Tomato Sorting Research Articles

A Tomato Recognition and Rapid Sorting System Based on Improved YOLOv10

In order to address the issue of time-consuming, labor-intensive traditional industrial tomato sorting, this paper proposes a high-precision tomato recognition strategy and fast automatic grasping system. Firstly, the Swin Transformer module is integrated into YOLOv10 to reduce the resolution of each layer by half and double the number of channels, improving recognition accuracy. Then, the Simple Attention Module (SimAM) and the Efficient Multi-Scale Attention (EMA) attention mechanisms are added to achieve complete integration of features, and the Bi-level Routing Attention (BiFormer) is introduced for dynamic sparse attention and resource allocation. Finally, a lightweight detection head is added to YOLOv10 to improve the accuracy of tiny target detection. To complement the recognition system, a single-vertex and multi-crease (SVMC) origami soft gripper is employed for rapid adaptive grasping of identified objects through bistable deformation. This innovative system enables quick and accurate tomato grasping post-identification, showcasing significant potential for application in fruit and vegetable sorting operations.

Tomato Sorting System Based on Machine Vision

In the fresh tomato market, it is crucial to sort and sell tomatoes based on their quality. This is important to enhance the competitiveness and profitability of the market. However, the manual sorting process is subjective and inefficient. To address this issue, we have developed an automatic tomato sorting system that uses the Raspberry PI 4B as the control platform for the robot arm. This system has been integrated with a human–computer interaction interface sorting system. Our experimental results indicate that this sorting method has an accuracy rate of 99.1% and an efficiency of 1350 tomatoes per hour. This development is in line with modern agricultural mechanization and intelligence needs.

IoT Based Automated Tomato Sorting Machine

IoT Based Automated Tomato Sorting Machine

Design of a Tomato Sorting Device Based on the Multisine-FSR Composite Measurement

The ripeness of tomatoes is crucial to determining their shelf life and quality. Most of the current methods for picking and sorting tomatoes take a long time, so this paper aims to design a device for sorting tomatoes based on force and bioelectrical impedance measurement. A force sensor installed on each of its four fingers may be used as an impedance measurement electrode. When picking tomatoes, the electrical impedance analysis circuit is first connected for pre-grasping. By applying a certain pre-tightening force, the FSR sensor on the end effector finger can be tightly attached to the tomato and establish an electric current pathway. Then, the electrical parameters of the tomato are measured to determine its maturity, and some of the electrical parameters are used for force monitoring compensation. Then, a force analysis is conducted to consider the resistance of the FSR under current stress. According to the principle of complex impedance circuit voltage division, the voltage signal on the tomato is determined. At the same time, the specific value of the grasping force at this time is determined based on the calibration of the pre-experiment and the compensation during the detection process, achieving real-time detection of the grasping force. The bioelectricity parameters of tomatoes can not only judge the ripeness of tomatoes, but also compensate for the force measurement stage to achieve more accurate non-destructive sorting. The experimental results showed that within 0.6 s of stable grasping, this system could complete tomato ripeness detection, improve the overall tomato sorting efficiency, and achieve 95% accuracy in identifying ripeness through impedance.

HE RELATIONSHIP OF WORK ATTITUDE AND WORK POSITION TOWARDS WORKLOAD ON TOMATO FRUIT SORTING WORKERS IN SEMANDING VILLAGE

Background: Workload is closely related to work capacity. One of the factors that affect the value of the workload is the tasks that are carried out both physically and mentally. Objective: To determine the relationship between Work Attitude and Work Position towards Workload on Tomato Fruit Sorting Workers in Semanding Village. Methods: analytic descriptive research, using cross sectional analytics research design, that is, the measurements and observations are conducted once with a total sampling technique. The subjects were 12 tomato sorting workers. This research used measurement of workload using Work Pulse Measurement. Results: The analysis results to the final condition (post) are higher than the initial conditions (pre) and the p value = 0.001. Conclusion: Based on data analysis, it can be concluded that there is a significant increase in the workload.

