Automatic Sorting Research Articles

Anti-corrosion wood automatic sorting robot system based on near-infrared imaging technology

To implement the discovery of discarded anti-corrosion wood, an automatic sorting robot system was built. Three kinds of commonly used wood were selected as the research object, which uses hyperspectral imaging technology to achieve the identification. In the range of 900–1700 nm (230 bands), the infrared spectra of three kinds of anti-corrosion wood were collected, and then the characteristic information was obtained through the analysis of MATLAB to distinguish them. Among them, three kinds of preservative woods are Scots pine (add CCA treatment), Pseudotsuga menziesii (high-temperature carbonization treatment) and Incense Cedar (pressurized treatment). After the pretreatment by the Savitzky-Golay method, spectral data were conducted by principal component analysis (PCA), and the contribution rate of the first three principal components reached 99.902 %. Besides, through the loading coefficients of the first three principal components that were plotted on the wavelength, we obtained five characteristic wavelengths and corresponding reflectance information, simultaneously; this set up a typical discriminant analysis model. Then, the model was validated by the validation set, and the accuracy rate of the prediction set was 98.89 %. This method can effectively identify and classify three kinds of anti-corrosion wood, which can provide a scientific method and basis for a solid waste sorting system.

Fast identification method for express end sorting label code based on convolutional recurrent neural network

In the automatic sorting process of express, the express end sorting label code is used to indicate that the express is dispatched to a specific address by a specific courier. Since there are many areas on the express bill containing digital information, some areas may be improperly photographed, etc. The difficulty in positioning and recognizing the express end sorting label code region is increased. To solve this problem, this paper proposes an express end sorting label code recognition method with convolutional recurrent neural network for the code specification, which has certain versatility. In order to improve the overall code recognition speed, this paper optimizes the traditional digital recognition method, removes the original segmentation operation of the character and recognizes the code as sequence recognition. Firstly, the coding region is located, and then, the express end sorting label code is recognized by the convolutional recurrent neural network. In order to test the experimental performance, this paper tests on Free-Type dataset and SUN-synthesized dataset. The experimental results show that the proposed method improves the recognition accuracy and processing speed of the express end sorting label code.

Design and Fabrication of Automatic Sorting Machine using Arduino

This work is based on Design of a transport line conveyor belt for sorting and arranging products based on their height using the IR sensors for detecting the object and mechanism to drive the conveyor belt. The project is locally controlled by the use of Arduino based embedded system. The automatic sorting and arranging machine are used to sort the different types of products based on the product height. This automation significantly reduces the time required for manual sorting in the production line of small/medium scale industries and hence it also decreases the percentage of human error during sorting/arranging. The products are placed on the transport line conveyor system and as it moves on the conveyor it is scanned by the IR sensor, depending on the height of the product these will be sorted into different bins automatically.

Automatic sorting of recycled aggregate using image processing and object detection

Automatic sorting of recycled aggregate using image processing and object detection

An automatic sorting system for unwashed eggs using deep learning

Egg quality and safety are significant concerns of consumers and modern food industries. This study proposes a novel and precise assessment of egg sorting using a deep convolutional neural network (CNN), which is a state-of-the-art computer vision method to perform classification tasks. To classify unwashed egg images, VGG16 architecture was modified by a global average pooling layer, dense layers, a batch normalization layer, and a dropout layer. The modified model was trained based on intact, bloody, and broken (breakage, crack, or hole on the eggshell) eggs, which were combined with being dirty. Performance evaluation of the CNN model through 5-fold cross-validation showed that it outperforms traditional machine vision-based models. The accuracy, precision, sensitivity, specificity, and area under the curve were 96.55, 95.59, 94.92, 97.39, and 96.16%, respectively. The CNN model achieved an average overall accuracy of 94.84 by 5-fold cross-validation.

Image Text Deblurring Method Based on Generative Adversarial Network

In the automatic sorting process of express delivery, a three-segment code is used to represent a specific area assigned by a specific delivery person. In the process of obtaining the courier order information, the camera is affected by factors such as light, noise, and subject shake, which will cause the information on the courier order to be blurred, and some information will be lost. Therefore, this paper proposes an image text deblurring method based on a generative adversarial network. The model of the algorithm consists of two generative adversarial networks, combined with Wasserstein distance, using a combination of adversarial loss and perceptual loss on unpaired datasets to train the network model to restore the captured blurred images into clear and natural image. Compared with the traditional method, the advantage of this method is that the loss function between the input and output images can be calculated indirectly through the positive and negative generative adversarial networks. The Wasserstein distance can achieve a more stable training process and a more realistic generation effect. The constraints of adversarial loss and perceptual loss make the model capable of training on unpaired datasets. The experimental results on the GOPRO test dataset and the self-built unpaired dataset showed that the two indicators, peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), increased by 13.3% and 3%, respectively. The human perception test results demonstrated that the algorithm proposed in this paper was better than the traditional blur algorithm as the deblurring effect was better.

