Surface texture defect recognition method of machined parts based on machine vision

2020 ◽  
Author(s):  
Xiong Ruyi
Keyword(s):  
Machine Vision ◽  
Surface Texture ◽  
Recognition Method ◽  
Machined Parts ◽  
Defect Recognition

A New Kind of Beer Bottle Mouth Defect Recognition Method Based on Vision

2014 ◽  
Vol 490-491 ◽  
pp. 1465-1469
Author(s):  
Yu Chan Xie
Keyword(s):  
Hough Transform ◽  
Production Line ◽  
Recognition Method ◽  
Circular Area ◽  
Circular Symmetry ◽  
Hough Space ◽  
Pixel Location ◽  
Image Pixels ◽  
Defect Recognition ◽  
Implementation Steps

According to the beer bottle mouth defect recognition problem on modern production line, a new recognition method based on the combination the Hough Transform and the Midpoint circle algorithm was put forward. Firstly, extract edge pixels on beer bottle mouth mage and transform them into Hough space, which was to draw circles at each pixel location with bottle mouth radius. According to the circular symmetry, only 1/8 circle pixels were needed to draw circles, which were worked out by the Midpoint Circle Algorithm. The circles there overlapped each other to vote. Secondly, took the position with the highest votes as the center of bottle mouth and determined the bottle circular area. Divided the area into regions. Finally, count out the number of image pixels in each region and recognition beer bottle defect. In this paper detailed implementation steps with detection results were given. Experiments and its analysis shows: the algorithm can recognition beer bottle mouth defect correctly and quickly.

Assessment of Tool Wear Based on Surface Texture Parameters

2009 ◽  
Author(s):  
Yi Liao ◽  
David A. Stephenson ◽  
Jun Ni
Keyword(s):  
Tool Wear ◽  
Surface Texture ◽  
Surface Measurement ◽  
Warning Sign ◽  
Surface Waviness ◽  
High Definition ◽  
Statistical Process ◽  
Texture Parameters ◽  
Machined Parts ◽  
On Line

This research presents a new way to determine the condition of a cutting tool based on high definition surface texture parameters. Recently, a laser holographic interferometer has been developed to rapidly measure the whole workpiece surface (e.g. 300mm×300mm) and generate a 3D surface height map with micron level accuracy. This technique enables on-line surface measurement for machined parts. By measuring the surface texture of workpieces, the interaction between the tool’s cutting edges and the surface can be extracted as a spatial signature. It can then be used as a warning sign for tool change because the workpiece produced by a heavily worn tool exhibits more irregularities than those produced by a normal tool. Three surface texture parameters: image intensity histogram, surface peak-to-valley height and surface waviness are employed to detect the onset of severe tool wear. Furthermore, surface waviness can also be used to classify the different phases of tool wear. In this work, nine surface samples under different tool wear phases are created and analyzed using surface texture parameters combined with Statistical Process Control (SPC) charts to assess tool conditions. The results verify that these surface texture parameters can be used for on-line tool wear monitoring.

scholarly journals Design and Image Research of Tennis Line Examination Based on Machine Vision Analysis

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Liu Yan ◽  
Sun Xin
Keyword(s):  
Machine Vision ◽  
Camera Calibration ◽  
Recognition Accuracy ◽  
Calibration Method ◽  
Recognition Method ◽  
Systematic Analysis ◽  
High Recognition Accuracy ◽  
Intelligent Recognition ◽  
Region Growth ◽  
Design Experiments

In view of the intelligent demand of tennis line examination, this paper performs a systematic analysis on the intelligent recognition of tennis line examination. Then, a tennis line recognition method based on machine vision is proposed. In this paper, the color region of the image recognition region is divided based on the region growth, and the rough estimation of the court boundary is realized. In order to achieve the effect of camera calibration, a fast camera calibration method which can be used for a variety of court types is proposed. On the basis of camera calibration, a tennis line examination and segmentation system based on machine vision analysis is constructed, and the experimental results are verified by design experiments. The results show that the machine vision analysis-based intelligent segmentation system of tennis line examination has high recognition accuracy and can meet the actual needs of tennis line examination.

scholarly journals Recognition Method of Tunnel Lining Defects Based on Deep Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Anfu Zhu ◽  
Shuaihao Chen ◽  
Fangfang Lu ◽  
Congxiao Ma ◽  
Fengrui Zhang
Keyword(s):  
Deep Learning ◽  
Tunnel Lining ◽  
Training Algorithms ◽  
Test Results ◽  
Recognition Method ◽  
Training Time ◽  
Recognition Model ◽  
New Ideas ◽  
Defect Recognition ◽  
Ground Penetrating

The defect identification of tunnel lining is a task with a lot of tasks and time-consuming work, and currently, it mainly relies on manual operation. This paper takes the ground-penetrating radar image of the internal defects of the lining as the research object, and chooses the popular VGG16, ResNet34 convolutional neural network (CNN) to build the automatic recognition model for comparative study, and proposes an improved ResNet34 defect-recognition model. In this paper, SGD and Adam training algorithms are used to update network parameters, and the PyTorch depth framework is used to train the network. The test results show that the ResNet34 network has faster convergence speed, higher accuracy rate, and shorter training time than the VGG16 network. The ResNet34 network using the Adam algorithm can achieve 99.08% accuracy. The improved ResNet34 network can achieve an accuracy of 99.25%, and at the same, reduce the parameter amount by 4.22% compared with the ResNet34 network, which can better identify defects in the lining. The research in this paper shows that the deep learning method can provide new ideas for the identification of tunnel lining defects.

Sign in / Sign up

Export Citation Format

Share Document