The Use of Image Processing and Sensor in Tomato Sorting Machine by Color, Size, and Weight

Tomatoes are a popular vegetable in Indonesia, where production increases every year according to market demand. The large production requires proper post-harvest handling both in quality and time. It has been well-known that sorting and grading are the first and foremost processes in the post-harvest process of tomatoes. Sorting tomatoes can be conducted by color and adjusted to the target market. The automation process in the post-sorting and grading process can save time and resources. This research proposes a sorting system that sorts tomatoes based on color, size, and weight. Tomatoes are sorted by red, yellow, and green colors. The detection of color and size was carried out by image processing with the OpenCV library. The color detection was carried out by HSV's red, yellow, and green values. In comparison, the dimensional measurement was carried out by determining the outermost point of the detected object both vertically and horizontally. At the same time, tomatoes' weight was measured by a weight sensor. This system was implemented into a prototype sorting system with a webcam, Arduino, a conveyor, and motors. The final part was a storage box used to accommodate tomatoes based on grading. The implementation has the maximum results for detecting color with 100% accuracy and measuring weight with 95% accuracy. However, it still needs development for dimensional measurements. In this research, it has only 5% accuracy. This proposed system can be used both in software and hardware design as an inline tomato sorting tool.

Rapid Softness Prediction and Microbial Spoilage Visualization of Whole Tomatoes by Using Hyper/Multispectral Imaging

The choice of selecting fruit for canned whole tomatoes is driven by several quality attributes including sweetness, acidity, and softness of tomatoes. Moreover, tomatoes can be contaminated with a variety of molds during cultivation, harvest, and transportation. Conventional evaluation operations for tomato softness and microbial spoilage are usually time-consuming, destructive, and high-cost. One strategy for rapid tomato sorting is to utilize hyper/multispectral imaging. This paper proposes to improve on traditional broad-band infrared imaging of existing color and dirt sorters by increasing the spectral resolution of the information collected. The findings of this study will characterize the potential of the technology in terms of predicting tomato softness and identification of tomato microbial spoilage for further development by the industry.

Изменение быстрой фазы флуоресценции хлорофилла при созревании помидоров

Sorting tomatoes by controlling their maturation is an important direction that characterizes the quality and marketability of tomatoes. Therefore, reliable control of the maturation of tomatoes is an actual and practically significant task. Currently, there are known methods of such control (RGB), based on determining the color of tomatoes. These methods have disadvantages, for example, insufficient reliability of monitoring the maturation of tomatoes of various (especially not contrasting in color) varieties, complexity and expensive equipment. (Research purpose) The research purpose is in proposing a new method of rapid sorting of tomatoes based on the control of the minimum (initial) level (Fo) of their rapid phase of chlorophyll fluorescence induction. The time of a single Fo measurement is from 0.01 to 0.07 seconds. (Materials and methods) The article presents mathematical models and conducted experimental studies for the fast phase of chlorophyll fluorescence induction, which confirmed the functional relationship between the maturation of tomatoes and their minimum (initial) level (Fo) of the fast phase of chlorophyll fluorescence induction. Authors used widely distributed botanical varieties of tomatoes "Alcazar", "Lezginka", "Rozanchik" with five stages of maturation (green, brown, pink, light red and red), for each of which we determined the key indicators of chlorophyll fluorescence induction: maximum (Fm), minimum (Fo), variable (Fv) values, the ratio of indicators (Fv/Fm). (Results and discussion) Chlorophyll fluorescence can be used to assess the maturation of tomatoes. As tomatoes ripen, the values of chlorophyll fluorescence parameters, such as Fo, Fm, Fv, and Fv/Fm, decrease. The article presents models that allowed us to estimate the stage of maturation of tomatoes for all three varieties. (Conclusions) The model that used both parameters of chlorophyll fluorescence was the best for three varieties of tomatoes.

Model Design of Tomato Sorting Machine Based on Artificial Neural Network Method Using Node MCU Version 1.0

Tomatoes have different quality and maturity, this is a problem in sorting because it is often wrong on put the grade of tomato marketing and takes a long time in sorting. One solution offered to overcome this problem is a tomato sorting system based on artificial neural network method that can minimizes the sorting time and also places the tomato according to grade. In this research, the model of artificial neural network system backpropagation method on microcontroller NodeMCU Lua version 1.0. The artificial neural network method is used to process the image of tomato objects moving through conveyor in the form of RGB value and captured by color sensor TCS 3200, the image obtained can classify the grade of tomatoes into unripe, half ripe and ripe. This research compared the results of training and testing of artificial neural networks between Matlab R2015a and NodeMCU Lua version 1.0. The outputs or decisions of artificial neural networks will be forwarded to the control system in the form of hardware and software used in this research. The results showed that the tomato sorting model successfully classified the tomato grade, and was able to control motor servo & DC motor automatically based on RGB value with processing time about 5 seconds and error 8.3%.

