Pregled bibliografske jedinice broj: 956214
Computer Generated Image Alterations Database
Computer Generated Image Alterations Database // Proceedings ELMAR-2018 / Muštra, Mario ; Grgić, Mislav ; Zovko-Cihlar, Branka ; Vitas, Dijana (ur.).
Zagreb, 2018. str. 97-101 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 956214 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Computer Generated Image Alterations Database
Autori
Pul, Matija ; Vranješ, Mario ; Kaprocki, Zvonimir ; Stefanović, Dejan
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Proceedings ELMAR-2018
/ Muštra, Mario ; Grgić, Mislav ; Zovko-Cihlar, Branka ; Vitas, Dijana - Zagreb, 2018, 97-101
ISBN
978-953-184-244-0
Skup
60th International Symposium ELMAR-2018
Mjesto i datum
Zadar, Hrvatska, 16.09.2018. - 19.09.2018
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
Functionality Verification ; Image Database ; Image Alterations ; Full Reference ; Set-Top-Box
Sažetak
Modern user interfaces (UI) use animations and special effects to appear more interesting and appealing to consumers, such is the case for modern Set-Top-Boxes (STB). In order to provide their consumers with functional and reliable products, manufacturers are required to perform functionality verification (FV) of each product. Automated FV systems are becoming a prevailing method of FV due to manual FV becoming exceedingly time consuming as the devices become more complex. Generally, full reference (FR) image comparison between the device output image and the referent image is used in order to perform FV of device under test (DUT). Common methods for image comparison proved to be ineffective when comparing images captured from UIs containing animated objects or dynamic background. In order to provide manufacturers with high-end FV systems, it is necessary to develop new methods for image comparison capable of comparing images despite alterations caused by UI animations. Development of such algorithms requires large image databases which effectively simulate such image alterations. In this paper we present new Computer Generated Image Alterations Database (CGIAD) which contains 10000 test images with alterations caused by object transformations commonly used in UI animations (rotation, scaling, occlusion, and translation). CGIAD is freely available to the research community at http://www.rt-rk.com/other/CGIAD.html.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo
POVEZANOST RADA
Ustanove:
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek
Profili:
Mario Vranješ
(autor)