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.

Automated Detection of Mechanically Induced Bruise Areas in Golden Delicious Apples Using Fluorescence Imagery

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

Citation:  Transactions of the ASABE. 58(2): 215-225. (doi: 10.13031/trans.58.10578) @2015
Authors:   Yi-Chich Chiu, Xing-Liang Chou, Tony E. Grift, Mu-Te Chen
Keywords:   Adaptive binarization, Chlorophyll, Image processing, Non-destructive inspection.

Abstract. This study pursues the detection of bruised areas caused by mechanical impact on Golden Delicious apples using chlorophyll fluorescence imagery. When a fruit is impacted by a mechanical force and a bruise occurs, the chlorophyll nuclei inside the peel are damaged, which causes a reduction in fluorescence excitation compared to non-impacted areas. This difference allows automated detection of bruises and removal of damaged fruits to maintain optimal quality. In this study, fruit bruises were created using impact forces of 68.6, 88.2, and 107.8 N, and the resulting damage to chlorophyll nuclei inside the fruit peel was observed. Expansion of the area of damaged chlorophyll nuclei over time was observed using fluorescence imagery 0.5, 1, 2, and 4 h after the mechanical impact. This study employed a continuous capture of fruit fluorescence images and used MATLAB software for image processing and analysis. Edge contour noise was filtered by presetting a proper threshold, and the contour features of fruit bruises were distinguished using local adaptive binarization and a size filter. The experimental results showed that the mean recognition rate of a bruise 0.5 h after impact forces of 68.6, 88.2, and 107.8 N was as high as 86.7%, and the bruise recognition rate 1 h after impact was 100%. In conclusion, the fluoroscopic examination system for bruises was capable of detecting bruises accurately before the bruises were visible to the naked eye.

(Download PDF)    (Export to EndNotes)