Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification Network

Disease has always been one of the main reasons for the decline of apple quality and yield, which directly harms the development of agricultural economy. Therefore, precise diagnosis of apple diseases and correct decision making are important measures to reduce agricultural losses and promote economic growth. In this paper, a novel Multi-scale Dense classification network is adopted to realize the diagnosis of 11 types of images, including healthy and diseased apple fruits and leaves. The diagnosis of different kinds of diseases and the same disease with different grades was accomplished. First of all, to solve the problem of insufficient images of anthracnose and ring rot, Cycle-GAN algorithm was applied to achieve dataset expansion on the basis of traditional image augmentation methods. Cycle-GAN learned the image characteristics of healthy apples and diseased apples to generate anthracnose and ring rot lesions on the surface of healthy apple fruits. The diseased apple images generated by Cycle-GAN were added to the training set, which improved the diagnosis performance compared with other traditional image augmentation methods. Subsequently, DenseNet and Multi-scale connection were adopted to establish two kinds of models, Multi-scale Dense Inception-V4 and Multi-scale Dense Inception-Resnet-V2, which facilitated the reuse of image features of the bottom layers in the classification neural networks. Both models accomplished the diagnosis of 11 different types of images. The classification accuracy was 94.31 and 94.74%, respectively, which exceeded DenseNet-121 network and reached the state-of-the-art level.

Effectiveness of Low-Dose Continuous Gaseous Ozone in Controlling Listeria innocua on Red Delicious Apples During 9-Month Commercial Cold Storage

This study aimed to investigate the effects of low-dose continuous ozone gas in controlling Listeria innocua and quality attributes and disorders of Red Delicious apples during long-term commercial cold storage. Red Delicious apples were inoculated with a three-strain L. innocua cocktail at ∼6.2 log10 CFU/apple, treated with or without 1-methylcyclopropene, and then subjected to controlled atmosphere (CA) storage with or without continuous gaseous ozone in a commercial facility for 36 weeks. Uninoculated Red Delicious apples subjected to the above storage conditions were used for yeast/mold counts and quality attributes evaluation. The 36 weeks of refrigerated air (RA) or CA storage caused ∼2.2 log10 CFU/apple reduction of L. innocua. Ozone gas application caused an additional > 3 log10 CFU/apple reduction of L. innocua compared to RA and CA storage alone. During the 36-week CA storage, low-dose continuous gaseous ozone application significantly retarded the growth of yeast/mold, delayed apple firmness loss, and had no negative influence on ozone burn, lenticel decay, russet, CO2 damage, superficial scald, and soft scald of Red Delicious apples compared to CA-alone storage. In summary, the application of continuous low-dose gaseous ozone has the potential to control Listeria on Red Delicious apples without negatively influencing apple quality attributes.

Salicylic acid and nutrient immersion to maintain apple quality and bioactive compounds in postharvest

The world production of apples in the 2019 cycle reached 7´620,288 tonnes. For marketing purposes and to supply the demand, apple fruits need to be stored for different periods under refrigerated conditions. However, in the market, the shelf life of the fruit is short, the quality decreases in postharvest due to the dynamic changes of its physicochemical properties, which cannot be stopped, but can be slowed down to improve its shelf life. Postharvest treatments by immersing apple fruit in salicylic acid (SA) and nutrients are an innovative technological alternative to maintain their quality. In this study, 5 concentrations were tested for the immersion of apple fruits cv ‘Golden Delicious’, using a 56 factorial arrangement delimited to 25 treatments, using the Taguchi L25 structure: SA 0 - 1.440 mM, potassium (K) 0 - 2.250, calcium (Ca) 0 - 31.500 mM, cobalt (Co) 0 - 0.180 mM, molybdenum (Mo) 0 - 0.0900 mM and magnesium (Mg) 0 - 0.0900 mM. The study was conducted in the municipality of Cuauhtémoc, Chihuahua, Mexico. After 7 months of storage and 13 days of shelf life, the combination of K, Ca, SA and Co with the appropriate concentration values can maintain the quality variables and bioactive compounds at the desired optimum. It is concluded that the quality variables; firmness, juice percentage, juice density, titratable acidity and total soluble solids and the bioactive compounds; total phenols and antioxidant capacity can be maintained at the desired optimum.

