Submitted to: Proceedings of SPIE
Publication Type: Proceedings
Publication Acceptance Date: September 26, 2005
Publication Date: October 27, 2005
Citation: Liu, Y., Chen, Y.R., Wang, C.Y., Chan, D.E., Kim, M.S. 2004. Development of hyperspectral imaging technique for the detection of chilling injury in cucumbers. In: Chen, Y.R., Tu, S.I, editors. Proceedings of Nondestructive Sensing for Food Safety, Quality, and Natural Resources. The International Society for Optical Engineering Conference, October 26-27, 2004, Philadelphia, Pennsylvania. p. 18-28. Interpretive Summary: Cucumbers are sensitive to chilling environments and are apt to suffer chilling injury from relatively short periods of time at low temperatures during storage and transportation process. 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 is time consuming and unsuitable for on-line real-time application. The development of fast and non-destructive 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 this study, we reported a new strategy to explore the hyperspectral images for the classification analysis. First, we determined the characteristic bands in visible and NIR region for chilling damaged cucumbers, and developed a number of classification methods for the discrimination of good cucumber skins from those of chilling injured ones. The results on Regions of Interests (ROIs) data revealed that both dual-band ratio algorithm (R811 nm / R756 nm) and principal component analysis (PCA) model from a narrow 733-848 nm spectral region can detect chilling injured skins with a great success of over 90%. Second, we applied the optimal dual-band ratio algorithm to analyze the hyperspectral images of cucumbers, and resultant images were well confirmed by additional processing method and analysis of cucumbers at various stages. This information is useful to vegetable packers, retailers, and researchers who are interested in applying imaging spectroscopy based safety/quality grading or classifying.
Technical Abstract: Hyperspectral images of cucumbers were acquired before and during cold storage treatment as well as during subsequent room temperature (RT) storage to explore the potential for the detection of chilling induced damage in whole cucumbers. Region of interest (ROI) spectral features of chilling injured areas, resulting from cold storage treatments at 0°C or 5 °C, showed a reduction in reflectance intensity during multi-day post-chilling periods of RT storage. Large spectral differences between good-smooth skins and chilling injured skins occurred in the 700-850 nm visible/NIR region. A number of data processing methods, including simple spectral band algorithms, second difference, and principal component analysis (PCA), were attempted to discriminate the ROI spectra of good cucumber skins from those of chilling injured skins. Results revealed that using either a dual-band ratio algorithm (Q811/756) or a PCA model from a narrow spectral region of 733-848 nm could detect chilling injured skins with a success rate of over 90%. Furthermore, the dual-band algorithm was applied to the analysis of images of cucumbers at different conditions, and the resultant images showed more correct identification of chilling injured spots than other processing methods.