國立虎尾科技大學 |

Image quality assessment of computer-generated images = based on machine learning and soft computing /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Image quality assessment of computer-generated images/ by Andre Bigand ... [et al.].
其他題名:	based on machine learning and soft computing /
其他作者:	Bigand, Andre.
出版者:	Cham :Springer International Publishing : : 2018.,
面頁冊數:	xiv, 88 p. :ill., digital ; : 24 cm.;
Contained By:	Springer eBooks
標題:	Computer graphics. -
電子資源:	http://dx.doi.org/10.1007/978-3-319-73543-6
ISBN:	9783319735436

Image quality assessment of computer-generated images = based on machine learning and soft computing /
Image quality assessment of computer-generated imagesbased on machine learning and soft computing /[electronic resource] :by Andre Bigand ... [et al.]. - Cham :Springer International Publishing :2018. - xiv, 88 p. :ill., digital ;24 cm. - SpringerBriefs in computer science,2191-5768. - SpringerBriefs in computer science..

Introduction -- Monte-Carlo Methods for Image Synthesis -- Visual Impact of Rendering on Image Quality -- Full-reference Methods and Machine Learning -- No-reference Methods and Fuzzy Sets -- Reduced-reference Methods -- Conclusion.

Image Quality Assessment is well-known for measuring the perceived image degradation of natural scene images but is still an emerging topic for computer-generated images. This book addresses this problem and presents recent advances based on soft computing. It is aimed at students, practitioners and researchers in the field of image processing and related areas such as computer graphics and visualization. In this book, we first clarify the differences between natural scene images and computer-generated images, and address the problem of Image Quality Assessment (IQA) by focusing on the visual perception of noise. Rather than using known perceptual models, we first investigate the use of soft computing approaches, classically used in Artificial Intelligence, as full-reference and reduced-reference metrics. Thus, by creating Learning Machines, such as SVMs and RVMs, we can assess the perceptual quality of a computer-generated image. We also investigate the use of interval-valued fuzzy sets as a no-reference metric. These approaches are treated both theoretically and practically, for the complete process of IQA. The learning step is performed using a database built from experiments with human users and the resulting models can be used for any image computed with a stochastic rendering algorithm. This can be useful for detecting the visual convergence of the different parts of an image during the rendering process, and thus to optimize the computation. These models can also be extended to other applications that handle complex models, in the fields of signal processing and image processing.

ISBN: 9783319735436

Standard No.: 10.1007/978-3-319-73543-6doiSubjects--Topical Terms:

561602
Computer graphics.

LC Class. No.: T385

Dewey Class. No.: 006.6

Image quality assessment of computer-generated images = based on machine learning and soft computing /
LDR:02883nam a2200325 a 4500 001 924690
003 DE-He213
005 20180309102127.0
006 m d
007 cr nn 008maaau
008 190625s2018 gw s 0 eng d
020 $a 9783319735436 $q (electronic bk.)
020 $a 9783319735429 $q (paper)
024 7 $a 10.1007/978-3-319-73543-6 $2 doi
035 $a 978-3-319-73543-6
040 $a GP $c GP
041 0 $a eng
050 4 $a T385
072 7 $a UYQV $2 bicssc
072 7 $a COM016000 $2 bisacsh
082 0 4 $a 006.6 $2 23
090 $a T385 $b .I31 2018
245 0 0 $a Image quality assessment of computer-generated images $h [electronic resource] : $b based on machine learning and soft computing / $c by Andre Bigand ... [et al.].
260 $a Cham : $c 2018. $b Springer International Publishing : $b Imprint: Springer,
300 $a xiv, 88 p. : $b ill., digital ; $c 24 cm.
490 1 $a SpringerBriefs in computer science, $x 2191-5768
505 0 $a Introduction -- Monte-Carlo Methods for Image Synthesis -- Visual Impact of Rendering on Image Quality -- Full-reference Methods and Machine Learning -- No-reference Methods and Fuzzy Sets -- Reduced-reference Methods -- Conclusion.
520 $a Image Quality Assessment is well-known for measuring the perceived image degradation of natural scene images but is still an emerging topic for computer-generated images. This book addresses this problem and presents recent advances based on soft computing. It is aimed at students, practitioners and researchers in the field of image processing and related areas such as computer graphics and visualization. In this book, we first clarify the differences between natural scene images and computer-generated images, and address the problem of Image Quality Assessment (IQA) by focusing on the visual perception of noise. Rather than using known perceptual models, we first investigate the use of soft computing approaches, classically used in Artificial Intelligence, as full-reference and reduced-reference metrics. Thus, by creating Learning Machines, such as SVMs and RVMs, we can assess the perceptual quality of a computer-generated image. We also investigate the use of interval-valued fuzzy sets as a no-reference metric. These approaches are treated both theoretically and practically, for the complete process of IQA. The learning step is performed using a database built from experiments with human users and the resulting models can be used for any image computed with a stochastic rendering algorithm. This can be useful for detecting the visual convergence of the different parts of an image during the rendering process, and thus to optimize the computation. These models can also be extended to other applications that handle complex models, in the fields of signal processing and image processing.
650 0 $a Computer graphics. $3 561602
650 0 $a Machine learning. $3 561253
650 0 $a Soft computing. $3 562548
650 1 4 $a Computer Science. $3 593922
650 2 4 $a Computer Imaging, Vision, Pattern Recognition and Graphics. $3 671334
650 2 4 $a Computational Intelligence. $3 768837
700 1 $a Bigand, Andre. $3 1201869
710 2 $a SpringerLink (Online service) $3 593884
773 0 $t Springer eBooks
830 0 $a SpringerBriefs in computer science. $3 883114
856 4 0 $u http://dx.doi.org/10.1007/978-3-319-73543-6
950 $a Computer Science (Springer-11645)