Automatic Sorting Machine

Businesses around the world automate their outbound profiling and sortation process for an increased productivity. Sorting plays a key role in any industrial automation, particularly in the field of packaging industries. This paper aims at providing significant low-cost automation in packaging industries that calls for sorting and how the implication of pneumatics can yield a desirable solution. The prototype of the automatic sorting machine allows a systematic sorting of the carton boxes corresponding to their sizes using a pneumatic system, which is achieved by using pneumatic cylinders and direction control valves. The sorted carton boxes are shoved from the main line conveyor to the sub-line conveyor using the pneumatic cylinder, which is then collected and dispatched to the next division for the packaging purposes. Using this approach, the packaging industries can attain the maximum benefits thereby enabling a surge in their production.

Multisource Model-Driven Digital Twin System of Robotic Assembly

The digital twin technology effectively fuels improvements in the quality and efficiency of robotic assembly, especially for sophisticated processes. High-quality digitalization requires a comprehensive description and real-time rendering of system, which are challenging. This article aims to demonstrate a novel multisource model-driven digital twin system, which is based on the geometric, physics, and sequential rule descriptions for producing a precise and real-time simulation of a robotic assembly system. In our system, the digital counterpart rendered with virtual reality technology is created and updated by the real environment information. A 3-D graphic model is reconstructed first using the geometric information of surroundings captured by the depth sensor. During interaction, a fast and efficient approach is proposed to generate the contact force and render the object deformation in the virtual environment. The virtual space also provides the sequential rule that is based on the danger field, which helps to constrain the operation of digital twin. At last, the experimental platform is established in which the virtual space is at an update rate of 100 Hz, while the automatic sorting task is performed and verified; the results show the effectiveness and applicability of the method to digital twin system.

Stable grasp planning based on minimum force for dexterous hands

The paper investigates a grasp planning method for dexterous hands grasping different objects. It aims at planning the robotic hands’ grasping position and applied force of each finger, respectively, in order to realize a stable grasp by using minimum force. We optimize grasp stability by the principle of the maximum internal tangent sphere and conduct a stable grasp planning based on minimum force which is considered to avoid breaking either the dexterous hand or the object. Calculation examples are provided in order to verify that our process is correct. Furthermore, grasp planning experiments are also carried out and analyzed in accordance with the UR-Barrett Hand system. It is found that the dexterous hand is able to grasp different shapes of objects with a high success rate. In addition, the applied force is the minimum force to grasp objects stably. It is likely to be widely used in many fields, such as service, medical treatment and automatic sorting, which have strict requirements on force to avoid breaking objects.

Design and Test of a Sorting Device Based on Machine Vision

At present, the sorting of agricultural products in China mainly relies on manual labour, which results in low efficiency, and the development of corresponding automatic equipment lags behind. The grasping method based on machine vision has been widely used in industry, and can provide a reference for the automatic sorting of agricultural products. In this paper, an automatic sorting device for agricultural products was designed. The grasping mechanism adopted a 4-degree-of-freedom (4-DOF) manipulator, and the machine vision control system adopted a monocular camera, which can realize the positioning and classification of the grasp-target. First, the geometric model of the manipulator was established, and the kinematics model of the manipulator was established via the Denavit-Hartenberg (D-H) parameter method. Next, the kinematics analysis and verification were carried out. Then, Zhang Zhengyou calibration method was used to calibrate the camera. An image processing method based on histogram correction was proposed. Based on this, a target positioning algorithm based on the pinhole imaging principle and a target classification algorithm based on the area threshold were established. Finally, an automatic sorting test platform for agricultural products using a visual servo was built. Target classification, positioning and sorting tests were conducted using tomatoes and oranges as the test objects. The test results show that the success rate of the target positioning is close to 98%, that of the target classification is close to 98% and that of the grasping is close to 95%. Furthermore, the sorting time of a single target object can be as fast as 1 second, which can meet the requirements of automatic sorting for common agricultural products. The automatic sorting device for agricultural products has a simple structure, reliable performance and low costs. The structure and algorithms proposed in this paper are simple, reliable, and highly efficient and thus can easily realize technology transplantation. These relevant methods provide a theoretical reference for the development of an automatic sorting device for agricultural products.