Apple quality identification and classification by image processing based on convolutional neural networks

This work researched apple quality identification and classification from real images containing complicated disturbance information (background was similar to the surface of the apples). This paper proposed a novel model based on convolutional neural networks (CNN) which aimed at accurate and fast grading of apple quality. Specific, complex, and useful image characteristics for detection and classification were captured by the proposed model. Compared with existing methods, the proposed model could better learn high-order features of two adjacent layers that were not in the same channel but were very related. The proposed model was trained and validated, with best training and validation accuracy of 99% and 98.98% at 2590th and 3000th step, respectively. The overall accuracy of the proposed model tested using an independent 300 apple dataset was 95.33%. The results showed that the training accuracy, overall test accuracy and training time of the proposed model were better than Google Inception v3 model and traditional imaging process method based on histogram of oriented gradient (HOG), gray level co-occurrence matrix (GLCM) features merging and support vector machine (SVM) classifier. The proposed model has great potential in Apple’s quality detection and classification.

Application of a MOGA Algorithm and ANN in the Optimization of Apple Drying and Rehydration Processes

The aim of the study was to estimate the optimal parameters of apple drying and the rehydration temperature of the obtained dried apple. Conducting both processes under such conditions is aimed at restoring the rehydrated apple to the raw material properties. The obtained drying parameters allow the drying process to be carried out in a short drying time (DT) and at low energy consumption (EC). The effect of air velocity (vd), drying temperature (Td), characteristic dimension (CD), and rehydration temperature (Tr) on rehydrated apple quality was studied. Quality parameters of the rehydrated apple as: color change (CC), mass gain ratio (MG), solid loss ratio (SL), volume gain ratio (VG) together with DT and EC were taken into consideration. The artificial neural network was used for modeling of rehydrated apple quality parameters, DT, and EC. A multi-objective genetic algorithm was developed in order to optimize parameters of the drying and rehydration processes. The simultaneous minimization of CC, SL, DT, EC, and the maximization of MG and VG were considered with the following drying and rehydration processes parameters: Td: 50–70 °C, vd: 0.01–2 m/s, Tr: 20–70 °C. The best solution has been found at drying temperature 56.1 °C, air velocity 1.3 m/s, characteristic dimension 2.0 mm, and rehydration temperature 59.2 °C. This apple drying and rehydration resulted in MG = 3.51, SL = 0.57, VG = 4.77, CC = 11.2, DT = 5.4 h, EC = 159.8 GJ/kg. The parameters of apple drying and rehydration processes can be recommended for the industry application.

Apple Quality Identification and Classification by Computer Vision Based on Deep Learning

This work researched apple quality identification and classification from real images containing complicated disturbance information (background was similar to the surface of the apples). This paper proposed a novel model based on Convolutional Neural Networks (CNN) which aimed at accurate and fast grading of apple quality. The proposed model was trained and validated, with best training and validation accuracy of 99% and 98.98% at 2590th and 3000th step, respectively. Two other methods, which were Google Inception v3 model and traditional imaging process method, were also used for apple quality classification. The greatest training accuracy of the Google Inception v3 model was 92% with 91.2% validation accuracy. The 78.14% accuracy was obtained by traditional method based on histogram of oriented gradient (HOG) and gray level co-occurrence matrix (GLCM) features merging and support vector machine (SVM) classifier. The three models were tested using independent 300 apples testing set, getting accuracy of 95.33%, 91.33%, and 77.67%, respectively. The results showed that the proposed model was more helpful and accurate for classification of apple quality. Furthermore, the training times of three methods were 27, 51, and 287 minutes, respectively. The proposed model can be considered a cost-effective method for fast grading of apple quality.