Recognition of Defective Carrots Based on Deep Learning and Transfer Learning

Surface Defect Detection System for Carrot Combine Harvest Based on Multi-Stage Knowledge Distillation

Carrots are a type of vegetable with high nutrition. Before entering the market, the surface defect detection and sorting of carrots can greatly improve food safety and quality. To detect defects on the surfaces of carrots during combine harvest stage, this study proposed an improved knowledge distillation network structure that took yolo-v5s as the teacher network and a lightweight network that replaced the backbone network with mobilenetv2 and completed channel pruning as a student network (mobile-slimv5s). To make the improved student network adapt to the image blur caused by the vibration of the carrot combine harvester, we put the ordinary dataset Dataset (T) and dataset Dataset (S), which contains motion blurring treatment, into the teacher network and the improved lightweight network, respectively, for learning. By connecting multi-stage features of the teacher network, knowledge distillation was carried out, and different weight values were set for each feature to realize that the multi-stage features of the teacher network guide the single-layer output of the student network. Finally, the optimal lightweight network mobile-slimv5s was established, with a network model size of 5.37 MB. The experimental results show that when the learning rate is set to 0.0001, the batch size is set to 64, and the dropout is set to 0.65, the model accuracy of mobile-slimv5s is 90.7%, which is significantly higher than other algorithms. It can synchronously realize carrot harvesting and surface defect detection. This study laid a theoretical foundation for applying knowledge distillation structures to the simultaneous operations of crop combine harvesting and surface defect detection in a field environment. This study effectively improves the accuracy of crop sorting in the field and contributes to the development of smart agriculture.

Utilisation of Deep Learning with Multimodal Data Fusion for Determination of Pineapple Quality Using Thermal Imaging

Fruit quality is an important aspect in determining the consumer preference in the supply chain. Thermal imaging was used to determine different pineapple varieties according to the physicochemical changes of the fruit by means of the deep learning method. Deep learning has gained attention in fruit classification and recognition in unimodal processing. This paper proposes a multimodal data fusion framework for the determination of pineapple quality using deep learning methods based on the feature extraction acquired from thermal imaging. Feature extraction was selected from the thermal images that provided a correlation with the quality attributes of the fruit in developing the deep learning models. Three different types of deep learning architectures, including ResNet, VGG16, and InceptionV3, were built to develop the multimodal data fusion framework for the classification of pineapple varieties based on the concatenation of multiple features extracted by the robust networks. The multimodal data fusion coupled with powerful convolutional neural network architectures can remarkably distinguish different pineapple varieties. The proposed multimodal data fusion framework provides a reliable determination of fruit quality that can improve the recognition accuracy and the model performance up to 0.9687. The effectiveness of multimodal deep learning data fusion and thermal imaging has huge potential in monitoring the real-time determination of physicochemical changes of fruit.

Determining the Stir-Frying Degree of Gardeniae Fructus Praeparatus Based on Deep Learning and Transfer Learning

Gardeniae Fructus (GF) is one of the most widely used traditional Chinese medicines (TCMs). Its processed product, Gardeniae Fructus Praeparatus (GFP), is often used as medicine; hence, there is an urgent need to determine the stir-frying degree of GFP. In this paper, we propose a deep learning method based on transfer learning to determine the stir-frying degree of GFP. We collected images of GFP samples with different stir-frying degrees and constructed a dataset containing 9224 images. Five neural networks were trained, including VGG16, GoogLeNet, Resnet34, MobileNetV2, and MobileNetV3. While the model weights from ImageNet were used as initial parameters of the network, fine-tuning was used for four neural networks other than MobileNetV3. In the training of MobileNetV3, both feature transfer and fine-tuning were adopted. The accuracy of all five models reached more than 95.82% in the test dataset, among which MobileNetV3 performed the best with an accuracy of 98.77%. In addition, the results also showed that fine-tuning was better than feature transfer in the training of MobileNetV3. Therefore, we conclude that deep learning can effectively recognize the stir-frying degree of GFP.

Research progress on detection techniques for point-of-care testing of foodborne pathogens

The global burden of foodborne disease is enormous and foodborne pathogens are the leading cause of human illnesses. The detection of foodborne pathogenic bacteria has become a research hotspot in recent years. Rapid detection methods based on immunoassay, molecular biology, microfluidic chip, metabolism, biosensor, and mass spectrometry have developed rapidly and become the main methods for the detection of foodborne pathogens. This study reviewed a variety of rapid detection methods in recent years. The research advances are introduced based on the above technical methods for the rapid detection of foodborne pathogenic bacteria. The study also discusses the limitations of existing methods and their advantages and future development direction, to form an overall understanding of the detection methods, and for point-of-care testing (POCT) applications to accurately and rapidly diagnose and control diseases.

Application of Machine Vision System in Food Detection

Food processing technology is an important part of modern life globally and will undoubtedly play an increasingly significant role in future development of industry. Food quality and safety are societal concerns, and food health is one of the most important aspects of food processing. However, ensuring food quality and safety is a complex process that necessitates huge investments in labor. Currently, machine vision system based image analysis is widely used in the food industry to monitor food quality, greatly assisting researchers and industry in improving food inspection efficiency. Meanwhile, the use of deep learning in machine vision has significantly improved food identification intelligence. This paper reviews the application of machine vision in food detection from the hardware and software of machine vision systems, introduces the current state of research on various forms of machine vision, and provides an outlook on the challenges that machine vision system faces.