Fruit Quality Detection Research Articles

Quantitative impact damage of apple based on hyperspectral imaging combined with mechanical parameters and size correction.

In order to solve the problem of decreasing the accuracy of quantitative prediction of damage of fruits resulting in the size difference of fruits, the spectral correction method based on the size difference of fruits was adopted. To provide richer theoretical knowledge for the quality detection of fruits and the design of damage reduction programs in reality. First, the undamaged spectra of the group of apples with better performance of the model were selected as the reference spectra by analyzing and comparing the modeling results of the prediction models of mechanical parameters with the single fruit diameter groups. The spectral correction coefficient was calculated with the formulas, and the damage spectra of three groups of apples were size-corrected by this coefficient to build the mechanical parameter models. Finally, the corrected spectra were screened for characteristic wavelengths by competitive adaptive reweighting and uninformative variable elimination algorithms. The results of study showed that the correlation coefficients of the prediction set of the models were improved by 2.1%-13% and the root mean square errors were reduced by 16%-51% with the spectrally corrected models compared with the precorrection models. Therefore, the size correction method can be used to eliminate the effect of size difference on the mechanical parameter models to improve the applicability of the quantitative damage prediction models, and it can provide the theoretical guidance to design the loss-reducing protective measures and the agricultural mechanized operation process.

Frequency selection method with support vector machine to minimize the impact of individual differences on the electrical impedance spectra of fruits

Individual differences in electrical impedance spectroscopy (EIS) parameters is a technical bottleneck in fruit quality detection. To achieve non-destructive fruit quality testing and minimize the impact of individual differences, this paper proposes a frequency selection + support vector machine strategy based on the frequency response characteristics of biological tissues and the path of current flow. This study found obvious differences in the EIS parameters of different samples. The measurement stability was affected by the electrode type and frequency. The destructive needle electrode was much less affected by individual differences than the non-destructive patch electrode. The effect of low frequencies was greater than that of high frequencies. The heterogeneity of the fruit peel and pulp and the contact area between the electrode and peel were the main reasons for individual differences. When detecting banana maturity, the highest precision of the models was 98.9% by proposed methods; however, the generalizability of the model and its application for other fruit quality tests still require further verification and optimization. The results promote the practical application of EIS in the field of fruit quality assessment and provide new insights for the quality evaluation of other agricultural products.

Design and research of multi-information fusion RFID sensor for fruit and vegetable quality detection.

With the increasing demand for fruits and vegetables in the market, the development of cold chain logistics has put forward higher requirements for the quality of fruits and vegetables in storage. To ensure the freshness of fruits and vegetables during storage and transportation and avoid unnecessary loss, it is necessary to conduct real-time detection of their odor to ensure their quality. Therefore, based on nano-composite materials combined with Radio Frequency Identification (RFID) technology, this paper designs an integrated RFID sensor that can simultaneously detect temperature, carbon dioxide, and ethanol concentrations. The test results show that the sensor has a high sensitivity of 0.25dB/°C, 0.011dB/ppm, and 0.65MHz/ppm for detecting temperature, carbon dioxide, and ethanol concentration, respectively. The sensor also uses Printed Circuit Board (PCB) technology to make the sensor base, which has the advantages of low cost, easy portability, and mass production capability. The results obtained evidencethat the system meets the requirements of environmental monitoring for fruit and vegetable storage, runs stably, and has a high use value.

Development of deep learning based user-friendly interface for fruit quality detection

The implementation of deep learning algorithms has contributed to various applications related to the detection of fruit quality. The quality attributes of fruit such as total soluble solids, moisture content, pH, colour changes, and firmness at different varieties can be predicted according to different storage conditions with reliable classification accuracy. The advances in non-destructive techniques have led to the rapid utilisation of the imaging approach in order to monitor the fruit quality. These image datasets encompass diverse information which requires extensive data extraction. To overcome this issue, a deep learning approach using convolutional neural network was used to evaluate the fruit quality. A graphical user interface-based software (DLFRUIT-GUI) for data processing of fruit quality is developed. The toolbox allows the model training and selection based on the image datasets of the fruit. The software offers a push-button approach to establish deep learning models for monitoring fruit quality. The adoption of convolutional neural network model successfully improves the model performance which demonstrated efficient results in predicting the fruit quality at different varieties according to various storage conditions. The DLFRUIT-GUI toolbox provides rapid monitoring of fruit quality detection that can easily be accessible by users who have no programming skills and tedious data analysis.

