Vision-based mixed color detection of plastic particles DOI
Yinyin Yu,

Huaishu Hou,

Zhifan Zhao

и другие.

Review of Scientific Instruments, Год журнала: 2024, Номер 95(9)

Опубликована: Сен. 1, 2024

In the production process of high-end PP-R pipes, mixing different colored raw material particles can result in uneven color final product, affecting its appearance quality. addition, reduce physical properties impacting their durability and safety. To address this issue, we propose a visual, non-destructive inspection solution based on image processing technology. The aims to enhance detection efficiency accuracy by reducing background interference enabling adaptive adjustments various environments. Initially, K-Means segmentation algorithm is employed eliminate complex factors from original image, significantly improving accuracy. Subsequently, Gaussian mixture model utilized automatically extract threshold foreground after removal, facilitating adjustments. Finally, mean value introduced swiftly accurately identify plastic colors using obtained thresholds. Experimental results demonstrate that method quickly effectively support rejection impurity particles. Through approach, achieves an average 99.3%.

Язык: Английский

Employing the Concept of Stacking Ensemble Learning to Generate Deep Dream Images Using Multiple CNN Variants DOI Creative Commons

Lafta R. Al-Khazraji,

Ayad R. Abbas, Abeer Salim Jamil

и другие.

Intelligent Systems with Applications, Год журнала: 2025, Номер unknown, С. 200488 - 200488

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
Vision-based mixed color detection of plastic particles DOI
Yinyin Yu,

Huaishu Hou,

Zhifan Zhao

и другие.

Review of Scientific Instruments, Год журнала: 2024, Номер 95(9)

Опубликована: Сен. 1, 2024

In the production process of high-end PP-R pipes, mixing different colored raw material particles can result in uneven color final product, affecting its appearance quality. addition, reduce physical properties impacting their durability and safety. To address this issue, we propose a visual, non-destructive inspection solution based on image processing technology. The aims to enhance detection efficiency accuracy by reducing background interference enabling adaptive adjustments various environments. Initially, K-Means segmentation algorithm is employed eliminate complex factors from original image, significantly improving accuracy. Subsequently, Gaussian mixture model utilized automatically extract threshold foreground after removal, facilitating adjustments. Finally, mean value introduced swiftly accurately identify plastic colors using obtained thresholds. Experimental results demonstrate that method quickly effectively support rejection impurity particles. Through approach, achieves an average 99.3%.

Язык: Английский

Процитировано

0