Detection of early decay in navel oranges by structured-illumination reflectance imaging combined with image enhancement and segmentation

Authors: LI, JIANGBO - Beijing Academy Of Agricultural Sciences; LU, YUZHEN - Mississippi State University; Lu, Renfu

Submitted to: Postharvest Biology and Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/15/2022
Publication Date: 10/29/2022
Citation: Li, J., Lu, Y., Lu, R. 2022. Detection of early decay in navel oranges by structured-illumination reflectance imaging combined with image enhancement and segmentation. Postharvest Biology and Technology. 196. Article 112162. https://doi.org/10.1016/j.postharvbio.2022.112162.
DOI: https://doi.org/10.1016/j.postharvbio.2022.112162

Interpretive Summary: Orange fruit are susceptible to disease infection during postharvest handling, which could result in significant product quality and thus economic loss to growers. Penicillum digitatum (P. digitatum) is one of the most important pathogens responsible for citrus decay. During early stages of the fungal development, the infected or decayed fruit exhibit few visual symptoms. Early detection and remove of these infected fruit is thus critical to ensure the quality and safety of the product delivered to the consumer. This study evaluated the feasibility of a new imaging technique, called structured-illumination reflectance imaging (SIRI), for early detection of navel oranges infected with the fungus of P. digitatum. Different from conventional imaging techniques which apply uniform illumination to the product items to be inspected, SIRI utilizes special patterns of illumination to enhance image resolution and contrast, while providing better control of light penetration in the sample via modulating the spatial frequency of the illuminating light. The technique can thus provide greatly improved capabilities of detecting subtle defects of fruit occurring at the surface or in the subsurface tissue layers, which would otherwise be difficult to detect by conventional imaging techniques. Images were acquired from 290 navel oranges five days after they had been inoculated with the fungus of P. digitatum, using an inhouse assembled SIRI system under patterned illumination at four different spatial frequencies of 0.05, 0.10, 0.15 and 0.20 cycles/mm and at three different wavelengths (690, 730, and 810 nm). Two sets of new images, called direct and alternating components (denoted as DC and AC respectively), were extracted from the acquired images. From the DC and AC images were obtained two additional sets of images, called ratio and corrected ratio images. Results showed that the AC images were able to reveal the decayed tissues in the navel orange. It was found that the wavelength of 810 nm and a spatial frequency of 0.20 cycles per mm were optimal for detection of the orange fruit with fungal infection. The corrected ratio images produced the best detection performance with an overall detection accuracy of over 97%, by using one of the three image segmentation methods. This study has demonstrated that when combined with appropriate image enhancement and processing methods, the SIRI technique is effective for the early detection of decay in citrus fruit.

Technical Abstract: Early detection and removal of decayed fruit is critical for reducing product and economic losses for the fruit industry. It is, however, challenging to detect tissue decay in the early stage of its development due to few visual symptoms. This study was intended to evaluate the feasibility of an emerging structured-illumination reflectance imaging (SIRI) technique for early detection of decay in navel oranges. Pattern images were acquired from navel oranges five days after the fruit had been inoculated with fungal spores of Penicillium digitatum (P. digitatum), one of the most important pathogens responsible for citrus decay, using an inhouse assembled multispectral imaging platform under phase-shifted sinusoidal illumination at four spatial frequencies (0.05, 0.10, 0.15 and 0.20 cycles mm-1) and three wavelengths (690, 730 and 810 nm). The pattern images were processed through demodulation to obtain direct component (DC) and amplitude component (AC) images for each wavelength and spatial frequency. The AC images were able to reveal decayed areas in the fruit. The wavelength of 810 nm and a spatial frequency of 0.20 cycles mm-1 were determined to be optimal for decayed tissue detection, based on quantitative assessment of the contrast between decayed and sound tissues in images. Moreover, the ratio image between the AC and DC images and the corrected ratio image, which was obtained by applying the image brightness transform to the ratio images, have showed improved defect contrast and background uniformity. Three image segmentation methods including watershed, Otsu and global thresholding were applied for segmenting decayed areas in the AC, ratio and corrected ratio images. The corrected ratio images produced the best detection performance with an overall detection accuracy of over 97%. This study has demonstrated that when combined with appropriate image enhancement and processing methods, the SIRI technique is effective for the early detection of decay in citrus fruit.