Optimalisasi Model Ensemble Learning dengan Augmentasi dan SMOTE pada Sistem Pendeteksi Kualitas Buah

Fruit quality is an important factor in selecting fruit for consumption because it affects consumer health and satisfaction. Identification of fruit quality has become the focus of research, and one of the approaches used is a non-destructive approach through measuring the gases produced by the fruit. Machine learning can be used to process this gas data and build system models that can classify fruit quality. This research discusses the application of the DCS-OLA and Stacking dynamic ensemble learning algorithms to build a fruit quality detection system model. The basic methods used to build models are Logistic Regression, Decision Tree, Gaussian Naïve Bayes, and Mul-ti-Layer Perceptron. The fruit used is mango with a shelf life of 7 days and Srikaya (sugar apple) with a shelf life of 4 days. The condition of the initial dataset is unbalanced. The research results show that trimming the mango dataset to only 4 days according to the shelf life of sugar apple helps reduce the difference in shelf life between the two. Then jittering and balancing techniques are used to increase and balance the number of datasets between the two types of fruit. High accuracy is achieved by the DCS-OLA ensemble and stacking ensemble by combining the basic methods of Logistic Regression and Decision Tree, especially in balanced dataset conditions. In conclusion, the use of ensemble learning in detecting fruit quality has great potential for real-world applications. However, further validation is needed with larger datasets and a wider variety of conditions.

Improving Apple Fruit Quality Detection with AI and Machine Vision

The detection of apples using Raspberry Pi is an innovative approach that merges the realms of computer vision, machine learning, and agricultural automation. This abstract provides an extensive overview of the methodologies, implementations, challenges, and future directions pertaining to apple detection using Raspberry Pi, encapsulating the essence of the research conducted in this domain. The quest for automation in agriculture has spurred the development of novel technologies aimed at improving efficiency and reducing manual labor. Fruit detection, particularly the identification of apples, holds significant importance due to the fruit's widespread cultivation and economic value. Traditional methods of fruit detection often involve manual sorting, which is labor>intensive and time>consuming. Hence, there arises a need for automated systems capable of accurately identifying and sorting fruits, thereby streamlining agricultural processes. The implementation section details the practical realization of the apple detection system using Raspberry Pi. Hardware setup involves the integration of Raspberry Pi boards with camera modules and other peripherals necessary for image acquisition and processing. Software development entails the creation of Python>based modules for image preprocessing, feature extraction, and classification. OpenCV and scikit>learn libraries are utilized for implementing image processing and machine learning algorithms, respectively. The system is tested in different environments to evaluate its performance under various conditions, including controlled laboratory settings and outdoor agricultural scenarios.

Research on Quality Detection of Jujube (Ziziphus jujuba Mill.) Fruit Based on UAV Multi-Spectrum

To enhance the accuracy of multispectral detection using unmanned aerial vehicles (UAVs), multispectral data of jujube fruit with different soluble solids content (SSC) and moisture content (MC) were obtained under different relative azimuth angles. Prediction models for SSC and MC of jujube fruit were established using partial least squares regression (PLSR) and support vector machines (SVM), respectively. The findings revealed that the MC of jujube fruit had the best prediction effect when the relative azimuth angle was 90°, while the SSC of the jujube fruit had the best prediction effect at an azimuth angle of 180°. Then, the spectral reflectance data corresponding to the eight relative azimuth angles were used as input variables to establish a jujube fruit quality detection model. The results showed that the prediction model for MC and SSC, established using the angle fusion method, had higher detection accuracy compared to the prediction model established at a single angle. This research provides a technical reference for improving the accuracy of outdoor jujube fruit quality detection using spectral technology.

