Deep Learning-Based Classification of Rotten Fruits and Identification of Shelf Life

The freshness of fruits is considered to be one of the essential characteristics for consumers in determining their quality,flavor and nutritional value.The primary need for identifying rotten fruits is to ensure that only fresh and high-quality fruits are sold to consumers.The impact of rotten fruits can foster harmful bacteria,molds and other microorganisms that can cause food poisoning and other illnesses to the consumers.The overall purpose of the study is to classify rotten fruits,which can affect the taste,texture,and appearance of other fresh fruits,thereby reducing their shelf life.The agriculture and food industries are increasingly adopting computer vision technology to detect rotten fruits and forecast their shelf life.Hence,this research work mainly focuses on the Convolutional Neural Network’s(CNN)deep learning model,which helps in the classification of rotten fruits.The proposed methodology involves real-time analysis of a dataset of various types of fruits,including apples,bananas,oranges,papayas and guavas.Similarly,machine learningmodels such as GaussianNaïve Bayes(GNB)and random forest are used to predict the fruit’s shelf life.The results obtained from the various pre-trained models for rotten fruit detection are analysed based on an accuracy score to determine the best model.In comparison to other pre-trained models,the visual geometry group16(VGG16)obtained a higher accuracy score of 95%.Likewise,the random forest model delivers a better accuracy score of 88% when compared with GNB in forecasting the fruit’s shelf life.By developing an accurate classification model,only fresh and safe fruits reach consumers,reducing the risks associated with contaminated produce.Thereby,the proposed approach will have a significant impact on the food industry for efficient fruit distribution and also benefit customers to purchase fresh fruits.

A Device for Rapid Detection of Dithiocarbamate Pesticide Residues in Fruits

Based on the chemical properties of dithiocarbamate pesticides,a device for rapid detection was developed in the paper,and the experimental conditions were optimized. Dithiocarbamate residues in fruits were successfully detected using molecular absorption spectro-photometry,and the recovery rate was over 80%.The rapid detection method was simple to operate with low cost,and was conducive to application in basic level and enterprise laboratories.

Promising real-time fruit and vegetable quality detection technologies applicable to manipulator picking process

In recent years,worldwide research on fruit and vegetable quality detection technology includes machine vision,spectroscopy,acoustic vibration,tactile sensors,etc.These technologies have also been gradually applied to fruit and vegetable grading and sorting lines in recent years,greatly improving the income of farmers.There have been numerous reviews of these techniques.Most of the published research on fruit and vegetable quality detection technology is still carried out in the laboratory.The emphases have been on quality feature extraction,model establishment and experimental verification.The successful application in the fruit and vegetable sorting production line proves that these studies have high application potential and value,and we look forward to the performance of these sensing technologies in the fruit and vegetable picking field.Therefore,in this paper,based on the future highly automated fruit and vegetable picking mode,we will focus on three kinds of fruit and vegetable quality detection technologies including machine vision,tactile sensor and spectroscopy,to provide some reference for future research.Since there are currently limited cases of detecting quality during the fruit and vegetable picking,experiments performed on prototypes of manipulator,or devices such as Nanocilia sensors,portable spectrometers,etc.,which are compact and convenient to mount on manipulator will be reviewed.Several tables and mosaics showing the performance of the three technologies in the detection of fruit and vegetable quality over the past five years have been listed.The performance of each sensing technology was relatively satisfactory in the laboratory in general.However,in the picking scenario,there are still many challenges to be solved.Different from industrial environments,agricultural scenarios are complex and changeable.Fragile and vulnerable agricultural products pose another challenge.The development of portable devices and nanomaterials have become important breakthroughs.Optical and tactile detection methods,as well as the integration of different quality detection methods,are expected to be the trends of research and development.

Automatic detection of pecan fruits based on Faster RCNN with FPN in orchard

Although the development of the robot picking vision system is widely applied,it is very challenging for fruit detection in orchards with complex light and environment,especially for fruit colors similar to the background.In recent,there are few studies on pecan fruit detection and location based on machine vision.In this study,an accurate and efficient pecan fruit detection method was proposed based on machine vision under natural pecan orchards.In order to solve the illumination problem,a light compensation algorithm was first utilized to process the collected samples,and then an improved Faster Region Convolutional Neural Network(Faster RCNN)with the Feature Pyramid Networks(FPN)was established to train the samples.Finally,the pecan number counting method was introduced to count the number of pecan.A total of 241 pecan images were tested,and comparison experiments were carried out.The mean average precision(mAP)of the proposed detection method was 95.932%,compared with the result without uneven illumination correction(UIC),which was increased by 0.849%,while the mAP of the Single Shot Detector(SSD)+FPN was 92.991%.In addition,the number of clusters was counted using the proposed method with an accuracy rate of 93.539%compared with the actual clusters.The results demonstrate that the proposed network has good robustness for pecan fruit detection in different illumination and various unstructured environments,and the experimental achievement has great potential for robot-picking visual systems.