Anzeige
Erschienen in:
2018 | OriginalPaper | Buchkapitel
88. A No-Reference Quality Assessment Method of Color Image Based on Visual Characteristic
verfasst von : Ling Dong, Xianqiao Chen
Erschienen in: Information Technology - New Generations
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
With the advent of the information age, the image plays an increasingly important role in people’s daily work and lives. People’s requirements of image quality are increasing. In order to make the assessment result of image quality more in line with person’s subjective feeling, a improved no-reference quality assessment method of color image was presented. Firstly, divide the image into several blocks and calculate contrast of each block under the Lab color model, then take each block’s effect on the whole visual perception with masking effect into consideration, optimize the whole assessment result of image quality, to achieve the objective and subjective consistency. Using the images of several image databases and the given subjective scores of the images to do the experiment. The experimental results show that the presented method has a good consistency with subjective feelings of image quality, and it’s assessment result is more accurately compare to other methods.