Research of Navel Orange Defect and Color Detection Based on Machine Vision

2014 ◽  
Vol 513-517 ◽  
pp. 3442-3445 ◽  
Author(s):  
Guo Liang Yang ◽  
Lu Luo ◽  
Yi Qin Feng ◽  
Hai Sheng Zhao
Keyword(s):  
Machine Vision ◽  
Surface Defect ◽  
Recognition Rate ◽  
Navel Orange ◽  
Test Results ◽  
Color Detection ◽  
Consistency Measure ◽  
Low Efficiency ◽  
Artificial Classification

For the problem of high intensity, low efficiency and poor accuracy in the artificial classification of navel oranges, a detection method is proposed based on machine vision technology. In defect detection, we analyze the color information of navel oranges surface, and obtain surface defect with a proper ratio of R/B and G/B. In the detection of color and luster, we calculate the texture information of the grayscale image, and propose three characteristics such as smoothness R, "consistency" measure U and entropy descriptor e. Finally, a hierarchical model is established based on BP neural network. The test results show that this method can be used for detecting the color and luster of navel orange with a high recognition rate.

scholarly journals Strip Steel Surface Defects Recognition Based on SOCP Optimized Multiple Kernel RVM

2018 ◽  
Vol 2018 ◽  
pp. 1-8
Author(s):  
Hou Jingzhong ◽  
Xia Kewen ◽  
Yang Fan ◽  
Zu Baokai
Keyword(s):  
Steel Surface ◽  
Surface Defect ◽  
Surface Defects ◽  
Recognition Rate ◽  
Strip Surface ◽  
Strip Steel ◽  
Practical Applications ◽  
Multiple Kernel ◽  
Low Efficiency ◽  
Defect Recognition

Strip steel surface defect recognition is a pattern recognition problem with wide applications. Previous works on strip surface defect recognition mainly focus on feature selection and dimension reduction. There are also approaches on real-time systems that mainly exploit the autocorrection within some given picture. However, the instances cannot be used in practical applications because of a bad recognition rate and low efficiency. In this paper, we study the intelligent algorithm of strip steel surface defect recognition, where the goal is to improve the accuracy and save running time. This problem is very important in various applications, especially the process testing of steel manufacturing. We propose an approach called the second-order cone programming (SOCP) optimized multiple kernel relevance vector machine (MKRVM), which can recognize strip surface defects much better than other methods. The method includes the model parameter estimation, training, and optimization of the model based on SOCP and the classification test. We compare our approach with existing methods on strip surface defect recognition. The results demonstrate that our proposed approach can improve the recognition accuracy and reduce the time costs of the strip surface defect.

Automatic Calibration System for Digital-Display Vibrometers Based on Machine Vision

2014 ◽  
Vol 21 (2) ◽  
pp. 317-328 ◽  
Author(s):  
Wen He ◽  
Guanhua Xu ◽  
Zuochao Rong ◽  
Gen Li ◽  
Min Liu
Keyword(s):  
Machine Vision ◽  
Image Recognition ◽  
Recognition Rate ◽  
Digital Camera ◽  
Automatic Calibration ◽  
Vibration Exciter ◽  
Digital Display ◽  
Vibration Level ◽  
Calibration System ◽  
Low Efficiency

Abstract Considering the low efficiency during the process of traditional calibration for digital-display vibrometers, an automatic calibration system for vibrometers based on machine vision is developed. First, an automatic vibration control system is established on the basis of a personal computer, and the output of a vibration exciter on which a digital-display vibrometer to be calibrated is installed, is automatically adjusted to vibrate at a preset vibration level and a preset frequency. Then the display of the vibrometer is captured by a digital camera and identified by means of image recognition. According to the vibration level of the exciter measured by a laser interferometer and the recognized display of the vibrometer, the properties of the vibrometer are calculated and output by the computer. Image recognition algorithms for the display of the vibrometer with a high recognition rate are presented, and the recognition for vibrating digits and alternating digits is especially analyzed in detail. Experimental results on the built-up system show that the prposed image recognition methods are very effective and the system could liberate operators from boring and intense calibration work for digital-display vibrometers

scholarly journals A Study on Railway Surface Defects Detection Based on Machine Vision

