To Detect and Identify the Defects of Industrial Pipe

Mayuri Dharma Shinde

Abstract: In many of industries, conventional defects are detected by experienced human inspectors who sketch the defect patterns or types manually and then resolve them. However, such detection methods are more costly, less accurate, time consuming and complicated. To overcome these problems, a method has been developed to detect and identify the defects in industrial pipes, effectively as well as automatically which is based on image processing and embedded system. This method works on video streaming. This proposed method basically works in three steps. Firstly, it converts the RGB images of the pipe into a gray scale image. Secondly, it extracts the pipe as well as fault. Then finally it detects and identifies the defect and it gives the idea of major and minor defect. So, according to this decision will be taken whether to modify that pipe or remove that pipe from process.

Keywords: Defect detection, defect identification, embedded system, image processing, pipe industry

How to Cite?: Mayuri Dharma Shinde, "To Detect and Identify the Defects of Industrial Pipe", Volume 5 Issue 7, July 2016, International Journal of Science and Research (IJSR), Pages: 1561-1564, https://www.ijsr.net/getabstract.php?paperid=ART2016486, DOI: https://dx.doi.org/10.21275/ART2016486