2017 Volume 19 Issue 3 Pages 103-108
We developed a method to evaluate the glossiness and whiteness of cooked rice using image analysis software. Appearance images of cooked rice, just after cooking, were taken by a digital camera. Feature points of the images were detected using OpenCV, and the number of these was used as an index of the glossiness of cooked rice. Also, b* values (the color-opponent dimensions in L*a*b* color space) were calculated for each pixel of the image, and the average value was used as an index of the whiteness of cooked rice. These glossiness and whiteness values obtained by image analysis were significantly correlated to the values evaluated by sensory tests using 11 varieties. The software was able to analyze images that contain at least 9 million pixels. The image analysis evaluated the glossiness and whiteness of cooked rice independently of each other, but in sensory tests, a positive correlation was observed.