A computer vision system for defect discrimination and grading in tomatoes using machine learning and image processing

With large-scale production and the need for high-quality tomatoes to meet consumer and market standards criteria, have led to the need for an inline, accurate, reliable grading system during the post-harvest process. This study introduced a tomato grading machine vision system based on RGB images. The proposed system performed calyx and stalk scar detection at an average accuracy of 0.9515 for both defected and healthy tomatoes by histogram thresholding based on the mean g-r value of these regions of interest. Defected regions were detected by an RBF-SVM classifier using the LAB color-space pixel values. The model achieved an overall accuracy of 0.989 upon validation. Four grading categories recognition models were developed based on color and texture features. The RBF-SVM outperformed all the explored models with the highest accuracy of 0.9709 for healthy and defected category. However, the grading accuracy decreased as the number of grading categories increased. A combination of color and texture features achieved the highest accuracy in all the grading categories in image features evaluation. This proposed system can be used as an inline tomato sorting tool to ensure that quality standards are adhered to and maintained.

Evaluation of engineering properties for waste control of tomato during harvesting and postharvesting.

In Iran, more than 30% of agricultural products turn into waste at different stages from harvesting to consumption. Thus, main factors for performing of this present study are including of: (a) the importance of tomato as an agricultural product and (b) lack of information about reducing waste during tomato processing. In this study, some physical, nutritional, mechanical, and hydrodynamic properties of tomato were measured under standard conditions. Physical properties included the length, width, thickness, mean diameter (geometric and arithmetic), mass, volume, density, sphericity, surface area, and aspect ratio. Also, nutritional properties, moisture, dry matter, pH, total soluble solid (TSS), and titration acidity (TA) of tomato were evaluated. The mechanical properties of tomato (compression and shear) were measured using Instron instrument. The hydrodynamic properties were measured with water in transportation, separation, and sorting of tomatoes. The physical properties were including of length, width, thickness, mass, volume, and geometric and arithmetic mean diameters showed a direct relationship with the size of tomatoes. Also, volumetric mass (density) had an inverse relation with tomato size. Yield point and shear force were obtained 51.27 and 22.20 N, respectively. The nutritional properties such as pH value, TSS, and TA were equal to 4.22, 22.23οBrix, and 2%, respectively. The hydrodynamic properties of tomatoes such as the terminal velocity, the tomatoes' rise time in the water column, the buoyancy force, and the drag force were obtained to be equal to 0.05 m/s, 10.11 S, 0.52 N, and 0.17 N, respectively.

Highlights of sixty years of processing tomato research in California

Tomato processing is an integral part of CaliforniaRSQUOs economy and research on tomato breeding, disease resistance and improved quantity and quality of processed tomato products supports this industry. Since 1957, the California League of Food Producers (CLFP) (www.clfp.com) has been funding research on tomato processing. The CLFP has represented both large and small food processors and beverage producers in California since 1905. Research reports dating back to 1957 were reviewed and summaries will be made of the following: 1) topic of research; 2) financial allocation per year; 3) accumulated financial allocation; and 4) average funding per project. Comparison will be made to more production-related research funded by the California Tomato Research Institute (CTRI) over the past 50 years. From 1957-2000, the largest amount of research funding was allocated to the topic of tomato breeding or advanced backcross breeding. Pest and disease resistance were also of great interest, however, after about 2001, very few of these projects were funded. It may be that CTRI funding of breeding and pest/disease resistance became more predominant at this time. Processing studies for new tomato cultivars were an important topic from 1974-2013, at which time the University of California-Davis project was superseded by more extensive studies carried out by two California seed suppliers. Additional research topics of interest included tomato sorting, pectic enzymes and consistency, color, rapid measurement of mold, peelability and quality, and numerous others. Research spanning the 60-year period from 1957 to 2017 will be summarized, and potential topics for future research will be identified. In addition, the potential for international collaborations with other WPTC members will be discussed.