Entropy ◽  
2021 ◽  
Vol 23 (11) ◽  
pp. 1437
Author(s):  
Tangbo Bai ◽  
Jialin Gao ◽  
Jianwei Yang ◽  
Dechen Yao
Keyword(s):  
Machine Vision ◽  
Surface Defect ◽  
Surface Defects ◽  
Image Features ◽  
Detection Accuracy ◽  
Test Results ◽  
Defect Area ◽  
Surface Defect Detection ◽  
Speed Up ◽  
Track Surface

The detection of rail surface defects is an important tool to ensure the safe operation of rail transit. Due to the complex diversity of track surface defect features and the small size of the defect area, it is difficult to obtain satisfying detection results by traditional machine vision methods. The existing deep learning-based methods have the problems of large model sizes, excessive parameters, low accuracy and slow speed. Therefore, this paper proposes a new method based on an improved YOLOv4 (You Only Look Once, YOLO) for railway surface defect detection. In this method, MobileNetv3 is used as the backbone network of YOLOv4 to extract image features, and at the same time, deep separable convolution is applied on the PANet layer in YOLOv4, which realizes the lightweight network and real-time detection of the railway surface. The test results show that, compared with YOLOv4, the study can reduce the amount of the parameters by 78.04%, speed up the detection by 10.36 frames per second and decrease the model volume by 78%. Compared with other methods, the proposed method can achieve a higher detection accuracy, making it suitable for the fast and accurate detection of railway surface defects.

PENGEMBANGAN PERANGKAT PEMBELAJARAN MENGGUNAKAN PENDEKATAN CONTEXTUAL TEACHING AND LEARNING (CTL) DENGAN INTEGRASI NILAI-NILAI KARAKTER DI SMAN I TUGUMULYO

2014 ◽  
Vol 13 (3) ◽  
Author(s):  
Sri Wahyu Widyaningsih ◽  
Irfan Yusuf
Keyword(s):  
Teaching And Learning ◽  
Lesson Plan ◽  
Development Stage ◽  
Design Stage ◽  
Learning Tools ◽  
Test Results ◽  
Learning Materials ◽  
Is Research ◽  
Efficacy Trials

<p>The research is motivated not yet using CTL approach. In addition, the study provided yet foster the character value of students. This study aimed to the development of learning materials by using CTL approach with the integration of character value are valid, practical, and effective. The type of this research is research and development by using 4-D models. The stages of this research are define, design, and development. The define stage consists of analyzing of curriculum, students, and concept. Then, the learning materials as lesson plan, handout, student’s worksheet, and evaluation, were designed at design stage. The development stage was doing validity, practicality, and effectiveness test. The data of this research was collected by using validation instruments, questionnaire of students and teacher, observation and test instruments. The result of research with validity of the test results showed that the syllabus, lesson plans, teaching materials, worksheets and assessment sheets (cognitive, affective and psychomotor) developed very valid. The test results showed that the learning practicalities developed very practical. Based on the results of efficacy trials, it was stated that the developed learning very effectively used as learning tools are developed to improve the activity and competence of students in the cognitive, affective and psychomotor and behavioral character. And Those, learning materials by using CTL approach with the integration of character values are classification of very valid, very practical, and effective.</p>

scholarly journals Phylogenetic relationships among accessions in Citrus and related genera based on the insertion polymorphism of the CIRE1 retrotransposon

2020 ◽  
Vol 5 (1) ◽  
pp. 243-251
Author(s):  
Akira Horibata ◽  
Tsuneo Kato
Keyword(s):  
Phylogenetic Relationships ◽  
Sweet Orange ◽  
Point Of View ◽  
Insertion Polymorphism ◽  
Navel Orange ◽  
Citrus Germplasm ◽  
Outgroup Species ◽  
Blood Orange

