Figure - available from: Journal of Food Quality
This content is subject to copyright. Terms and conditions apply.
Source publication
As a cost-effective and nondestructive detection method, the machine vision technology has been widely applied in the detection of potato defects. Recently, the depth camera which supports range sensing has been used for potato surface defect detection, such as bumps and hollows. In this study, we developed a potato automatic grading system that us...
Similar publications
Field experiment was conducted in Chora District of south western Ethiopia, to evaluate the effect of different rates of coffee husk compost (CHC) and 18.9N + 37.7P + 6.94S + 0.15B (NPSB) in the form of NH4, P2O5, SO4−, and B2O5, repectively, blended fertilizer on selected soil chemical properties of potato field during 2021. The treatment consiste...
Citations
... One is mechanical grading [4][5][6], predominantly employing mesh and drum mechanisms, capable of efficiently grading and processing large quantities of potatoes in a short amount of time and featuring a simple operation [7][8][9][10]. The other direction is machine vision grading [11][12][13], offering higher grading accuracy without requiring direct contact with potatoes, reduced the damage to potatoes [14][15][16][17]. Mechanical grading equipment for potatoes is relatively inexpensive compared to machine vision technology. ...
Traditional potato grading in China relies mostly on manual sorting, which is labor-intensive, time-consuming, costly, and inefficient. To enhance the operational performance of potato-grading devices, this paper focuses on optimizing the slide rail structure, which is the key component of a self-developed first-generation potato-grading device. A five-factor, three-level orthogonal experiment was designed, with the experimental factors being the height of the horizontal slide rail, angle of the first-stage inclined slide, angle of the second-stage inclined rail, chain horizontal movement speed, and conveyor belt speed. The indoor experiments were conducted using grading accuracy and grading efficiency as the experimental indicators. On the basis of the analysis of the orthogonal experiment results, two relatively optimal solutions were obtained, and validation experiments were conducted. The validation results show that when the height of the horizontal slide rail was 185 mm, the angle of the first-stage inclined rail was 4°, the angle of the second-stage inclined rail was 2.5°, the horizontal movement speed of the chain was 700 mm/s, and the movement speed of the conveyor belt was 275.60 mm/s, the performance of the movable rotating plate (MRP)-type grading device for potatoes reached its optimum. At this point, the grading accuracy was 94.88%, and the grading efficiency was 13.9477 t/h. Compared with the first-generation grading device, the optimized grading device achieved an improvement of 3.84% in grading accuracy and 12.94% in grading efficiency. The research methodology provided in this paper serves as a reference for the performance optimization of potato-grading devices.
... Additionally, some researchers have embraced cutting-edge technologies such as machine vision, spectral analysis, and neural networks to conduct precise analyses and identification of potatoes. This enables the potato shape, quality, and damage conditions to be assessed with remarkable accuracy, facilitating more refined and efficient grading processes (Su et al., 2017;Su et al., 2018;Su et al., 2020;Zhang et al., 2019). ...
Existing potato grading device has a complex structure and a large volume, which is not suitable for small‐scale potato farmers. However, traditional manual grading methods not only have low efficiency but also high labor costs. This article developed a small movable rotating plate (MRP)‐type potato grading device, and the influences of three factors (the height of the horizontal slide, the tilt angle of the inclined slide, and the chain speed) on the grading efficiency and accuracy were investigated using the discrete element method and virtual orthogonal experiments. It was found that the horizontal slide height of 185 mm, the inclined slide tilt angle of 3.5°, and the chain speed of 0.9 m/s yielded the optimal grading efficiency (13.84 t/h) and grading accuracy (94.11%). Finally, the potato grading process was tested and validated through indoor tests, and the optimal grading accuracy was 91.04%. The grading accuracy deviation between the test and simulation results was less than 8%.
Practical Application
Currently, most commercial potato grading machines are designed for large‐scale farms, which are not suitable for developing countries. The potato grading device designed in this article can not only be used independently by small‐scale farms, but also be integrated with potato combine harvesters to achieve potato harvest and grading joint operations. This grading device has a simple structure, small footprint (1700 × 1200 × 840 mm³), and a very low cost ($600). With a high grading efficiency and accuracy, it can significantly improve the grading productivity of small and medium‐sized potato farmers in developing countries, reduce the production costs, and save labors.
... Therefore, there is an urgent need to develop an automatic, non-destructive cucumber grading technology and corresponding equipment. With the widespread application of machine vision and mechatronics technology in agricultural production [6][7][8][9], an effective approach is provided for the design of a cucumber grading machine. ...
