Fast and Non-invasive Surface Crack Detection of Press Panels Using Image Processing

Jung, Hweekwon; Lee, Chang-Won; Park, Gyuhae

doi:10.1016/j.proeng.2017.04.459

Cited by 10 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results had shown the high sensitivity and strong reliability of the method. H. K. Jung et al [2] suggested a digital image processing technique for fast as well as automated crack detection for various pressed panel products. First of all authors extracted the target part from backgrounds of the digital image by taking into account various color as well as brightness attributes.…”

Section: IImentioning

confidence: 99%

“…Along and in amid these processes which have punching, blanking, embossing and other processes the material undergo huge transformations and various deformations occurred in the material as well as in the tool. As a result of it there is various kind of manufacturing defects occurs like cracks, necking and marking lines [1,2]. So it is necessary to detect these defects.…”

Section: Introduction a Developmentmentioning

confidence: 99%

“…Among the various mechanical faults like unbalance in a rotor and other reciprocating unbalances, various types of misalignment and other mechanical run-outs, faults in gears, etc., the crack in the rotor is found to be the one of the most serious and fatigue fault. [2][3][4][5] There are various reasons which can lead to generation of the crack in a shaft. One of the reasons can be the fluctuating load in the shaft.…”

Section: Introduction a Developmentmentioning

confidence: 99%

See 2 more Smart Citations

Crack Detection and Monitoring of Shaft using Artificial Intelligent Way

Ramzan¹

2021

IJRASET

View full text Add to dashboard Cite

In the process of core manufacturing the quality control and its management detection of cracks is one of the fundamental steps of panel products. Old methods used for detection of cracks are quite costly and also takes enough time and maximum of these techniques could only be executed by experts only. So there is need of some fast, accurate and reliable method which should also be automatic so that crack can be detected by without the human intervention. In this thesis a smart way of detection of cracks is proposed which is relied on image processing. Here images are captured by the camera and then are examined for whether cracks are present in the mechanical panels and not. Crack detection and as well as its exact position cannot be easily examined by human eye but the camera system can easily recognize the hole or some crack present in the image captured of mechanical device. Crack can be holes or it can be a straight or curved line present in the part. So the proposed system should be able to detect all the irregularities present in the mechanical part.To check and show the capability of the proposed system different mechanical panels and other mechanical parts will be examined and after performing different tests the worthiness of the proposed system will be shown. The system will be evaluated for fast execution time and accuracy of finding the cracks in the mechanical parts. I.

show abstract

Section: IImentioning

confidence: 99%

Section: Introduction a Developmentmentioning

confidence: 99%

Section: Introduction a Developmentmentioning

confidence: 99%

See 1 more Smart Citation

Crack Detection and Monitoring of Shaft using Artificial Intelligent Way

Ramzan¹

2021

IJRASET

View full text Add to dashboard Cite

show abstract

“…On the other hand, non-invasive techniques are based mostly on surface inspection methods [ 7 ]. For example, the classification of the colored material can be achieved straightforwardly with machine vision, which is inefficient for in-depth analysis [ 8 ]. Also, inspections based on thermal, microwave, ultrasonic, acoustic emission, and magnetic techniques are not adequate for IP classification [ 1 , 9 ].…”

Section: Introductionmentioning

confidence: 99%

Automated Inorganic Pigment Classification in Plastic Material Using Terahertz Spectroscopy

Sarjaš

Pongrac

Gleich

2021

Sensors

View full text Add to dashboard Cite

This paper presents an automatic classification of plastic material’s inorganic pigment using terahertz spectroscopy and convolutional neural networks (CNN). The plastic materials were placed between the THz transmitter and receiver, and the acquired THz signals were classified using a supervised learning approach. A THz frequency band between 0.1–1.2 THz produced a one-dimensional (1D) vector that is almost impossible to classify directly using supervised learning. This paper proposes a novel pre-processing of 1D THz data that transforms 1D data into 2D data, which are processed efficiently using a convolutional neural network. The proposed pre-processing algorithm consists of four steps: peak detection, envelope extraction, and a down-sampling procedure. The last main step introduces the windowing with spectrum dilatation that reorders 1D data into 2D data that can be considered as an image. The spectrum dilation techniques ensure the classifier’s robustness by suppressing measurement bias, reducing the complexity of the THz dataset with negligible loss of accuracy, and speeding up the network classification. The experimental results showed that the proposed approach achieved high accuracy using a CNN classifier, and outperforms 1D classification of THz data using support vector machine, naive Bayes, and other popular classification algorithms.

show abstract

“…The outcome of the study revealed that that the segmentation depending on the RGB color space provided the best results compared to other color spaces for the considered set of images. In [32] an image processing technique for rapid and automated crack detection was proposed as based on RGB color space. The comparative study among different color spaces in [33] does not show significant differences.…”

Section: Introductionmentioning

confidence: 99%

A robotics and computer-aided procedure for defect evaluation in bridge inspection

Potenza

Rinaldi

Ottaviano

et al. 2020

J Civil Struct Health Monit

View full text Add to dashboard Cite

Image processing may enhance condition assessment of bridge defects. In this perspective, we propose a robotics and computer-aided procedure, which enables quantitative evaluation of defect extension with a specific storage organization, and performed by Unmanned Aerial Vehicle (UAV). The methodology for defect evaluation uses color-based image processing. Data contained in digital images are taken on pre-classified structural elements. A campaign of UAV-based inspections has been performed to evidence the potentiality of the proposed procedure. Recurrent defects, occurring in infrastructure belonging to the Italian National railway system, allow evidencing the main features of the developed image-processing algorithm. The proposed process of damage detection and quantification is discussed with respect to both the level of automation that can be reached in each phase, and the robustness of the used image processing adopted procedure.

show abstract

Fast and Non-invasive Surface Crack Detection of Press Panels Using Image Processing

Cited by 10 publications

References 9 publications

Crack Detection and Monitoring of Shaft using Artificial Intelligent Way

Crack Detection and Monitoring of Shaft using Artificial Intelligent Way

Automated Inorganic Pigment Classification in Plastic Material Using Terahertz Spectroscopy

A robotics and computer-aided procedure for defect evaluation in bridge inspection

Contact Info

Product

Resources

About