AbstractA total of 145 accessions of the genus Citrus and related genera, maintained in the Conservation Garden for Citrus Germplasm at the Experimental Farm of Kindai University, Yuasa, Wakayama, Japan, were examined for their phylogenetic relationships. The present classification was conducted using an inter-retrotransposon amplified polymorphism (IRAP) method based on the insertion polymorphism of a retrotransposon, CIRE1, identified in C. sinensis. The objective of this study was to evaluate the applicability of the IRAP method for citrus classification. The constructed dendrogram showed that the 145 accessions and two outgroup species were successfully classified into five major clades. A large number of C. sinensis accessions were divided into three traditional groups, navel orange, sweet orange, and blood orange, almost corresponding to the sub-clades in the dendrogram. Several other accessions belonging to the same species, and also many hybrid cultivars from crossbreeding, were localized into the respective sub-clades or near positions in the dendrogram. Several unclassified accessions could also be located in the dendrogram, suggesting novel relationships with other accessions. It was concluded that the IRAP method based on CIRE1 insertion polymorphism was suitable for the classification of citrus from a molecular point of view.

Research on cargo-loading optimization based on genetic and fuzzy integration

2021 ◽  
Vol 40 (4) ◽  
pp. 8493-8500
Author(s):  
Yanwei Du ◽  
Feng Chen ◽  
Xiaoyi Fan ◽  
Lei Zhang ◽  
Henggang Liang
Keyword(s):  
Genetic Algorithm ◽  
Mathematical Model ◽  
Three Dimensional ◽  
Distribution Center ◽  
Long Time ◽  
Low Efficiency ◽  
Decision Making Model ◽  
The Mathematical Model ◽  
Loading Scheme

With the increase of the number of loaded goods, the number of optional loading schemes will increase exponentially. It is a long time and low efficiency to determine the loading scheme with experience. Genetic algorithm is a search heuristic algorithm used to solve optimization in the field of computer science artificial intelligence. Genetic algorithm can effectively select the optimal loading scheme but unable to utilize weight and volume capacity of cargo and truck. In this paper, we propose hybrid Genetic and fuzzy logic based cargo-loading decision making model that focus on achieving maximum profit with maximum utilization of weight and volume capacity of cargo and truck. In this paper, first of all, the components of the problem of goods stowage in the distribution center are analyzed systematically, which lays the foundation for the reasonable classification of the problem of goods stowage and the establishment of the mathematical model of the problem of goods stowage. Secondly, the paper abstracts and defines the problem of goods loading in distribution center, establishes the mathematical model for the optimization of single car three-dimensional goods loading, and designs the genetic algorithm for solving the model. Finally, Matlab is used to solve the optimization model of cargo loading, and the good performance of the algorithm is verified by an example. From the performance evaluation analysis, proposed the hybrid system achieve better outcomes than the standard SA model, GA method, and TS strategy.

scholarly journals A Machine Vision Approach for Bioreactor Foam Sensing

2021 ◽  
pp. 247263032110088
Author(s):  
Jonas Austerjost ◽  
Robert Söldner ◽  
Christoffer Edlund ◽  
Johan Trygg ◽  
David Pollard ◽  
...  
Keyword(s):  
Machine Learning ◽  
Machine Vision ◽  
State Of The Art ◽  
Low Cost ◽  
High Accuracy ◽  
Consumer Electronics ◽  
Learning System ◽  
Automotive Applications ◽  
Fine Grained

Machine vision is a powerful technology that has become increasingly popular and accurate during the last decade due to rapid advances in the field of machine learning. The majority of machine vision applications are currently found in consumer electronics, automotive applications, and quality control, yet the potential for bioprocessing applications is tremendous. For instance, detecting and controlling foam emergence is important for all upstream bioprocesses, but the lack of robust foam sensing often leads to batch failures from foam-outs or overaddition of antifoam agents. Here, we report a new low-cost, flexible, and reliable foam sensor concept for bioreactor applications. The concept applies convolutional neural networks (CNNs), a state-of-the-art machine learning system for image processing. The implemented method shows high accuracy for both binary foam detection (foam/no foam) and fine-grained classification of foam levels.

Sign in / Sign up

Export Citation Format

Share Document