Submitted to: Applied Engineering in Agriculture
Publication Type: Peer reviewed journal
Publication Acceptance Date: 9/20/2004
Publication Date: N/A
Citation: Interpretive Summary: Exposure to low temperature environment during the storage and transportation process could induce chilling injury in cucumbers. Symptoms of chilling injury develop very rapidly and might become sites for further fungal decay and bacterial infection after a few days at warmer temperatures. Such bacterial pathogens could be transmitted to humans by consumption of uncooked or mishandled cucumbers. Hence, one of the greatest concerns in vegetable industry is to detect chilling injury, ultimately providing the safety and quality guaranteed cucumber products for the consumers. Existing method in cucumber safety / quality assessment, such as human visual inspection, can provide reliable information about chilling injured portions. However, it is time consuming and unsuitable for on-line application. The development of fast, non-destructive, accurate, and on-line / at-line techniques is desired. Hyperspectral imaging spectroscopy could form the basis for such a technique due to the speed, non-invasive, and large sampling area. In the preceding paper, we analyzed region of interest (ROI) spectral features of good and chilling injured cucumber skins and found the great success of a dual-band algorithm (R811 nm / R756 nm) in discriminant analysis between good and injured skin classes. This is the second paper aiming to utilize the earlier findings to analyze the original hyperspectral images for the identification of chilling injury in cucumbers. The results revealed the great potential of the dual-band algorithm in the hyperspectral imaging analysis for the detection of chilling injury in cucumbers. This information is useful to vegetable packers, retailers, and researchers who are interested in applying both visible/NIR and imaging spectroscopy based safety/quality grading or classifying.
Technical Abstract: Hyperspectral images of cucumbers under different conditions were analyzed by the use of a simple dual-band algorithm (R811nm / R756 nm), which was identified from region of interest (ROI) data for the classification of good and injured skins. The performance of the dual-band algorithm in detection of chilling injury could not be evaluated quantitatively, due to the unknown number of chilling-injured spots. However, either other processing methods or testing of additional independent samples whose conditions were clearly evident could be used to validate the algorithm. The results revealed that the classification of chilling injured areas as performed by the dual-band algorithm was well confirmed by both other processing methods and the independent cucumber samples at different conditions. Generally, the dual-band algorithm images showed better discrimination than second difference images and PC images did. The algorithm could be implemented in a dual-band multispectral imaging system for cucumber safety and quality evaluation.