Moisture and total sugar content are two important internal qualities of Huizao. In order to explore their correlation with external qualities, a novel method of moisture and total sugar content analysis was proposed based on surface images. Firstly, five geometric features and seven texture features of Huizao were obtained to be the external quality indexes by digital image processing technology. Secondly, the wrinkle degree as an important index was extracted by marked watershed segmentation algorithm. According to the external quality the Huizao samples were grouped, and the moisture and total sugar content were determined through physical and chemical methods. Lastly, the moisture and total sugar content and twelve external indexes were all processed by step discriminatory analysis. Meanwhile, the regression models of moisture content with short diameter, contrast, and wrinkle degree and total sugar with wrinkle degree were established. The coefficients of the model were 0.9992 and 0.9978 respectively, and all the significance was less than 0.01, which show that the regression equation and regression coefficient effect are highly significant. The results indicate that the moisture and total sugar content of Huizao are greatly correlated with the wrinkle degree. The moisture and total sugar content are the highest when the wrinkle degree is at 2 to 3 grade, and they decrease gradually with the wrinkle degree increasing. Moisture content shows positive correlation with the size of Huizao. The results of model analysis agree well with the experimental results, which can provide valuable reference for improving Huizao grade diversity. Keywords: Huizao, step discriminatory analysis, moisture content, total sugar DOI: 10.25165/j.ijabe.20181104.3386 Citation: Zhang J X, Ma Q Q, He F, Qu F, Li W. Analysis of moisture and total sugar content of Huizao based on surface images. Int J Agric & Biol Eng, 2018; 11(4): 238-243.

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.