Limits...
A Novel Machine Vision System for the Inspection of Micro-Spray Nozzle.

Huang KY, Ye YT - Sensors (Basel) (2015)

Bottom Line: These texture features (contrast, entropy, energy), color features (mean and variance of gray level) and geometric features (distance variance, mean diameter and diameter ratio) were used in the classification procedures.A back-propagation neural network classifier was employed to detect the defects of micro-spray nozzles.The methodology presented herein effectively works for detecting micro-spray nozzle defects to an accuracy of 90.71%.

View Article: PubMed Central - PubMed

Affiliation: Department of Bio-Industrial Mechatronics Engineering, National Chung Hsing University, Tai-Chung 402, Taiwan. kuoyi@nchu.edu.tw.

ABSTRACT
In this study, we present an application of neural network and image processing techniques for detecting the defects of an internal micro-spray nozzle. The defect regions were segmented by Canny edge detection, a randomized algorithm for detecting circles and a circle inspection (CI) algorithm. The gray level co-occurrence matrix (GLCM) was further used to evaluate the texture features of the segmented region. These texture features (contrast, entropy, energy), color features (mean and variance of gray level) and geometric features (distance variance, mean diameter and diameter ratio) were used in the classification procedures. A back-propagation neural network classifier was employed to detect the defects of micro-spray nozzles. The methodology presented herein effectively works for detecting micro-spray nozzle defects to an accuracy of 90.71%.

No MeSH data available.


The scanning direction of the circle inspection for the ROI.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541833&req=5

sensors-15-15326-f008: The scanning direction of the circle inspection for the ROI.

Mentions: Segmenting defect regions is an important procedure before possible defects (including the deckle edge, pellet and stripe metal fillings) are detected and classified. A prior experiment proceeded as follows. Firstly, an inspection circle is used to find gray levels with scanning resolution in a pixel, as shown in Figure 8. There are different distribution forms of gray levels in different circles, as illustrated in Figure 9. However, the difference between defects and non-defects is difficult to distinguish using the thresholding method [13]. Therefore, a novel method, the circle inspection algorithm (CI algorithm), is proposed for defect region segmentation of micro-spray nozzles in this study.


A Novel Machine Vision System for the Inspection of Micro-Spray Nozzle.

Huang KY, Ye YT - Sensors (Basel) (2015)

The scanning direction of the circle inspection for the ROI.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541833&req=5

sensors-15-15326-f008: The scanning direction of the circle inspection for the ROI.
Mentions: Segmenting defect regions is an important procedure before possible defects (including the deckle edge, pellet and stripe metal fillings) are detected and classified. A prior experiment proceeded as follows. Firstly, an inspection circle is used to find gray levels with scanning resolution in a pixel, as shown in Figure 8. There are different distribution forms of gray levels in different circles, as illustrated in Figure 9. However, the difference between defects and non-defects is difficult to distinguish using the thresholding method [13]. Therefore, a novel method, the circle inspection algorithm (CI algorithm), is proposed for defect region segmentation of micro-spray nozzles in this study.

Bottom Line: These texture features (contrast, entropy, energy), color features (mean and variance of gray level) and geometric features (distance variance, mean diameter and diameter ratio) were used in the classification procedures.A back-propagation neural network classifier was employed to detect the defects of micro-spray nozzles.The methodology presented herein effectively works for detecting micro-spray nozzle defects to an accuracy of 90.71%.

View Article: PubMed Central - PubMed

Affiliation: Department of Bio-Industrial Mechatronics Engineering, National Chung Hsing University, Tai-Chung 402, Taiwan. kuoyi@nchu.edu.tw.

ABSTRACT
In this study, we present an application of neural network and image processing techniques for detecting the defects of an internal micro-spray nozzle. The defect regions were segmented by Canny edge detection, a randomized algorithm for detecting circles and a circle inspection (CI) algorithm. The gray level co-occurrence matrix (GLCM) was further used to evaluate the texture features of the segmented region. These texture features (contrast, entropy, energy), color features (mean and variance of gray level) and geometric features (distance variance, mean diameter and diameter ratio) were used in the classification procedures. A back-propagation neural network classifier was employed to detect the defects of micro-spray nozzles. The methodology presented herein effectively works for detecting micro-spray nozzle defects to an accuracy of 90.71%.

No MeSH data available.