Northern maize leaf blight is one of the major diseases that endanger the health of maize. The complex background of the field and different light intensity make the detection of diseases more difficult. A multi-scale feature fusion instance detection method, based on convolutional neural network, is proposed to detect maize leaf blight. The proposed technique incorporates three major steps of data set preprocessing part, fine-tuning network and detection module. In the first step, the improved retinex is used to process data sets, which successfully solves the problem of poor detection effects caused by high-intensity light. In the second step, the improved RPN is utilized to adjust the anchor box of diseased leaves. The improved RPN network identifies and deletes negative anchors, which reduces the search space of the classifier and provides better initial information for the detection network. In this paper, a transmission module is designed to connect the fine-tuning network with the detection module. On the one hand, the transmission module fuses the features of the low-level and high-level to improve the detection accuracy of small target diseases. On the other hand, the transmission module converts the feature map associated with the fine-tuning network to the detection module, thus realizing the feature sharing between the detection module and the fine-tuning network. In the third step, the detection module takes the optimized anchor as input, focuses on detecting the diseased leaves. By sharing the features of the transmission module, the time-consuming process of using candidate regions layer by layer to detect is eliminated. Therefore, the efficiency of the whole model has reached the efficiency of the one-stage model. In order to further optimize the detection effect of the model, we replace the loss function with generalized intersection over union (GIoU). After 60000 iterations, the highest mean average precision (mAP) reaches 91.83%. The experimental results indicate that the improved model outperforms several existing methods in terms of greater precision and frames per second (FPS).

With the continuous development of economy and the change in consumption concept, the demand for meat, a nutritious food, has been dramatically increasing. Meat quality is tightly related to human life and health, and it is commonly measured by sensory attribute, chemical composition, physical and chemical property, nutritional value, and safety quality. This paper surveys four types of emerging non-destructive detection techniques for meat quality estimation, including spectroscopic technique, imaging technique, machine vision, and electronic nose. The theoretical basis and applications of each technique are summarized, and their characteristics and specific application scope are compared horizontally, and the possible development direction is discussed. This review clearly shows that non-destructive detection has the advantages of fast, accurate, and non-invasive, and it is the current research hotspot on meat quality evaluation. In the future, how to integrate a variety of non-destructive detection techniques to achieve comprehensive analysis and assessment of meat quality and safety will be a mainstream trend.

Nowadays, the development of the food industry and economic recovery have driven escalating consumer demands for high-quality, nutritious, and safe food products, and spectroscopic technologies are increasingly prominent as essential tools for food quality inspection. Concurrently, the rapid rise of artificial intelligence (AI) has created new opportunities for food quality detection. As a critical branch of AI, deep learning synergizes with spectroscopic technologies to enhance spectral data processing accuracy, enable real-time decision making, and address challenges from complex matrices and spectral noise. This review summarizes six cutting-edge nondestructive spectroscopic and imaging technologies, near-infrared/mid-infrared spectroscopy, Raman spectroscopy, fluorescence spectroscopy, hyperspectral imaging (spanning the UV, visible, and NIR regions, to simultaneously capture both spatial distribution and spectral signatures of sample constituents), terahertz spectroscopy, and nuclear magnetic resonance (NMR), along with their transformative applications. We systematically elucidate the fundamental principles and distinctive merits of each technological approach, with a particular focus on their deep learning-based integration with spectral fusion techniques and hybrid spectral-heterogeneous fusion methodologies. Our analysis reveals that the synergy between spectroscopic technologies and deep learning demonstrates unparalleled superiority in speed, precision, and non-invasiveness. Future research should prioritize three directions: multimodal integration of spectroscopic technologies, edge computing in portable devices, and AI-driven applications, ultimately establishing a high-precision and sustainable food quality inspection system spanning from production to consumption.

In the current natural environment, due to the complexity of the background and the high similarity of the color between immature green tomatoes and the plant, the occlusion of the key organs (flower and fruit) by the leaves and stems will lead to low recognition rates and poor generalizations of the detection model. Therefore, an improved tomato organ detection method based on convolutional neural network (CNN) has been proposed in this paper. Based on the original Faster R-CNN algorithm, Resnet-50 with residual blocks was used to replace the traditional vgg16 feature extraction network, and a K-means clustering method was used to adjust more appropriate anchor sizes than manual setting, to improve detection accuracy. The test results showed that the mean average precision (mAP) was significantly improved compared with the traditional Faster R-CNN model. The training model can be transplanted to the embedded system, which lays a theoretical foundation for the development of a precise targeting pesticide application system and an automatic picking device.

Apple diseases cause a lot of economic losses to fruit growers in China. Early diagnosis and accurate recognition of apple diseases can control the spread of disease and reduce production costs. However, the significance of disease characteristic of apple leaves in complex environment is relatively weak, and the fine-grain among different diseases of apple leaves is high, and the conventional feature extraction methods will lose the discrimination information. To solve these problems, an apple disease classification model based on multi-scale feature fusion is proposed in this paper. Firstly, the information flow of conventional residual network (ResNet) was improved to achieve efficient information circulation through changing the position of batch normalization and rectified linear unit (ReLU). Secondly, in order to solve the problem of serious loss of information in ResNet downsample, the channel projection and spatial projection of downsample were separated. Lastly, the 3×3 conv in ResBlocks was replaced by pyramid convolution, and the dilated convolution with different dilation rate was introduced into pyramid convolution to enhance the output scale of feature maps and improve the robustness of the model. The optimized model was verified on the dataset of this paper, and the optimized model had stronger anti-noise ability and better robustness, excellent learning effect and fast convergence speed. The classification accuracy on the original dataset is 94.24%, and that on the preprocessed dataset is 94.99%. The results demonstrate that the optimal model has a high accuracy, which can provide a reference for the prevention and control of apple leaf diseases.

In the current natural environment, due to the complexity of the background and the high similarity of the color between immature green tomato and plant, the occlusion of the key organs (flower and fruit) by the leaves and stems will lead to low recognition rate and poor generalization of the detection model. Therefore, an improved tomato organ detection method based on convolutional neural network has been proposed in this paper. Based on the original Faster R-CNN algorithm, Resnet-50 with residual blocks was used to replace the traditional vgg16 feature extraction network, and K-means clustering method was used to adjust more appropriate anchor size than manual setting to improve detection accuracy. A variety of data augmentation techniques were used to train the network. The test results showed that compared with the traditional Faster R-CNN model, the mean average precision (mAP) of the optimal model was improved from 85.2% to 90.7%, the memory requirement decreased from 546.9MB to 115.9 MB, and the average detection time was shortened to 0.073S/sheet. As the performance greatly improved, the training model can be transplanted to the embedded system, which lays a theoretical foundation for the development of precise targeting pesticide application system and automatic picking device.