An Intelligent Hybrid Experimental-Based Deep Learning Algorithm for Tomato-Sorting Controllers

Conventionally, the methods used for the sorting of tomatoes are manual. These methods are costly, non-productive, and their reliability is uncertain. With advancing technology, deep-learning, and artificial intelligence techniques are being utilized to develop fully automated system controllers. The primary reason behind using these techniques is their competitive performance in solving high nonlinear classification problems. Therefore, this paper investigates the performance and combination scenarios of a number of effective artificial intelligence techniques and strategies. Improving the classification accuracy of automated tomato-sorting controllers shall also be explored. Convolution neural network (CNN), artificial neural network (ANN), self-organizing map (SOM), learning vector quantization (LVQ), and support vector machine (SVM) are developed, optimized, assessed, and compared. In this paper, three main categories are considered, namely, unripe, ripe, and defective (overripe and rotten). Moreover, an experimental setup is designed, manufactured, and tested to verify the computational results obtained from the neural networks as well as to assess the real-time performance of the proposed algorithm. As per the research findings, the utilization of a hybrid CNN-ANN-based algorithm is favored, as it demonstrated a superior performance during validation and experimental testing. The CNN-ANN-based control algorithm yielded a theoretical classification performance of 100% for all classes while the experimental results produced 100% for unripe and ripe classifications and 90% for the ripe and defective (overripe and rotten) classifications. The results of this paper have the potential to improve the classification accuracy of similar fruit and vegetable sorting machines.

Selecting optimal wavelengths for detection of insect infested tomatoes based on SIMCA-aided CFS algorithm

Selection of effective wavelengths is a decisive step for online multispectral imaging systems. In this study, a new approach was utilized to distinguish the most informative wavelengths for detection of insect infestation in tomatoes within 400–1100nm. Soft independent modeling of class analogy (SIMCA) was first conducted in the entire spectral region after applying different pretreatment procedures. Following satisfactory results obtained from 1st derivative preprocessing (accuracy of 90%), the most effective wavebands for detection of infestation were attained by discrimination power plot of SIMCA analysis. Transmission differences between all possible pairs of wavelengths (T(λ1)–T(λ2)) in the obtained informative wavebands were then calculated to substitute the 1st derivative spectra. Afterward, correlation-based feature selection (CFS) algorithm was used to find the best pairs of wavelengths. To compare the performance of SIMCA-aided CFS procedure, CFS was also conducted on the raw spectral data. Seven spectral difference features and six wavelength features were found superior by CFS. To classify tomatoes, three different machine learning techniques including Bayesian networks (BNs), artificial neural networks (ANNs), and support vector machines (SVMs) were implemented. The test set validation results of all machine learning techniques revealed that the spectral difference features outperformed the raw spectra features, indicating the superiority of SIMCA-aided CFS procedure for detection of optimal wavelengths. Among different machine learning techniques, the best performance obtained by ANN based on spectral difference features with a classification accuracy of 95.0%. The results of this study can be adapted for developing an online tomato sorting system for detection of infestations.

A STUDY ON COLOR SORTING OF TOMATOES MATURITY USING MACHINE VISION AND ARTIFICIAL NEURAL NETWORKS

tomatoes are commercial commodies that play a major role in Egyptian economy. They are considered one of the major vegetable crops in Egypt because of its nutritional, consumption, processing and export value. They may be harvested at different maturity stages and each maturity stage has its characteristics of quality. On the other hand, acceptance of tomato for eating depends on many factors such as variety, texture, maturity, size, shape etc. In this study, a simple machine vision system was developed for sorting three maturity classes of tomatoes grown in Egypt. For the sorting analysis, three color features L*,a* and b* were extracted from each tomatoes class images. Nine different color features are calculated from the three color features. An artificial neural network classifier with Backpropagation method was tested. The input layer consists of twelve color features, the hidden layer consists of twelve nodes and the output layer consists of three nodes representing three tomatoes classes (green, pink and red). The best sorting accuracies in testing data set are 100%, 92.9% and 100% for green, pink and red classes, respectively. The overall sorting accuracy is 97.9%. Finally, based on the obtained results, a tomato sorting machine can be designed to categorize 3 colors of tomatoes decreasing human labor and to reducing sorting time.

COMPUTERIZED SPOILED TOMATO DETECTION

In this paper illustrates the improvement of a low cost machine vision system using webcams and image processing algorithms for defect detection and sorting of tomatoes The sortin g decision was based on three features extracted by the different image processing algorithms. This methodology based on the color fea tures, which used for detecting the BER from good t omatoes. Two methods were developed for decision based sorting. The color ima ge threshold method with shape factor was found eff icient for differentiating good and defective tomatoes. The overall accuracy of def ect detection attained was 94 and 96.5% respectivel y. Comparison of the results is also presented in this paper.

