2011 | OriginalPaper | Buchkapitel
Scotopic Visual Image Mining Based on NR-IQAF
verfasst von : Fengbo Tian, Xiafu Lv, Jiaji Cheng, Zhengxiang Xie
Erschienen in: Computing and Intelligent Systems
Verlag: Springer Berlin Heidelberg
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
In this paper, a new image mining method is proposed considering the contrast resolution limitation of human vision under scotopic visual environment. First, a valid gray distribution of an image is taken from scotopic vision condition. Second, the gray values of a target image pixels are computed from the original image via Zadeh-X transformation. Third, a no reference image quality assessment function (NR-IQAF) is used to estimate the image after transformation. Experiments demonstrate that this method greatly improves the visual contrast and luminance of the image, so image quality and visual effects have been improved significantly after mining; in addition, the optimal quality image can be obtained by the NR-IQAF.