We use a few cookies

Essential cookies keep the library working. With your permission, we'd also like to use analytics to see what's useful and improve the experience. Read our Privacy Policy or Cookie Policy.

Skip to main content
Home/e-Resources/Artificial Intelligence & Machine Learning/Computer vision-based apple grading for golden delicious apples based on surface features
PeriodicalsArtificial Intelligence & Machine Learning

Computer vision-based apple grading for golden delicious apples based on surface features

Checking your access to this record.

Abstract & Overview

In this paper, a computer vision-based algorithm for golden delicious apple grading is proposed which works in six steps. Non-apple pixels as background are firstly removed from input images. Then, stem end is detected by combination of morphological methods and Mahalanobis distant classifier. Calyx region is also detected by applying K-means clustering on the Cb component in YCbCr color space. After that, defects segmentation is achieved using Multi-Layer Perceptron (MLP) neural network. In the next step, stem end and calyx regions are removed from defected regions to refine and improve apple grading process. Then, statistical, textural and geometric features from refined defected regions are extracted. Finally, for apple grading, a comparison between performance of Support Vector Machine (SVM), MLP and K-Nearest Neighbor (KNN) classifiers is done. Classification is done in two manners which in the first one, an input apple is classified into two categories of healthy and defected. In the second manner, the input apple is classified into three categories of first rank, second rank and rejected ones. In both grading steps, SVM classifier works as the best one with recognition rate of 92.5% and 89.2% for two categories (healthy and defected) and three quality categories (first rank, second rank and rejected ones), among 120 different golden delicious apple images, respectively, considering K-folding with K = 5. Moreover, the accuracy of the proposed segmentation algorithms including stem end detection and calyx detection are evaluated for two different apple image databases.

Cite this record

Payman Moallem, Alireza Serajoddin, Hossein Pourghassem (2016). Computer vision-based apple grading for golden delicious apples based on surface features. Information Processing in Agriculture, 4(1), 33–40. https://doi.org/10.1016/j.inpa.2016.10.003

Copy in another style

Moallem, P., Serajoddin, A., & Pourghassem, H. (2016). Computer vision-based apple grading for golden delicious apples based on surface features. Information Processing in Agriculture, 4(1), 33–40. https://doi.org/10.1016/j.inpa.2016.10.003
Author names are used as deposited, so check their order before you submit.

Metadata is harvested from open-access indexes and can be incomplete. Check a citation against the published version before relying on it — see our open access & attribution policy.