Jiangbo Li

Quality and safety assessment of food and agricultural products by hyperspectral fluorescence imaging

Hyperspectral fluorescence imaging (HSFI) is potentially useful for assessing food and agricultural products, because it combines the merits of both hyperspectral imaging and fluorescence spectroscopy. This paper provides an introduction to HSFI: the principle and components of HSFI, calibration and image processing are described. In addition, recent advances in the application of HSFI to food and agricultural product assessment are reviewed, such as contaminant detection, constituent analysis and quality evaluation. Finally, current limitations and likely future development trends are discussed.

Hyperspectral reflectance imaging for detecting citrus canker based on dual-band ratio image classification method

Citrus are one of the major fruit produced in China. Most of this production is exported to Europe for fresh consumption, where consumers increasingly demand best quality. Citrus canker is one of the most devastating diseases that threaten peel of most commercial citrus varieties. The aim of this research was to investigate the potential of using hyperspectral imaging technique for detecting canker lesions on citrus fruit. Navel oranges with cankerous, normal and various common diseased skin conditions including wind scar, thrips scarring, scale insect, dehiscent fruit, phytotoxicity, heterochromatic stripe, and insect damage were studied. The imaging system (400-1000 nm) was established to acquire reflectance images from samples. Region of interest (ROI) spectral feature of various diseased peel areas was analyzed and characteristic wavebands (630, 685, and 720 nm) were extracted. The dual-band reflectance ratio (such as Q720/685) algorithm was performed on the hyperspectral images of navel oranges for differentiating canker from normal fruit skin and other surface diseases. The overall classification success rate was 96.84% regardless of the presence of other confounding diseases. The presented processing approach overcame the presence of stem/navel on navel oranges that typically has been a problematic source for false positives in the detection of defects. Because of the limited sample size, delineation of an optimal detection scheme is beyond the scope of the current study. However, the results showed that two-band ratio (Q685/630) along with the use of a simple threshold value segmentation method for discriminating canker on navel oranges from other peel diseases may be feasible.

Study on Detection Method for Cut Roses Based on Machine Vision

Recently, research of detection and grading of cut flower is few. In this study, the detection algorithms of stem-length, diameter, curvature and bud opening degree for cut roses were proposed. The stem-length was computed by scanning and searching the highest and lowest point of cut roses. The stem was extracted using morphology method, then the average diameter was obtained by the diameter of the top and bottom. The algorithm based on calculating anti-cosine angle was put forward to estimate curvature, and projected area and length-width ratio ware utilized to measure cut rose opening degree. Finally, a linear regression method was used for developing prediction models of cut rose stem-length. In this research, sixty cut rose samples were used, and the results showed that the coefficient of determination R2 was 0.9848 and the average deviation was 0.61 cm between actual measurement values and experimental detection valves of stem-length.