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 structure of the back propagation neural network (BPNN) classifier.
© Copyright Policy
Related In: Results  -  Collection

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

sensors-15-15326-f011: The structure of the back propagation neural network (BPNN) classifier.

Mentions: Geometric, texture and color features analysis have been widely employed in classification. With proper feature selections, the design of a classifier can be greatly simplified. This study adopts the geometric feature (mean diameter, diameter ratio, distance variance), the color features (mean gray level, variance of gray level) and texture features (contrast, energy and entropy from the gray level co-occurrence matrix (GLCMs) [15]) to classify defects and non-defects using a back propagation neural network [16] (BPNN, as shown in Figure 11). Mathematical formulations of these features are given in Table 1.


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

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

The structure of the back propagation neural network (BPNN) classifier.
© Copyright Policy
Related In: Results  -  Collection

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

sensors-15-15326-f011: The structure of the back propagation neural network (BPNN) classifier.
Mentions: Geometric, texture and color features analysis have been widely employed in classification. With proper feature selections, the design of a classifier can be greatly simplified. This study adopts the geometric feature (mean diameter, diameter ratio, distance variance), the color features (mean gray level, variance of gray level) and texture features (contrast, energy and entropy from the gray level co-occurrence matrix (GLCMs) [15]) to classify defects and non-defects using a back propagation neural network [16] (BPNN, as shown in Figure 11). Mathematical formulations of these features are given in Table 1.

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.