Click on “Download PDF” for the PDF version or on the title for the HTML version.


If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Mealiness Detection Using Supervised Locally Linear Embedding and Support Vector Machine

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2010 Pittsburgh, Pennsylvania, June 20 - June 23, 2010  1008915.(doi:10.13031/2013.29756)
Authors:   Qibing Zhu, Min Huang, Ginlin Zhao
Keywords:   Hyperspectral scattering, Mealiness, Supervised locally linear embedding, Support vector machine, Kennard-Stone algorithm, Fruit, Apple, Hardness, Juiciness, Classification.

Apple mealiness is a symptom of internal fruit disorder. Hyperspectral scattering, as a promising technique, was investigated for noninvasive measurement of apple mealiness. A supervised locally linear embedding (SLLE) coupled with support vector machine (SVM) was proposed to detect the mealiness in apples using hyperspectral scattering images. SLLE reveals the structure of the global non-linear by the local linear joint. This method belongs to manifold learning methods and it can effectively calculate high-dimensional input data embedded in a low-dimensional space manifold. Support vector machine (SVM) was used to develop models classifying nonmealy apple and mealy apple. The classification results from SLLE-SVM were compared with those obtained using the traditional SVM. The results show that the classification accuracy of the calibration models obtained with the SLLE-SVM was higher than that with SVM and the accuracy of the validation models was improved. It is expected that SLLE-SVM method would provide an effective classification method for apple mealiness detection using hyperspectral scattering technique.

(Download PDF)    (Export to EndNotes)