This paper presents a research over possibilities to evaluate a cut surface of white brined cheese by images analysis. Samples from seven trademarks of Bulgarian white cheese in brine are evaluated by experts and their cut surfaces are captured with digital camera. A Java application for color images processing in HSI color space is developed. The application executes multilevel thresholding and produces grayscale images with four colors – white, black, light gray and dark gray. The images of all tested cheese samples are processed with this application and there are calculated ratios of pixels with the same color to all pixels in the processed images (Kdiv for white, black, light gray and dark gray colors). The cut surfaces of cheese samples are evaluated by experts and it is performed a correlation analysis between experts’ estimation and the coefficients Kdiv. The results show that there are a significant correlation between experts’ estimation and the pixels with dark gray color (their coefficient Kdiv) in the processed images.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.