Online tomato sorting based on shape, maturity, size, and surface defects using machine vision

Online sorting of tomatoes according to their features is an important postharvest procedure. The purpose of this research was to develop an efficient machine vision-based experimental sorting system for tomatoes. Relevant sorting parameters included shape (oblong and circular), size (small and large), maturity (color), and defects. The variables defining shape, maturity, and size of the tomatoes were eccentricity, average of color components, and 2-D pixel area, respectively. Tomato defects include color disorders, growth cracks, sunscald, and early blight. The sorting system involved the use of a CCD camera, a microcontroller, sensors, and a computer. Images were analyzed with an algorithm that was developed using Visual Basic 2008. In order to evaluate the accuracy of the algorithms and system performance, 210 tomato samples were used. Each detection algorithm was applied to all images. Data about the type of each sample image, including healthy or defective, elongated or rounded, small or large, and color, were extracted. Results show that defect detection, shape and size algorithm, and overall system accuracies were 84.4%, 90.9%, 94.5%, and 90%, respectively. System sorting performance was estimated at 2517 tomatoes h^{-1} with 1 line.

독립성분분석을 이용한 RGB 이미지 토마토 분류

Abstract Tomatoes were harvested at different ripening stages. To determine the ripening stages, We analyzed the relation between the compound concentrations of tomato measured with HPLC and the tomato RGB images. Among the compound concentrations, tomato quality is mostly affected by the Lycopene. The   error of the predicted Lycopene concentration and the corresponding independent component of tomato RGB image, determined from the PLS procedure, was 0.92. and we show the effectiveness of the independent component by comparing the error between the pixel area of RGB image applied by independent component and the simple black white tomato image. This regression made it possible to construct concentration images of the tomatoes, which showed non-uniform ripening. The method can be applied in an unsupervised real time sorting machine of unripe and discolored tomato using the compound concentrations. Key Words : Independent Component Analysis, Tomato sorting, Concentration image * 교신저자 : Ki-Hyeon KwonTel: +82-10-4424-7591 e-mail: kweon@kangwon.ac.kr접수일 12년 01월 03일 수정일 12년 01월 17일 게재확정일 12년 03월 08일

Analysis on Actuating Mechanism for Tomato Color Sorting Robot Based on High-Speed Photography

To separate objects (immature tomatoes, foreign material) accurately from tomatoes using actuating mechanism of tomato color grading robot, high-speed photography was used to acquire images the tomato sorting process for studying effect between tomato cast position and track for separating. Test results show that tomatoes cast position affects tomato sorting; tomato track from conveyer belt affects the hitting position of pneumatic ejection finger directly. High-speed photography is used for tomatoes sorting process analysis at high speed, which can be helpful for design of tomato color sorting robot.

Postharvest firmness changes as measured by acoustic and low-mass impact devices: a comparison of techniques

Two commercially available non-destructive firmness sensors, one based on acoustic impulse response (AFS) and one on low-mass impact (SIQ-FT), were compared for the quality assessment of apples and tomatoes during a storage experiment. The aim was to quantify the repeatability of the sensors, the correlation between them, their ability to sense firmness decay during the storage experiment and their ability to sort fruit of a given batch. Our study shows that for apples, both sensors have a good repeatability and overall, the correlation between the measurements of both devices was rather high ( r = 0.88), but when considering the practical case of a given batch at a given time, inherently possessing smaller variability, the correlation was low. It was further shown that for AFS the uncertainty (measurement error by the device augmented by eventual model error) is lower than the natural heterogeneity of the considered batch during the whole experimental period denoting that the device is capable of sorting fruit for firmness. In case of SIQ-FT, the uncertainty was larger than the batch heterogeneity. For tomatoes, the repeatability was worse than for apples, but still acceptable during the whole experimental period for SIQ-FT. During softening, AFS showed low repeatability. The correlation between both techniques was also lower ( r = 0.70 overall). For both instruments, uncertainty was larger than the true batch heterogeneity, and increased during the experimental period indicating that tomato sorting is difficult, and should be performed as soon as possible after harvest.