Authors: Milos Klima, Jiri Pazderak, Martin Bernas, Petr Pata, Jiri Hozman, Karel Roubik
Klima M, Pazderak J, Bernas M, Pata P, Hozman J, Roubik K. Objective and subjective image quality evaluation for security technology. In Proceedings IEEE 35th Annual 2001 International Carnahan Conference on Security Technology (Cat. No. 01CH37186) 2001 Oct 16 (pp. 108-114). IEEE.
Fulltext in PDF & fulltext download
Published in IEEE.
Download fulltext in PDF here: Objective-and-Subjective-Image-Quality-Evaluation-for-Security-Technology.pdf
The paper is devoted to the impacts of image compression algoritms on security image data. It compares three fundamentally different evaluation techniques of image – objective criteria, subjective criteria and identification. We have selected two typical security image data (a car plate and a face) with different initial quality and we applied three different compression techniques – two professional (JPEG and LuRaWave – LWF) and one implemented (Karhunen-Loeve . transform KLT) [l]. A set of compressed images differing in compression rate was derived from each original image data. Finally the MSE as an objective criterion, the subjective image quality according to the ITU-R Rec. 500 and the identification measure were evaluated and compared.
 Bovik A., Handbook of Image Processing, Academic Press, 2000
 Safranek R.J., Comparison of the coding efficiency of perceptual models, Human Vision, Visual Processing and Digital Displays, Proc. SPIE, 2179, 1995
Osberger, W.: Perceptual Vision Models for Picture Quality Assessment and Compression Applications. Doctoral Theses. Queensland University of Technology, 1999.
 ITU-R Recommendation BT.500-10 (2000), Methodology for the subjective assessment of the quality of the television pictures.
 ITU-R Recommendation BT.1129-2 (1998), Subjective assessment of standard definition digital television (SDTV) systems.
 Miano, J.: Compressed Image File Formats: JPEG, PNG, GIF, XBM, BMP (ACM Press). Addison-Wesley Longman, Inc., 1999. 264 p.