Study on duck weight estimation by using image processing

The objective of this research was to process digital image to investigate the possibility of ducks weight estimation based on the software LabVIEW with the vision builder. In this study the images were record by the top-view camera. An ellipse fitting algorithm was applied to localize ducks within the stall. Estimating duck weight consists of these steps. First, image acquisition. Second, counts pixel of the samples. Third calculate duck weight by using samples pixel as the output. Results from this study showed that, the estimated ducks weight by using digital photos had 3.27% of the error when compare to the measured weight. The correlation coefficient of the body weight prediction equation from a comparison between measured (absolute) and estimated by camera for all duck is clearly high (R2=0.91). It was found that the system able to estimate duck weight with an acceptable error. So we can develop this research processing or build up the automatic sorting duck in the future. This method operated pretty well in prophecy live weight.

Precision conservation: from visual analysis of soil aggregates to the use of neural networks

The concept of precision conservation can be defined as a set of space technologies and other procedures linked to mappable environmental variables. These technologies and procedures can be used to program conservation management practices for natural resources that take into account the variability of such variables in space and time within natural or agricultural systems. In this context, the structural loss of soil due to human activities is considered as a process with spatial and temporal variations. The management of soil aggregation conditions can contribute to more regenerative and sustainable agricultural processes. It admits spatial analysis technologies through georeferenced visual indicators or even the use of systems with automatic learning, known as deep learning. In this sense, a fair visual method was developed with analysis of fuzzy logic to classify aggregates in terms of shape, surface roughness, and biogenic structures. Thus, in a second stage, a model of artificial neural network was developed. This model is capable of detecting and classifying different forms of soil aggregates, thus enabling a brief discussion of the topic and its potential application in conservation management through the analysis of aggregates via automatic sorting systems. Elements of research motivation and development on adaptive technologies are presented to support decision-making that can help integrate dynamic and spatial information for understanding of the structural condition of soil and hence its more precise preservation.

Improved Feature Extraction Method for Sound Recognition Applied to Automatic Sorting of Recycling Wastes

Improved Feature Extraction Method for Sound Recognition Applied to Automatic Sorting of Recycling Wastes

The Research of Recognizing the Class of Wastes Applying Generation of Various Shapes Images by DCGAN.

Construction wastes discharged from the dismantling site is sorted for each type by the heavy machine or the hand of a person at the site and transported to the treatment plant. The social needs of the construction wastes automatic sorting system has been increasing due to soaring labor costs and labor shortage. In this paper, we describe recognizing the class of wastes applying generation of various shapes images by DCGAN.

Способ и устройство для автоматического распознания некондиционных клубней картофеля

The aim of the article is to improve the quality and productivity of sorting by developing a method and an intelligent device for automatic recognition and inspection of substandard potato tubers. The article describes a prototype of an automatic sorting machine designed to recognize external defects in potato tubers and automatically inspect them with a jet of compressed air. The recognition process consisted of three main modules: segmentation, tracking a potato moving in a frame along a conveyor belt, and classification using a trained artificial neural network. For the segmentation of potato tubers against the background of the transporting conveyor in real time, a method based on the calculation of the color threshold was used. The centroid tracking algorithm was used to track moving potato tubers. To train the artificial neural network, we created our own dataset consisting of images of marketable and defective potato tubers. A prototype of an automatic sorting machine has been developed, which is based on the concept of intelligent data analysis, according to which the images of potato tubers obtained from a video camera are processed and formed into images with subsequent recognition and signaling to the executive device of the automatic inspection system in the form of a single pulse signal when determining the tuber as substandard.

Deep Learning-Based Fake-Banknote Detection for the Visually Impaired People Using Visible-Light Images Captured by Smartphone Cameras

Automatic recognition of fake banknotes is an important task in practical banknote handling. Research on this task has mostly involved methods applied to automatic sorting machines with multiple imaging sensors or that use specialized sensors for capturing banknote images in various light wavelengths. These approaches can make use of the security features on banknotes for counterfeit detection. However, they require specialized devices, which are not always available for general users or visually impaired people. Meanwhile, smartphones are becoming more popular and can be useful imaging devices. Moreover, the types of fake banknotes created by imaging devices such as smartphone cameras or scanners are sometimes cannot be recognized by especially the visually impaired people. Addressing these problems, we propose a method for classifying fake and genuine banknotes using visible-light images captured by smartphone cameras based on convolutional neural networks. Experimental results on a self-collected dataset of US dollar, Euro, Korean won, and Jordanian dinar banknotes showed that our method performs better in terms of fake detection than the state-of-the-art methods.

