Detection of early decay in peaches by structured-illumination reflectance imaging

Authors: SUN, YE - Nanjing Agricultural University; Lu, Renfu; LU, YUHZEN - Michigan State University; TU, KANG - Nanjing Agricultural University; PAN, LEIQING - Nanjing Agricultural University

Submitted to: Postharvest Biology and Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 1/21/2019
Publication Date: 5/1/2019
Citation: Sun, Y., Lu, R., Lu, Y., Tu, K., Pan, L. 2019. Detection of early decay in peaches by structured-illumination reflectance imaging. Postharvest Biology and Technology. 151:68-78. https://doi.org/10.1016/j.postharvbio.2019.01.011.
DOI: https://doi.org/10.1016/j.postharvbio.2019.01.011

Interpretive Summary: Peaches are susceptible to fungal infection after harvest, and detection of the symptom at early stage is critical to reducing economic loss for the industry, but is challenging because the symptom is not visible at the surface of infected fruit. In this research, a newly developed imaging technique, called structured-illumination reflectance imaging (SIRI), was used for detecting disease-infected peaches. Six hundred peaches, 300 each of two varieties (‘Redstar’ and ‘Ivory Princess’), were used in the experiment. The peaches were inoculated with Rhizopus stolonifer fungi, one of the main postharvest pathogens in peaches, and images were then taken from three groups of peaches at 24, 48 and 72 hours after the inoculation for seven wavelengths between 690 nm and 810 nm with the illumination of three spatial frequencies (i.e., 60, 100, and 150 cycles/m). Decomposed from the SIRI images were two sets of images, direct component (DC) and alternating component (AC). DC images are equivalent to the ones acquired under uniform, diffuse illumination, while AC images are unique to the SIRI technique and can reveal some subsurface features that are not visible from DC images. Three image processing algorithms (i.e., watershed, partial least squares discriminant analysis and convolutional neural network) were used to classify normal and disease-infected peaches. Results showed that AC images performed much better than DC images for all three algorithms. Among the three algorithms, the convolutional neural network algorithm for the AC images of 730 nm and 100 cycles/m frequency achieved the best detection rate of 98.6% for all peach samples, and it also demonstrated superior performance for detecting early decayed peaches with non-visible disease infection symptom at a detection rate of 97.6%. This study has shown that SIRI, coupled with an appropriate image classification method, can be effective for early disease detection of peaches.

Technical Abstract: Peaches are susceptible to fungal infection after harvest, and detection of the symptom at early stage is critical to reducing economic loss for the industry, but is challenging because the symptom is not visible at the surface of infected fruit. This research was therefore aimed to develop a non-destructive and accurate method, based on structured-illumination reflectance imaging (SIRI), for detection of early fungal infection in peaches. Patterned spectral images for seven wavelengths between 690 nm and 810 nm were acquired from 600 peaches of different decayed levels, using a multispectral SIRI system, under sinusoidally-modulated illumination at the spatial frequencies of 60, 100 and 150 cycles per meter. The resultant direct component (DC) images, which are equivalent to images acquired under uniform, diffuse illumination, could not reveal the slightly diseased symptom for peaches, but the symptom was visible from the alternating component (AC) images and ratio images calculated from the AC and DC images for the three frequencies. Watershed algorithm and partial least squares discriminant analysis were used for classification of diseased peaches based on the AC and ratio images, which achieved detection rates in the range of 65%-87%. Consistently better detections of diseased peaches were achieved with the AC images at the wavelength of 730 nm and the spatial frequency of 100 cycles/m. The pixel-based convolutional neural network for the AC images of 730 nm and 100 cycles/m frequency achieved an excellent detection rate of 98.6% for all peach samples, and it also demonstrated superior performance for detecting early decayed peaches with non-visible disease infection symptom at a detection rate of 97.6%. For comparison, detection rates of diseased peaches by the three classification methods for the DC images were consistently lower. This study has shown that SIRI, coupled with an appropriate image classification method, can be effective for early disease detection of peaches.