Research on the upgrade and maintenance method of apple soluble solids content models

AbstractIn this paper, 3 years (2020, 2021, and 2022) of Bingtangxin apples were used to study the upgrade and maintenance method of apple soluble solids content (SSC) model using near infrared (NIR) spectroscopy. Modeling by partial least squares (PLS) and one‐dimensional convolutional neural network (1D‐CNN) algorithm. The “base model” is built with apples in 2020 and then upgrade and maintain it. The upgraded model is used to predict the sample in 2021 and 2022. Three methods were used to upgrade and maintenance the model, which are based on updated data, direct correction‐based method, and similar band‐based method. Among the three upgrade methods, the model maintenance method using updated data had the greatest improvement in prediction correlation coefficients (Rp) in both years, and both obtained good predictions. The use of direct correction resulted in the greatest reduction in the root mean square error of prediction (RMSEP) in both years. However, the Rp of the model is not improved much by using the direct correction method. The model maintenance method using similar bands combined with different modeling methods also gives good prediction results. Finally, after comparison, the model maintenance method of selecting similar bands is preferred. In the case of limited improvement in the effect of using the similar band method, the model is maintained using the method of adding updated data. The investigation of model upgrade and maintenance methods can reduce human and material consumption and make apple SSC models more versatile.Practical applicationsNIR technology is the first choice for online fruit quality inspection, but its inspection process requires constant upgrading and maintenance with models. The quality of apples varies from year to year, and the model built with samples from a single year does not work well in predicting samples from other years, resulting in the need to upgrade and maintain the fruit quality detection model. However, sometimes, although a large amount of experimental material is lost, it still results in a generic calibration model that is too cumbersome and leads to poor prediction results. At this time, finding an effective model upgrade and maintenance method can both reduce the sample consumption and make the model prediction accuracy improve, and also reduce the model complexity and make the maintained model more robust.

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

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

An intelligent framework for estimating grade and quantity of tropical fruits in a multi-modal latent representation network

This research addresses the crucial aspects of ensuring the quality and origin of fruits in the supply chain, as well as estimating their quantity measures. A novel interwoven deep neural framework is proposed, incorporating an Object Detection Network (ODN) and a Multi-modal Regressive Convolution Neural Network (MRCNN). Two distinct datasets, Annotated FruitNet and FruitBox, were compiled to support the framework’s tasks. The FruitNet360 dataset was re-clustered based on geographical origin, enabling robust fruit quality detection and localization with a mean Average Precision (mAP) score of 95.70% using YOLOv7. Leveraging the representation learning capability of Residual Networks, the framework accurately predicted quantitative weight measures of fruit boxes, achieving a marginal Mean Squared Error (MSE) rate of 0.034. Furthermore, the origin of fruits was identified with an impressive accuracy of 98.67%. The proposed framework, with its combined regression and classification model, captured the latent representations of source data effectively, surpassing the limitations of conventional approaches and reducing manual system overhead. The automation framework holds potential for integration into smart devices, offering valuable assistance to both vendors and consumers in fruit analysis and selection.

Study on the dimension correction of juicy peach based on diffuse transmittance online detection

At present, visible/near infrared (VIS/NIR) spectroscopy has been widely used in fruit quality detection, but the different dimensions of fruit will affect the accuracy of quality detection, especially the online detection. At this time, it is necessary to study a dimension correction method to improve the accuracy of spectral detection. Therefore, in this paper, VIS/NIR spectroscopy technology was used to collect the spectra and soluble solid content (SSC) of three fruit types of peach(small, medium and large fruit) under different integration time. The analysis of their spectral attenuation revealed that the spectral energy of medium and large fruit, all attenuated under short integration time, and their complete spectrum could be collected under long integration time, indicating that adjusting the integration time was feasible. After that, partial least square method (PLS) was used to develop the combination model with the spectral data of different dimensions of peach under different integration time, and the optimal model was obtained. When the integration time of small fruit, medium fruit and large fruit was 80 ms, 100 ms and 120 ms respectively, the prediction correlation coefficient (Rp) of the model was 0.846. Then multiplicative scatter correction (MSC) was used to pretreat the optimal model, and the Rp of the model was 0.857. The results showed that using different integration time could reduce the influence of dimension difference on the online quality detection of peach, realize dimension correction, and more accurately detect the quality of peach. In addition, it also showed that the dimension correction method can improve the accuracy of spectral detection, and has certain application value for spectral detection.

YOLOAPPLE: Augment Yolov3 deep learning algorithm for apple fruit quality detection

YOLOAPPLE: Augment Yolov3 deep learning algorithm for apple fruit quality detection

Modeling and De-Noising for Nondestructive Detection of Total Soluble Solid Content of Pomelo by Using Visible/Near Infrared Spectroscopy.