Affinity of dual energy X-ray transmission sensors on minerals bearing heavy rare earth elements

This work demonstrates the effective use of automatic sensor-based sorting technology as a viable separation method for rare earth element (REE) rich ores composed primarily of xenotime minerals with gagarinite-(Y) and fluocerite-(Ce, La) inclusions. A dual energy X-ray transmission (DE-XRT) sensor affinity was used to evaluate forty-two heavy rare earth element (HREE) ore grab samples from the Madeira deposit. These samples and separated products were scanned by the sensor under many operating parameters. Subsequent analyses, including petrographic and multi-element chemical analyses were performed on the grab samples. Specific mass tests were also compared with energy attenuation curves from the sensor, which correlated strongly with every concentration stage – the highest achieved density being 3.01 g/cm3. The best estimated HREE recovery from laboratory-scale sorting of the samples identified by the sensor was effectively 100%, however this occurred in conjunction with a mass recovery equal to 97% of the feed. Such results are expected knowing that the sample method was not entirely representative. Ongoing research into automatic sorting technology for the upgrading of Brazilian ores is being performed by the Federal University of Rio Grande do Sul (UFRGS), Brazil.

Adaptive Binarization of QR Code Images for Fast Automatic Sorting in Warehouse Systems

As the fundamental element of the Internet of Things, the QR code has become increasingly crucial for connecting online and offline services. Concerning e-commerce and logistics, we mainly focus on how to identify QR codes quickly and accurately. An adaptive binarization approach is proposed to solve the problem of uneven illumination in warehouse automatic sorting systems. Guided by cognitive modeling, we adaptively select the block window of the QR code for robust binarization under uneven illumination. The proposed method can eliminate the impact of uneven illumination of QR codes effectively whilst meeting the real-time needs in the automatic warehouse sorting. Experimental results have demonstrated the superiority of the proposed approach when benchmarked with several state-of-the-art methods.

Multi-objective AGV scheduling in an automatic sorting system of an unmanned (intelligent) warehouse by using two adaptive genetic algorithms and a multi-adaptive genetic algorithm.

Automated guided vehicle (AGV) is a logistics transport vehicle with high safety performance and excellent availability, which can genuinely achieve unmanned operation. The use of AGV in intelligent warehouses or unmanned warehouses for sorting can improve the efficiency of warehouses and enhance the competitiveness of enterprises. In this paper, a multi-objective mathematical model was developed and integrated with two adaptive genetic algorithms (AGA) and a multi-adaptive genetic algorithm (MAGA) to optimize the task scheduling of AGVs by taking the charging task and the changeable speed of the AGV into consideration to minimize makespan, the number of AGVs used, and the amount of electricity consumption. The numerical experiments showed that MAGA is the best of the three algorithms. The value of objectives before and after optimization changed by about 30%, which proved the rationality and validity of the model and MAGA.

INTELLIGENT SYSTEM FOR AUTOMATIC CLASSIFICATION OF FRUIT DEFECT USING FASTER REGION-BASED CONVOLUTIONAL NEURAL NETWORK (FASTER R-CNN)

In 2018, the Indonesian fruit exports increased by 24% from the previous year. The surge in demand for tropical fruits from non-tropical countries is one of the contributing factors for this trend. Some of these countries have strict quality requirements – the poor level quality control of fruit is an obstacle in achieving greater export yield. This is because some exporters still use manual sorting processes performed by workers, hence the quality standard varies depending on the individual perception of the workers. Therefore, we need an intelligent system that is capable of automatic sorting according to the standard set. In this research, we propose a system that can classify fruit defects automatically. Faster R-CNN (FRCNN) architecture proposed as a solution to detect the level of defect on the surface of the fruit. There are three types of fruit that we research, its mangoes (sweet fragrant), lime, and pitaya fruit. Each fruit divided into three categories (i) Super, (ii) middle, (iii) and fruit defects. We exploit join detection and video tracking to calculate and determine the quality fruit in real-time. The datasets are taken in the field, then trained using the FRCNN Framework using the Tensorflow platform. We demonstrated that this system can classify fruit with an accuracy level of 88% (mango), 83% (lime), and 99% (pitaya), with an average computation cost of 0.0131 m/s. We can track and calculate fruit sequentially without using additional sensors and check the defect rate on fruit using the video streaming camera more accurately and with greater ease.