This paper explores the influence of the selection method of the region of interest (ROI) on the results in the total sugar of apple detection based on hyperspectral imaging technology. Taking Fuji apple as the detection object, the hyperspectral images of the samples were collected based on the 900~1750 nm hyperspectral imaging system, and the total sugar content of the samples was obtained based on the anthrone colorimetric method. The square ROI and circular ROI of different sizes were extracted. The average spectrum of the region was used to establish a quantitative analysis model of apple's total sugar content by partial least squares (PLS). The results show that apple's total sugar detection model established by extracting a circular ROI with a diameter of 25 pixels has the highest accuracy and strongest prediction ability(R c = 0.8977, RMSEC = 0.6459, R P = 0.8836, RMSEP = 0.6627). The research shows that selecting ROI with a suitable shape and size for the research object is of great significance for improving the accuracy of the prediction model of apple's total sugar content and giving play to the advantages of hyperspectral images.

No abstract

No abstract

To understand the research status and current dynamics of fruit quality detection and objectively reflect the influence of different countries, research institutions and authors in this field, the software CiteSpace was used to bibliometrically and visually analyze the relevant literature on fruit quality detection in Web of Science (WoS) database from 1982 to 2021. The results showed that the number of publications on fruit quality detection showed a trend of slow in the early stage, rapid in the middle stage and intensified in the late stage. China has the largest number of international publications, accounting for 21.80% of the WoS database, but its intermediary centrality is inferior to that of the United States, Germany, Italy and Spain; the United States is at the core of international cooperation, establishing cooperative relations with most countries; through keywords co-occurrence network and keyword clustering, it is concluded that the research mainly focuses on fruit quality detection based on spectral technology or electronic nose technology, fruit composition detection based on high-performance liquid chromatography (HPLC), fruit edible safety detection, and genetic analysis of fruit quality-related traits. Bibliometrics and visual analysis of this fruit quality detection research can provide a certain reference for relevant researchers.

A belt defect detection model based on unsupervised generative adversarial network is proposed for the problem of low number of defective samples in belt defect detection. The model is trained on defect-free normal samples and the detection results are obtained by calculating the outliers between the input samples and the reconstructed samples at the time of detection. Considering the information loss problem of the encoder compressing the input samples, this paper adds a selfattention mechanism to the model to enhance the extraction of useful features. In addition, the LeakyPeLU activation function in the model is replaced with PReLU to improve the fitting ability of the model, and the method is experimentally proven to achieve better image reconstruction results. The experimental results show that the accuracy of the assay using this method is 98.13%, AUC value is 99.89% and AP value is 99.75%, which was better than the other two comparative models. The method has good reconfiguration and defect detection capabilities.

No abstract

No abstract

This study proposes a novel method for jujube maturity and water content determination incorporating fractal theory. Firstly, the tissue section images of winter jujube at different maturity and tissue section image images of winter jujube with different moisture content were preprocessed by grayscale, median filter, histogram equalization and binarization. Secondly, the fractal dimension of jujube tissue section images of jujube at different maturity, and the fractal dimension of tissue slice images of jujube with different moisture content were calculated based on the box dimension algorithm. Finally, the relationships of the fractal dimension-maturity and fractal dimension-moisture content were explored. The results showed that the fractal features had good discrimination performance, the fractal dimension decreased with the increase of maturity, and the fractal dimension decreased with the increase of moisture content. This study provides a new way of thinking about the detection of physical and chemical indicators of winter jujube and other fruits.