The flavor of Pomelo is highly variable and difficult to determine without peeling the fruit. The quality of pomelo flavor is due largely to the total soluble solid content (TSSC) in the fruit and there is a commercial need for a quick but nondestructive TSSC detection method for the industrial grading of pomelo. Due to the large size and thick mesocarp of pomelo, determining the internal quality of a pomelo fruit in a nondestructive manner is difficult, and the detection accuracy is further complicated by the noise typically generated by the common methods for the internal quality detection of other fruits. Thus, the aim of this study was to determine the optimal method to accurately detect pomelo TSSC and find a de-noising model which reduces the influence of noise on the optimal method's results. After developing a full-transmission visible/near infrared (VIS/NIR) spectroscopy sampling method, the confirming experimental results showed that the optimal pomelo TSSC detection model was Savitzky Golay + standard normal variate + competitive adaptive reweighted sampling + partial least squares regression. The R2 and RMSE of the calibration set for pomelo TSSC detection were 0.8097 and 0.8508, respectively, and the R2 and RMSE of the validation set for pomelo TSSC detection were 0.8053 and 0.8888, respectively. Both reference and dark de-noising are important for pomelo internal quality detection and should be calibrated frequently to compensate for time drift. This study found that large sensor response translation noise can be reduced with an artificial horizontal shift. Data supplementation is efficient for improving the adaption of the detection model for batch differences in pomelo samples. Using this optimized de-noising model to compensate for time drift, sensor response translation, and batch differences, the developed detection method is capable of satisfying the requirements of the industry (TSSC detection R2 was equal or larger than 0.9, RMSE was less than 1). These results indicate that full-transmission VIS/NIR spectroscopy can be exploited to realize the nondestructive detection of pomelo TSSC on an industrial scale, and that the methodologies used in this study can be immediately implemented in real-world production.

Advancements and Applications of Raman Spectroscopy in Rapid Quality and Safety Detection of Fruits and Vegetables

With the improvement in living standards, consumers have become more aware of healthy diets and pay more attention to the quality and safety of fruits and vegetables. Therefore, it is essential to strengthen the research on rapid detection of the quality and safety of fruits and vegetables. This study mainly outlines five Raman spectroscopy techniques. It introduces their principles and advantages and the current research progress of their application in fruit and vegetable quality and safety detection. Based on the characteristic Raman spectroscopy analysis of different fruits and vegetables, researchers found that Raman spectroscopy techniques can quickly and accurately detect classification identification, ripeness, freshness, disease infestation, and surface pesticide residues of fruits and vegetables. In addition, Raman spectroscopy techniques can also detect the content and distribution of material components of fruits and vegetables. This paper also discusses Raman spectroscopy’s current technology and application difficulties in fruit and vegetable quality and safety testing. It looks forward to its future development trend, expecting to promote the broad application of Raman spectroscopy in fruit and vegetable quality and safety testing.

Artificial Intelligence Based Predictive Analysis of Customer Churn

Deep learning has been evidenced to be a cutting-edge technology for big data scrutiny with a huge figure of effective cases in image processing, speech recognition, object detection, and so on. Lately, it has also been acquainted with in food science and business. In this paper, a fleeting overview of deep learning and detailly labelled the structure of some prevalent constructions of deep neural networks and the method for training a model is provided. Various techniques that used deep learning as the data analysis tool are analyzed to answer the complications and challenges in food sphere together with quality detection of fruits & vegetables. The precise difficulties, the datasets, the pre-processing approaches, the networks and frameworks used, the performance attained, and the evaluation with other prevalent explanations of each research are examined. We also analyzed the potential of deep learning to be used as a cutting-edge data mining tool in food sensory and consume explores. The outcome of our review specifies that deep learning outclasses other approaches such as physical feature extractors, orthodox machine learning algorithms, and deep learning as a capable tool in food quality and safety inspection. The cheering outcomes in classification and regression problems attained by deep learning will fascinate more research exertions to apply deep learning into the arena of food in the forthcoming. The main aim of this work is to facilitate our learning and implement that in real life. Food quality and food security are always issues which are always overlooked. In modern times, this has morphed into more significant concerns relating to optimization of on- demand supply chains and profitability of agri-businesses. But now with the advanced systems and technology, it is possible to resolve this issue efficiently using the power of AI.

