Defects detection in magnetic particle inspection application using image processing techniques

Nondestructive testing (NDT) is widely used in many fields, particularly for critical applications such as welds of pressure vessels, ships, aircraft etc. Magnetic Particle Inspection (MPI) is one of the best-known and commonly used methods of NDT. Its aim is to detect the presence of surface braking discontinuities in the part under inspection. Currently, defects detection in MPI is still based on the subjection judgment by human operators. It is time and manpower consuming works. In addition, human interpretation is very subjective, inconsistent and sometime biased. So we propose a target defect identification approach that is capable of automating extraction the defects in MPI images. By using this approach we can develop the defect detection system in MPI from depending on the human which detects the defects manually upon his experience and skills which varies from one to one to the automated system depending on the computer vision.