![](https://csdnimg.cn/release/download_crawler_static/10573492/bg11.jpg)
4 1 Introduction
In Chap. 3, we study the visual impact of the rendering process on the quality of
the rendered image. We present experimental results obtained from a path-tracing
renderer and illustrate the influence of several parameters (virtual scene and rendering
parameters) on the visual quality of the rendered image.
Chapter 4 introduces image quality evaluation using full-reference methods.
We present a conventional way to obtain noise attributes from computer-generated
images and also introduce the use of deep learning to automatically extract them.
We then present how to use Support Vector Machines (SVM) and Relevance Vector
Machines (RVM) as image quality metrics.
Chapter 5 introduces image quality evaluation using reduced-reference methods.
We present Fast Relevance Vector Machines (FRVM) and explain image quality
evaluation using FRVM and inductive learning. Both methods are then compared on
experimental results.
Chapter 6 introduces no-reference methods using fuzzy sets. We present the
Interval-Valued Fuzzy Set (IVFS) and an entropy based on IVFS. We then detail
an image noise estimation method which uses IVFS and presents promising experi-
mental results obtained with computer-generated images.
In conclusion, Chap. 7 summarizes the important notions presented in this book
and gives some perspectives.
References
Beghdadi A, Larabi M, Bouzerdoum A, Iftekharuddin K (2013) A survey of perceptual image
processing methods. Sig Process Image Commun 28:811–831
Carnet M, Callet PL, Barba D (2008) Objective quality assessment of color images based on a
generic perceptual reduced reference. Sig Process Image Commun 23(4):239–256
Delepoulle S, Bigand A, Renaud C (2012) A no-reference computer-generated images quality
metrics and its application to denoising. In: IEEE intelligent systems IS’12 conference, vol 1, pp
67–73
Farrugia J, Péroche B (2004) A progressive rendering algorithm using an adaptive perceptually
based image metric. Comput Graph Forum 23(3):605–614
Faugeras O (1979) Digital color image processing within the framework of a human visual model.
IEEE Trans ASSP 27:380–393
Ferzli R, Karam L (2005) No-reference objective wavelet based noise immune image sharpness
metric. In: International conference on image processing
Kajiya J (1986) The rendering equation. Comput Graph ACM 20(4):143–150
Lahoudou A, Viennet E, Haddadi M (2010) Variable selection for image quality assessment using
a neural network based approach. In: 2nd European workshop on visual information processing
(EUVIP), pp 45–49
Lahoudou A, Viennet E, Bouridane A, Haddadi M (2011) A complete statistical evaluation of
state of the art image quality measures. In: The 7th international workshop on systems, signal
processing and their applications, pp 219–222
Longhurst P, Debattista K, Chalmers A (2006) A GPU based saliency map for high-fidelity selective
rendering. In: AFRIGRAPH 2006 4th international conference on computer graphics. Virtual
reality, visualisation and interaction in Africa, pp 21–29
Mitchell D (1987) Generating antialiased images at low sampling densities. In: Proceedings of
SIGGRAPH’87, New York, NY, USA, pp 65–72