Enhancing Transferability of Near-Infrared Spectral Models for Soluble Solids Content Prediction across Different Fruits

Near-infrared (NIR) spectroscopy is widely used for non-destructive detection of fruit quality, but the transferability of NIR models between different fruits is still a challenge. This study investigates the transferability of NIR models from strawberry to grape and apple using two case studies. A total of 94 strawberry, 80 grape, and 125 apple samples were measured for their soluble solids content (SSC) and NIR spectra. Partial least squares (PLS) regression was used to establish a model for predicting strawberry SSC, with an acceptable root mean square error of prediction (RMSEP) and correlation coefficient (R) of 0.53 °Brix and 0.91, respectively. Directly applying the strawberry model to grape and apple spectra significantly degrades the performance, increasing the RMSEP up to 3.47 and 16.40, respectively. Spectral preprocessing can improve the predictions for all three fruits, but the bias cannot be eliminated. Global modeling produces a generalized model, but the prediction for strawberry degrades. Calibration transfer with SS-PFCE and PLS correction, which are calibration methods without standard samples, was found to be an effective way to improve the prediction of grape and apple spectra using the strawberry model. Therefore, calibration transfer may be a feasible way for improving the transferability of NIR models for multiple fruits.

A novel, low-cost, smart IoT based framework for fruit and vegetable quality detection during transit in India

A novel, low-cost, smart IoT based framework for fruit and vegetable quality detection during transit in India

Non-destructive detection of kiwifruit soluble solid content based on hyperspectral and fluorescence spectral imaging.

The soluble solid content (SSC) is one of the important parameters depicting the quality, maturity and taste of fruits. This study explored hyperspectral imaging (HSI) and fluorescence spectral imaging (FSI) techniques, as well as suitable chemometric techniques to predict the SSC in kiwifruit. 90 kiwifruit samples were divided into 70 calibration sets and 20 prediction sets. The hyperspectral images of samples in the spectral range of 387 nm~1034 nm and the fluorescence spectral images in the spectral range of 400 nm~1000 nm were collected, and their regions of interest were extracted. Six spectral pre-processing techniques were used to pre-process the two spectral data, and the best pre-processing method was selected after comparing it with the predicted results. Then, five primary and three secondary feature extraction algorithms were used to extract feature variables from the pre-processed spectral data. Subsequently, three regression prediction models, i.e., the extreme learning machines (ELM), the partial least squares regression (PLSR) and the particle swarm optimization - least square support vector machine (PSO-LSSVM), were established. The prediction results were analyzed and compared further. MASS-Boss-ELM, based on fluorescence spectral imaging technique, exhibited the best prediction performance for the kiwifruit SSC, with the , and RPD of 0.8894, 0.9429 and 2.88, respectively. MASS-Boss-PLSR based on the hyperspectral imaging technique showed a slightly lower prediction performance, with the , , and RPD of 0.8717, 0.8747, and 2.89, respectively. The outcome presents that the two spectral imaging techniques are suitable for the non-destructive prediction of fruit quality. Among them, the FSI technology illustrates better prediction, providing technical support for the non-destructive detection of intrinsic fruit quality.

Fruit Quality Detection Using Medical Image Processing

Fruit Quality Detection Using Medical Image Processing

Flexible Vis/NIR wireless sensing system for banana monitoring

Abstract Objectives The quality of the fruit seriously affects the economic value of the fruit. Fruit quality is related to many ripening parameters, such as soluble solid content (SSC), pH, and firmness (FM), and is a complex process. Traditional methods are inefficient, do not guarantee quality, and do not adapt to the current rhythm of the fruit market. In this paper, a was designed and implemented for quality prediction and maturity level classification of Philippine Cavendish bananas. Materials and Methods The quality changes of bananas in different stages were analyzed. Twelve light intensity reflectance values for each maturity stage were compared to conventionally measured SSC, FM, PH, and color space. Results Our device can be compared with traditional forms of quality measurement. The experimental results show that the established predictive model with specific preprocessing and modeling algorithms can effectively determine various banana quality parameters (SSC, pH, FM, L*, a*, and b*). The RPD values of SSC and a* were greater than 3.0, the RPD values of L* and b* were between 2.5 and 3.0, and the pH and FM were between 2.0 and 2.5. In addition, a new banana maturity level classification method (FSC) was proposed, and the results showed that the method could effectively classify the maturity level classes (i.e. four maturity levels) with an accuracy rate of up to 97.5%. Finally, the MLR and FSC models are imported into the MCU to realize the near-range and long-range real-time display of data. Conclusions These methods can also be applied more broadly to fruit quality detection, providing a basic framework for future research.