Design and experiment of adjustment device based on machine vision for garlic clove direction

Li, Yuhua; Wu, Yanqiang; Li, Tianhua; Niu, Ziru; Hou, Jialin

doi:10.1016/j.compag.2020.105513

Cited by 10 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For future learning factory machine vision deployments, the methods used in this study might serve as a reference. Li et al [36] introduced the major commercial a crop whose planting areas have expanded year over year. The direction in which the cloves are placed during the sowing procedure has a significant impact on garlic's germination time, yield, and appearance.…”

Section: Related Workmentioning

confidence: 99%

Research on Machine Vision System Design Based on Deep Learning Neural Network

Tao

Ju-jiang

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

A machine vision system (MVS) is a technology that can analyze and recognize still or moving pictures using a computer. It is a branch of computer vision that looks like a security camera but can automatically capture, evaluate, and analyze images. The drawbacks are obvious. In the event of a computer vision system failure, firms must have a team of highly trained people with a thorough understanding of the distinctions. Artificial neural networks with numerous layers between the input and output layers are deep neural networks (DNN). Neurons, synapses, weights, biases, and functions are all part of any neural network, regardless of the kind. Many of the challenges in computer vision revolve around using convolutional neural networks (CNN) to categorize images into predefined categories. Convolutional and pooling layers were utilized to decrease the image’s size before feeding the reduced data to fully connected layers. According to the paper, the MVS-CNN algorithm can analyze a picture and determine the value of various characteristics and objects inside it. It is called convolution when combining two functions to create a third function. It is a fusion of two different datasets. A CNN performs convolution on the input data to build a feature map using a filter or kernel. Using a convolutional neural network, an inverted residual block is introduced as the basic block to balance identification accuracy and processing efficiency. The suggested method’s higher inspection performance is achieved with a huge dataset of photos of faulty and defect-free bottles. The result is obtained from the proposed method, the standard deviation ratio is 83.56%, absolute error ratio is 77.26%, trajectory length difference ratio is 82.35%, source pattern radiation amplitude ratio is 86.25%, classification of accuracy ratio is 83.25%, and finally, overall percentage performance ratio is 90.26%.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on Machine Vision System Design Based on Deep Learning Neural Network

Tao

Ju-jiang

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

show abstract

“…The maximum diameter of garlic shown in Figure 4 is 55 mm and the minimum diameter is 50 mm. The garlic image was obtained by the image acquisition module and its posture was identified by the garlic posture recognition system [15][16][17]. The image acquisition module consists of industrial camera and industrial lens.…”

Section: Structure and Working Principlementioning

confidence: 99%

Design and Experiment of a Garlic Orientation and Orderly Conveying Device Based on Machine Vision

Chen

Yao

et al. 2022

Agriculture

View full text Add to dashboard Cite

Aiming at the problem that the existing garlic-root-cutting equipment requires the orientation and orderly conveying of garlic, a garlic orientation and orderly conveying method based on machine vision and mechanical orientation mechanisms was proposed and a garlic orientation and orderly conveying device was designed. To realize garlic posture recognition, garlic and garlic roots were used as detection objects, the YOLOv5s objection detection model was used to establish a garlic feature detection model, and the model was trained. The garlic orientation and orderly conveying device was developed and a garlic posture recognition test and garlic orientation and orderly conveying test were completed. The test results show that the success rate of posture recognition is 98.67% and the average accuracy rate of the garlic deviation angle is 99.11%. When the conveying speed is 95 mm⋅s−1 and the rotating speed is 55 rpm, the orientation success rate is 95.6% and the conveying efficiency reaches 75 garlic per minute, which meets the design requirements. The accuracy of the garlic posture recognition method and the rationality of the garlic orientation and orderly conveying device design are verified, and the automatic orientation and orderly conveying of garlic is realized.

show abstract

“…16 Li et al designed a wheel-spoon-type garlic single-grain seed-taking device, wherein a seed-taking spoon and a seed-taking wheel were used to form a cavity, and the structure was optimized through the EDEM software. 17 However, before planting, the garlic was not screened or graded, and different grades of garlic were harvested with different structural parameters, resulting in slightly higher lost seed rate and numerous rate. Li et al designed a machine vision-based device to adjust the direction of garlic cloves.…”

Section: Introductionmentioning

confidence: 99%

Design and experiment of a type hole wheel garlic seed metering device

Wang

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

Aiming at the problems of low single-seed rate, high rate of missing seeds, high rate of multiple seeds, and low rate of upright seeds in the mechanized sowing of garlic seeds, this paper proposes a structural design scheme of a type hole wheel garlic seed metering device based on the characteristics of garlic species. Based on the agronomic requirements of garlic planting and the characteristics of garlic species, the mechanism of the hole wheel structure to improve the seed filling performance of the seed metering device was clarified, a structural parameter design of the key components of the device was established through theoretical calculations, and a single-factor simulation test was conducted using the Engineering Discrete Element Modelling (EDEM) software. Using the Design-Expert 11 data analysis software, a mathematical regression model of each test factor and test index was established, and the test factors were analyzed. The parameters were optimized, and the following was found to be the optimum parameter combination: seeding wheel speed of 30 rpm, profile hole depth of 18 mm, and adjustment length of the profile hole of 41 mm. The EDEM simulation test results showed a single-seed rate of 91.67% and a missing seed rate of 4.17%. The bench test results showed a single-seed rate of 89.2%, a missing seed rate of 5.0%, and a multiple seed rate of 5.8%. The field test results showed a single-seed rate of 88.44%, a multiple seed rate of 4.11%, a missing seed rate of 7.44%, a breakage rate of 1.11%, and an upright rate of 62.36%. The errors between the bench test/field test and the discrete element simulation test results were 2.7% and 3.5%, respectively, which were consistent with the simulation results, thus meeting the requirements of single-seed sowing using the garlic seed metering device.

show abstract

Design and experiment of adjustment device based on machine vision for garlic clove direction

Cited by 10 publications

References 23 publications

Research on Machine Vision System Design Based on Deep Learning Neural Network

Research on Machine Vision System Design Based on Deep Learning Neural Network

Design and Experiment of a Garlic Orientation and Orderly Conveying Device Based on Machine Vision

Design and experiment of a type hole wheel garlic seed metering device

Contact Info

Product

Resources

About