper, we developed a quality metric to compare the frames or images in accordance with the quantity of oscillation. A comparative study of statistical methods used to obtain the images with less oscillation from the video frames was presented. Images were obtained by using four statistical methods for the different numbers of frames. This study also focuses on evaluating how the statistical method choice affects the oscillation of images using the proposed quality metric and comparing the processing times of the methods.

PDF

___

[1] E. S. Gupta, and Y. Kaur, “Review of different histogram equalization based contrast enhancement techniques,” International Journal of Advanced Research in Computer and Communication Engineering, vol. 3, no. 7, 2014
[2] C. H. Hsia, T. C. Wu, and J. S. Chiang, “A new method of moving object detection using adaptive filter,” Journal of Real-Time Image Processing, vol. 13, no. 2, pp. 311-325, 2017.
[3] M. Szczepanski, “Fast spatio-temporal digital paths video filter,” Journal of Real-Time Image Processing, vol. 16, no. 2, pp. 477-489, 2019.
[4] J. Jasmine, and S. Annadurai, “Real time video image enhancement approach using particle swarm optimization technique with adaptive cumulative distribution function based histogram equalization,” Measurement, vol. 145, pp. 833-840, 2019.
[5] H. Okuhata, K. Takahashi, Y. Nozato, T. Onoye, and I. Shirakawa, “Video image enhancement scheme for high resolution consumer devices,” In 2008 3rd International Symposium on Communications, Control and Signal Processing, pp. 639-644, Mar. 2008.
[6] X. Tan, Y. Liu, C. Zuo, and M. Zhang, “A real-time video denoising algorithm with FPGA implementation for Poisson–Gaussian noise,” Journal of Real-Time Image Processing, vol. 13, no. 2, pp. 327-343, 2017.
[7] G. Anbarjafari, S. Izadpanahi, and H. Demirel, “Video resolution enhancement by using discrete and stationary wavelet transforms with illumination compensation,” Signal, Image and Video Processing, vol. 9, no. 1, pp. 87-92, 2015.
[8] P. Singh, R. Mukundan, and R. De Ryke, “Feature Enhancement in Medical Ultrasound Videos Using Contrast- Limited Adaptive Histogram Equalization,” Journal of Digital Imaging, pp. 1-13, 2019.
[9] P. S. Altares, A. R. I. Copo, Y. A. Gabuyo, A. T. Laddaran, L. D. P. Mejia, I. A. Policapio, E. A. G. Sy, H. D. Tizon, and A. M. S. D. Yao, “Elementary statistics: a modern approach,” Rex Bookstore Inc., Manila, Philippines, 2003.
[10] C. F. Lee, J. C. Lee, and A. C. Lee, “Statistics for business and financial economics,” Singapore: World Scientific, 2000.
[11] N. Bajpai, “Business statistics,” Pearson Education India, 2009.
[12] P. Singh, and R. Shree, “A comparative study to noise models and image restoration techniques,” Int. J. Comput. Appl., vol. 149, no. 1, pp. 18-27, 2016.
[13] P. Shivakumara, W. Huang, and C. L. Tan, “An efficient edge based technique for text detection in video frames,” The Eighth IAPR International Workshop on Document Analysis Systems, pp. 307-314, Sept. 2008.
[14] P. Shivakumara, W. Huang, T. Q. Phan, and C. L. Tan, “Accurate video text detection through classification of low and high contrast images,” Pattern Recognition, vol. 43, no. 6, pp. 2165-2185, 2010.
[15] H. Li, W. Lei, W. Zhang, and Y. Guan, “A joint optimization method of coding and transmission for conversational HD video service,” Computer Communications, vol. 145, pp. 243-262, 2019.