[Skip to content]

Image Analysis for Complex Data in Non-Destructive Testing
NSIRC student in the lab with equipment - landscape header image

Image Analysis for Complex Data in Non-Destructive Testing

Juvaria-Syeda-square.png
Name:
Juvaria Syeda
University:
Brunel University London
Research Title:
Image Analysis for Complex Data in Non-Destructive Testing
Abstract:

The reliability of structures is an important factor not only in the construction phase but also in the maintenance phase. By developing an effective system to assist in structural reliability assessment, it is potentially possible to reduce the number of inspectors, inspections, time, and maintenance costs and still extend the useful life of a structure. Moreover, we can judge the condition of the structural health, objectively by acquiring and processing the data.

 

The main scope of the project is to develop a system that can analyse the surface defects like pits and cracks efficiently as a non-destructive testing method. The project will require data acquisition by taking 2d images (or using existing ones) from real samples by using easily accessible and portable equipment like a microscopic camera, which contain a mixture of corrosion and cracks. The computer vision and image processing techniques that will be applied in this work are time-efficient and relevant in industrial applications.

 

Image analysis is meaningful when information is obtained from digital images using digital image processing techniques. The algorithm will compose of mainly two parts; first is image processing and second is image classification. The first part will include processing the images and finding the key areas-of-interest, after that image assessment will be performed to meet the industrial standards. The second part will include image classification based on the key features of the objects by using pattern recognition techniques and deep learning neural network. The system will also be applied for 3D images. It is expected that the outcomes of this research will have a significant impact on automatic crack detection using images.

Publications: