Abstract

The degree of surface wrinkles on a dried jujube fruit (Ziziphus jujuba Mill.) is an important quality grading criterion. The aim of this research was to propose an image processing method based on the watershed segmentation to extract the wrinkle features of jujube fruits. Original images of jujube fruit taken under cyan light were transformed into grayscale images. The noise in these images was then removed by morphological reconstruction. The H-minima extended transformation was used to label the foreground of jujube fruit images after reconstruction, and the labeled foreground regions were segmented by a distance transform-based watershed algorithm. Then, the grayscale images were filtered with a local range filter. The segmentation function was obtained using the minima imposition method. Finally, a watershed segmentation was used to extract the wrinkle features of jujube fruits. Experiments on 304 images of jujube fruit showed that the accuracy of wrinkle-based grading obtained by the algorithm was 92.11%, which proved that this method could be used to classify jujube wrinkles. Keywords: feature extraction, watershed segmentation, image processing, jujube fruit, wrinkle, quality grading DOI: 10.25165/j.ijabe.20171004.2638 Citation: Zhang J X, Ma Q Q, Li W, Xiao T T. Feature extraction of jujube fruit wrinkle based on the watershed segmentation. Int J Agric & Biol Eng, 2017; 10(4): 165–172.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call