The North China type cucumber, characterized by its dense spines and top flowers, is susceptible to damage during the grading process, affecting its market value. Moreover, traditional manual grading methods are time-consuming and labor-intensive. To address these issues, this paper proposes a cucumber quality grader based on machine vision and deep learning. In the electromechanical aspect, a novel fixed tray type grading mechanism is designed to prevent damage to the vulnerable North China type cucumbers during the grading process. In the vision grading algorithm, a new convolutional neural network is introduced named MassNet, capable of predicting cucumber mass using only a top-view image. After obtaining the cucumber mass prediction, mass grading is achieved. Experimental validation includes assessing the electromechanical performance of the grader, comparing MassNet with different models in predicting cucumber mass, and evaluating the online grading performance of the integrated algorithm. Experimental results indicate that the designed cucumber quality grader achieves a maximum capacity of 2.3 t/hr. In comparison with AlexNet, MobileNet, and ResNet, MassNet demonstrates superior cucumber mass prediction, with a MAPE of 3.9% and RMSE of 6.7 g. In online mass grading experiments, the grading efficiency of the cucumber quality grader reaches 93%.
... DL models have demonstrated their strong abilities in classification and regression tasks, but their effectiveness largely depends on having a sufficient amount of data that accurately represents the specific problem [11,12]. The classification machine learning models with a convolutional neural network produced a high success rate for size and appearance classification [13,14] in many applications such as the potato quality grading system, which is based on machine learning models that contain 3D potato appearance data [15,16]. ...
... Quality is a critical aspect of the modern food industry because the success of a product in today's highly competitive market is largely [11][12][13] dependent on its high quality. The quality of a substance determines its internal and exterior properties [14][15][16]. The observation of the dehydration procedure involved more than simply measuring weight and moisture content. ...
... Su et al. analyzed the appearance and size characteristics of potatoes using a convolutional neural network. Non-destructive grading of potatoes was achieved [16]. Tian et al. analyzed the image features of apples using the YOLOv3 model. ...
At present, the surface quality of Yuba skin is determined by sensory methods. In order to realize the intelligent classification detection of Yuba skin quality, this study designed a system that automatically determines the quality of Yuba skin surfaces based on image processing and support vector machine (SVM) approaches. Specifically, the system uses image preprocessing to extract the grayscale eigenvalues, gray level co-occurrence matrix (GLCM) eigenvalues, and gray level run length matrix (GLRLM) eigenvalues of the sample image and uses them as input values for a quality grading system. Through model evaluation of three classification models, the SVM classification model was selected according to the evaluation results, and different kernel functions were used in the model for sample training. Based on Matlab, the quality grading software of Yuba skin was developed and designed. Intelligent detection and grading were realized through the radial basis kernel function support vector machine (RBF-SVM) grading model. The best penalty factor (c = 3.50) and kernel parameter value (g = 0.98) were obtained through cross-validation. The accuracy of the model was 95.31% and 94.16% for the training and test sets, respectively. The grading accuracy of the RBF-SVM grading system was 93.56%, and the error was less than 5% compared with the traditional sensory method of grading; thus, the quality classification method based on the SVM classification system for Yuba skin is feasible and can be used for quality detection.
... The 3D camera can work stably under LED or fluorescent lighting, because the light source of the 3D camera is infrared radiation. It was noticed that the camera can be successfully used to detect unevenness, damage, and depressions, but it is not sensitive enough to identify surface sprouts [97]. ...
This article describes chemical and physical parameters, including their role in the storage, trade, and processing of potatoes, as well as their nutritional properties and health benefits resulting from their consumption. An analysis of the share of losses occurring during the production process is presented. The methods and applications used in recent years to estimate the physical and chemical parameters of potatoes during their storage and processing, which determine the quality of potatoes, are presented. The potential of the technologies used to classify the quality of potatoes, mechanical and ultrasonic, and image processing and analysis using vision systems, as well as their use in applications with artificial intelligence, are discussed.
... Previous works have predicted potato quality in disease or defect detections utilizing computer vision and learning algorithms. Those researchers utilized several algorithms, like the Softmax-based machine learning model [24], the Fixed Intensity Interception (FII) method [25], [26], SVM [9], ANN [27], and neural image analysis method [8]. The first advantage of this Fast.ai ...
The world population is constantly rising with a parallel surge in the agriculture sector to meet the growing demands. There is a need to have an effective strategy for classifying agricultural products on a quality basis. Artificial intelligence and computer vision methodologies can have applications in detecting and analyzing the quality of food products. Potato is one of the most cherished crops, particularly in India; hence, it is essential to perceive the potatoes' quality as they are vulnerable to catching any disease or getting rotten quickly. Prior studies have been conducted using various learning algorithms and models. In this work, we have utilized a deep learning approach called transfer training via the Fast.ai framework. Our prime objective was to detect and differentiate the potatoes based on three classes, i.e., healthy, diseased, and rotten potatoes, that could finally achieve an acceptable classification accuracy.
