Evaluation of image processing technique as an expert system in mulberry fruit grading based on ripeness level using artificial neural networks (ANNs) and support vector machine (SVM)

Azarmdel, Hossein; Jahanbakhshi, Ahmad; Mohtasebi, Seyed Saeid; Muñoz, Andrés Pedreño

doi:10.1016/j.postharvbio.2020.111201

Cited by 133 publications

(60 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Despite recent advancements in computer vision, only one research has been conducted to classify the ripening stages of mulberries [17]. In this work, traditional handcrafted features and two traditional machine learning classifiers, i.e., ANN and SVM, have been used.…”

Section: B Noveltymentioning

confidence: 99%

See 1 more Smart Citation

Detection of Mulberry Ripeness Stages Using Deep Learning Models

et al. 2021

View full text Add to dashboard Cite

Ripeness classification is one of the most challenging tasks in the postharvest management of mulberry fruit. The risks of microbial contamination and human error in manual sorting are significant; it may result in quality degradation and wasting of processed products. Due to advanced developments in computer vision and machine learning, automated sorting became possible. This study presents the results of developing and testing a computer vision-based application using convolutional neural networks (CNNs) for the classification of mulberry fruit ripening stages. To reduce the training cost and improve the accuracy of classification, transfer learning was used to fine-tune the CNN models. The CNN models in the test include DenseNet, Inception-v3, ResNet-18, ResNet-50, and AlexNet. Transfer learning was used to fine-tune the models and improve the accuracy of classification. The AlexNet and ResNet-18 networks exhibited the best performance with 98.32% and 98.65% overall accuracy for classifying the ripeness of white and black mulberries, respectively. Moreover, the performance of the models did not change when the data sets of both genotypes were mixed. The ResNet-18 was able to classify both genotype and ripeness from 600 fruit images in 2.36 min with an overall accuracy of 98.03%, which was superior to other architectures. It indicates that the model could be used for precise classification of the ripening stages of mulberries and other horticultural products, as a part of an automated sorting system.INDEX TERMS Convolutional neural network, computer vision, online detection, ripening classification, transfer learning.

show abstract

Section: B Noveltymentioning

confidence: 99%

“…Due to alternate ripening patterns (Fig. 1), harvest includes a mixture of fruits at various ripening levels [14], [17]. This inconsistency of the product negatively affects its commercial value and marketability [18].…”

Section: Introductionmentioning

confidence: 99%

Detection of Mulberry Ripeness Stages Using Deep Learning Models

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Fruits and vegetables are among the most important horticultural products that play an important role in providing human nutrition and health. This group of agricultural products is corruptible due to high moisture content and thus 5 to 50% of them spoil in the postharvest period (Azarmdel, Jahanbakhshi, Mohtasebi, & Muñoz, 2020; Jahanbakhshi, Abbaspour‐Gilandeh, Ghamari, & Heidarbeigi, 2019a; Jahanbakhshi & Salehi, 2019; Salehi, Taghizadeh‐Alisaraei, Jahanbakhshi, & Shahidi, 2018). Therefore, reducing agricultural product waste requires modifying the production chain from the garden or farm to the storage place and then the transportation and marketing processes.…”

Section: Introductionmentioning

confidence: 99%

Potato creep analysis during storage using experimental measurement and finite element method (FEM)

Shahgholi

Latifi

Jahanbakhshi

2020

J Food Process Engineering

Self Cite

View full text Add to dashboard Cite

Analysis of static forces has an important role in bulk storage of agricultural products. The forces exerted on individual fruits, vegetables, or grains cause mechanical damage to them and lead to their permanent deformation. By analyzing the forces involved, we can manage them with proper methods and prevent the creation of waste. In this research, by conducting experiments, the required parameters for potato samples were obtained and simulated through the finite element method under load. Creep and tension tests were conducted on a cylindrical potato sample with the diameter and height of 25 mm. Apparent shear modulus had been extracted over time and imported to the Abaqus 2016. Simulation results showed that the maximum tension of 0.061 MPa occurred in layers near the pressure plate. Tension concentration caused the maximum tension of 0.07 MPa in the center of the potato. In accordance with the created tension, maximum displacement of 0.35 mm occurred in contact layer with the pressure plate and by moving away from this plate, displacement decreased linearly and reached to zero at bottom layer. The results showed that measuring the forces in storage and knowing the forces applied to the product can be effective in controlling the storage quality of agricultural products and reducing waste. Practical Applications Analysis of static forces has important role in bulk storage of agricultural products. By analyzing the involving forces, they can be managed with proper methods and prevent the creation of waste. This paper found that maximum stress and damage occur at force inserted areas and in areas of tubers are in contact with external material like transporting and storage boxes. Then, it should be tried to fabricate new flexible and viscoelastic materials such as polymers which acts like tubers in contact areas to decrease tubers’ stress to minimum value at contact points. Also more attention should be paid to stress concentration that may occur inside tubers which can lead to crush and destroy the product. Stacking more tubers on storage which can increase inserted stress beyond the value that leads to stress concentration should be avoided.

show abstract

“…Selenium plays protective and antioxidant role in decreasing oxidative stress caused by temperature, drought, salinity, mechanical stress, UV radiation, pathogens, and heavy metals. Also, selenium ameliorates stress by increasing the antioxidant capacity of the plant through increasing the activity of enzymatic antioxidants and nonenzymatic antioxidants (Ahangarnezhad et al., 2019; Azarmdel et al., 2020; Cartes et al., 2010; Haghighi et al., 2016; Jahanbakhshi et al., 2018, 2019, 2020; Lin et al., 2012; Momeny et al., 2020; Pandey & Gupta, 2015; Qing et al., 2015; Yao et al., 2009).…”

Section: Introductionmentioning

confidence: 99%