Title :
A Vector Approach to Quality Assessment of Color Images
Author :
Russo, F. ; De Angelis, A. ; Carbone, P.
Author_Institution :
Dipt. di Elettrotec. Elettron. e Inf., Univ. of Trieste, Trieste
Abstract :
A full-reference method for objective assessment of image quality is presented. The approach aims at achieving an accurate characterization of the behavior of noise-reduction filters for color digital pictures. The proposed technique consists in the evaluation of a vector error whose components take into account key features such as noise cancellation and detail preservation affecting the luminance and chroma information of the image. Application examples dealing with different kinds of noise distributions are discussed. Results of computer simulations show that the proposed approach can be used to validate techniques for image denoising without the limitations of scalar image quality measurements and without resorting to visual inspection.
Keywords :
filtering theory; image colour analysis; image denoising; color digital picture; computer simulation; full-reference method; image denoising; image quality assessment; noise-reduction filter; vector approach; Application software; Color; Colored noise; Computer errors; Computer simulation; Digital filters; Image denoising; Image quality; Noise cancellation; Quality assessment; Full Reference methods; Image Quality Assessment; vector RMSE;
Conference_Titel :
Instrumentation and Measurement Technology Conference Proceedings, 2008. IMTC 2008. IEEE
Conference_Location :
Victoria, BC
Print_ISBN :
978-1-4244-1540-3
Electronic_ISBN :
1091-5281
DOI :
10.1109/IMTC.2008.4547149