... Food materials differ in, such as their chemical compositions and physical structures and have unique optical properties, such as absorptance and reflectance, which have been widely used to determine their properties. In recent years, hyperspectral imaging (HSI), Raman imaging (RI), fluorescence imaging (FI), soft X-ray imaging, laser light backscattering, light microscopy, and magnetic resonance imaging (MRI) have been used to determine food qualities such as the authenticity of edible oil [11], varieties and geographical origins [12], food spoilage [13], and grades [14]. In some cases, due to the high level of complexity of the spectral data, machine learning (ML) based imaging techniques, such as convolutional neural network (CNN) and recurrent neural networks (RNN) [15], are used to conduct classification and determination. ...
The determination of the levels of roasting of cocoa relies on expensive analytical equipment, sensory panel, and, in the cases of small processors and growers, empiricism. In this study, cocoa beans were roasted for 10-40 min to obtain different levels of roasting, and the images of the beans were captured by a smartphone camera. An extreme learning machine (ELM)-based algorithm was developed to predict the roasting degree of cocoa beans using the images of the cocoa bean cross-sections. A 22-dimension feature vector, including color and texture features, is extracted from each sample, and a total of 350 samples are used to train an ELM network. A majority rule-based voting method was used to make the decision. Experimental results showed that the proposed method achieved a classification accuracy of 93.75%. GC-MS analysis was conducted to determine the chemical compounds in the raw and roasted cocoa beans, and enrichment analysis, principal components analysis, partial least-squares-discriminant analysis, and Pearson correlation analysis were conducted to identify major chemicals respond to roasting time and classify the cocoa beans samples. Caffeine and theobromine were identified as primary chemical compounds that responded to roasting time, and cocoa beans with different levels of roasting were successfully classified.
... Machine vision technologies make it possible not only to sort fruits according to commercial strategies, but also to remove unwanted fruits from the conveyor. Similar studies are carried out by Su et al. [11] during the detection of potato defects by machine vision. ...
The article analyzes the process of natural restoration of the main component of the soil-humus, as a result of which the dependence of the thickness of the humus layer on the number of plants embedded in the soil was revealed. The technological process of surface tillage requires constant monitoring of the completeness of plant burying. The article analyzes the literature, which showed that machine vision systems are widely used in agriculture, for example, when detecting weeds for spot treatment with herbicides, analyzing citrus forms and diseases, automated counting of roundworms of cut trees, etc. A machine vision system is proposed as a control tool for detecting weeds on the soil surface. The authors proposed their own approach to control the completeness of burying pruned weeds in the soil using machine vision systems. The work of our own program for detecting weeds on the soil surface is described in detail and step by step. The program's operability was checked on some plant models and its effectiveness of reliable operation was confirmed. Experimental studies were conducted in the laboratory. Based on the results of research in the computer program developed by the authors, the following results were obtained: photos of the soil surface were analyzed; contours of plant models were identified; plant areas and their percentage in relation to the image area were determined, and a message was received on the screen about the presence of weeds on the surface in accordance with agrotechnical standards.
... Lopez [5], a case is described, with respect to a company dedicated to the food industry, in which the switching on and off of the production process is purely mechanical and manual, controlled by a staff who acted as operator, whose job was to flip a start and stop switch, this is the case [6] it is stated that in non-automatic processes, the function of the opposites is to interrupt the filling of inputs to obtain the product, said control strategy does not guarantee a balanced dosage of inputs. Now in relation to the production process related to the production of instant yellow potato puree, in [7], it is pointed out that Peru has an enviable variety of potatoes, but its low industrialization generates limited development opportunities for its producers. In response to the problem mentioned in the previous paragraphs in [8]- [10] it is indicated that the manufacturing processes in the food industry are capable of being automated to improve efficiency with the use of low cost, low maintenance and high maintenance systems durability. ...
p>The article describes a control logic used to automate the mixing stage of the instant mashed potato process, in order to improve the quality of the final product. Thus, initially the characteristics of the automated process are detailed, specifying the programming logic on the programmable logic controller, to later demonstrate through a data collection process the percentage of improvement in the quality of the final product from the perspective of the users. Indicators: percentage of humidity in the mixing stage, water absorption index (IAA), water solubility index (ISA) and hydrogen potential (pH). The development of the research concludes that the automation of the process, achieved that the IAA index and the ISA index, obtained in the spraying stage, improve by 8.13% and 23.05%, respectively, finding analyzed values within the optimal ranges. This in turn reflected a 39.61% improvement with respect to the humidity percentage, measured in the mixing stage, thus improving the quality of the final product, which brings with it a significant increase of 84.44% in production levels.</p
