<title>Human vision model for image quality evaluation suitable for smart imager implementation</title>

Abstract

ABSTRACT This article deals with image quality evaluation ofthe compressed images especially for compression format JPEG 2000.It shows evaluation of selected test images (scene with: textures, details, text, color of face, etc.) using selected methods:subjective testing as the reference method, objective testing and two designed human vision models. At the end articlecompares results ofthese methods.Keywords: Image quality testing, human vision system model. 1. INTRODUCTION One ofthe main reasons ofimage quality evaluation is introduction and employment ofimage compression methods andthen corresponding formats.The first approach to the image quality evaluation is subjective quality testing (e.g. DSIS - Double Stimulus ImpairmentScale, DSCQS - Double Stimulus Continuous Quality Scale, SCM - Stimulus Comparison Method, SSM - Single Stimulus Method, SSCQM — Single Stimulus Continuous Quality Evaluation), which is based on many observers that evaluate image quality. These tests are time demanding, expensive and they have a very strict definition of the