Fruit grading is an important step in postharvest processing. Based on the images of oranges, we can get those characters that describe the size and color of them. Then 16 features were used to grade the oranges. To the best of our knowledge, this is the first work that used the mean value of R, G, B, H, S, I and the variance of R, G, B, H, S, I together as parameters, and graded the oranges through Bayes inference method. Experimental result shows that our method is competitive.
Fruit grading is very important for promoting its additional value. We graded oranges based on its images. Four photos were taken from different view angles for each orange. Both RGB and HSI color model were utilized. We extracted a 28-dimensional feature which can describe the size and color of them. Then support vector machine was used to grade these oranges into four levels. Experimental result shows SVM has promising performance for orange grading.
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.