| （英） |
When color images are converted to grayscale images, color combinations that are easily distinguishable in the color image may be difficult to discriminate in a grayscale image represented by luminance components. For this reason, various color to grayscale conversion methods have been proposed. However, these methods have several problems, such as a loss of the original image's visual appearance, high computational cost, and a decline in image quality due to excessive enhancement for color discrimination. To address these problems, we propose a fast and effective color to grayscale conversion method. In the proposed method, a corrected luminance is obtained by adding values for color correction to the luminance value of the original image. The values for color correction are calculated by multiplying color information lost in luminance conversion, scores obtained by performing principal component analysis (PCA) on a chromaticity coordinate, and a parameter based on pixel value differences of the original image. In the experiments, we demonstrate the effectiveness of the proposed method through qualitative and quantitative evaluations. |