| Fresh peach fruits are susceptible to infection by several postharvest pathogens since they are typically picked in hot and rainy seasons.Their tender texture,appealing flavor,and abundant nutrition result in vulnerable to mechanical forces in its picking,transportation,and distribution process resulting in a great loss.The peaches are easy susceptibility to deterioration,while the flavor changes quickly within three to five days at ambient temperatures.Gray mold,soft rot and anthracnose caused by Botrytis cinerea,Rhizopus stolonifera,and Colletotrichum acutatum,respectively,are the major postharvest diseases of peaches.In order to avoid potential health risks,infected peaches must be identified before they are stored,sold or processed.Thus,there is a need for a rapid and reliable technique to detect and differentiate the pathogens of food or agricultural commodities that may cause severe outbreaks.Therefore,in this research,we selected the honey peaches as experimental material,and our objective was to investigate the hyperspectral imaging system for detection postharvest diseases of peaches.The contents and results are as follows:(1)The hyperspectral imaging system(HIS)was used to measure the spectral response of fungi inoculated otn potato dextrose agar plates.In this work,three methods for calculating HIS parameters,including the mean of the whole spectral response values covering the range of 400-1,000 nm5 the spectral response value of the wave peak at 716 nm,and the score of the first principal component of the whole spectral range of 400-1,000 nm using principal component analysis(PCA),were used to simulate the growth of fungi.The results showed that the coefficients of determination(R2)of simulation models for testing datasets of three fungi were 0.7223 to 0.9914,and the sum square error(SSE)and root mean square error(RMSE)were in a range of 2.03-53.40 × 10-4 and 0.011-0.756,respectively,based on the three methods.The correlation coefficients(R)between the HIS parameters and colony forming units of fungi were high with 0.887 to 0.957.In addition,fungi species can be discriminated by PCA and partial least squares discrimination analysis(PLSDA)based on the spectral information of the full wavelength range.The classification accuracy of the test dataset by PLSDA models for ftungi cultured for 36h were 97.5%among Botryis cinerea,Rhizopus stolonifer Colletotrichum acutatum,and the control.These supplied a new technique and useful information for flurther study into modeling the growth of fungi and detecting fruit spoilage caused by fungi based on HIS.(2)The spectral and imaging information of hyperspectral reflectance(400?1000 nm)was used to evaluate and classify three kinds of common diseases of peach.To reduce the large dimensionality of the hyperspectral imaging,Principal component analysis(PCA)was applied to analyse the whole wavelength images and the first principal component was selected to extract the imaging features and a total of 38 parameters were extracted as the imaging features for one sample.Three decayed stages(slight,moderate and severe decayed peaches)were considered for classification by partial least squares-discriminant analysis(PLS-DA)in this study.The results showed that,using spectral information(420 features),PLS-DA model showed the better classification results than the classification accuracy based on imaging features(38 features).The integrated infornation(478 features)using spectra and image showed the highest classification results for the three diseases,with accuracies of 85%,95%,and 95%for slight-decayed,moderate-decayed and severe-decayed samples,respectively.The results showed that the hyperspectral reflectance imaging technique is feasible for detecting different kinds of diseased peaches,especially at the moderate and severe decayed levels.(3)In order to detetermine the correlationship between hyperspectral imaging and quality indexes,a spatially-resolved reflectance hyperspectral imaging was investigated to caculate the the absorption coefficient(?a)and the reduced scattering coefficient(?s')during the rotten of peaches.the results show that light absorption is mainly related to the chemical composition and quality indexes(i.e.,chlorophylls,sugar,and water),while scattering is influenced by the structural properties(i.e.,cell struture,particle size,and cellular arrangement).The pearson linear correlation analysis was used for qualities indexes(chlorophyll,titratable acid,total phenolics and so on)and optical properties,while chlorophyll had the highest correlation with optical properties which can be used for further reseach of peach diseased detection(4)When pathogens infect fruit,chlorophyll as one of the important components related to fruit quality,decreased significantly.Here,the feasibility of hyperspectral imaging to determine the chlorophyll content thus distinguishing diseased peaches was investigated.Three optimal wavelengths(617 nm,675 nm,and 818 nm)were selected according to chlorophyll content via successive projections algorithm.Partial least square regression models were established to determine chlorophyll content.Three band ratios were obtained using these optimal wavelengths,which improved spatial details,but also integrates the information of chemical composition from spectral characteristics.The band ratio values were suitable to classify the diseased peaches with 98.75%accuracy and clearly show the spatial distribution of diseased parts.This study provides a new perspective for the selection of optimal wavelengths of hyperspectral imaging via chlorophyll content,thus enabling the detection of ffingal diseases in peaches.(5)A hyperspectral imaging system with a moving testbed was developed for detection of the disease caused by Rhizopus stolonifera in peaches.The all-around hyperspectral imaging of whole peach was obtained,which can identify the decayed area fully and is suitable for online monitoring.Three single-band images(709 nm,807 nm,and 874 nm)which were selected by statistics methods and an image segmentation algorithm were used for locating the decayed area of peach was developed based on band ratio image coupled with a simple thresholding method.The performance of image segmentation algorithm of the single-band images was evaluated.The detection accuracies of decayed peaches classified as‘sound','slight-decayed','moderate-decayed' and 'severe-decayed' were 99%,66.29%,100%and 100%,respectively.Then the spectral information was extracted from the decayed area to improve the detection accuracy.The six optical wavelengths were selected via SPA(successive projections algorithm)from the full spectral range.The distinguish accuracies of sound and decayed peaches were 100%.Results showed that the developed hyperspectral imaging method has the potential to be used for automatic detection of the fungal infection in peaches. |
PDF Full Text Request