A Novel Technique for Wall Crack Detection Using Image Fusion

Abstract

A Non-Destructive Testing (NDT) has been a popular analysis technique used in industrial product evaluation and for troubleshooting in research work without causing damage which can also save both money and time. This paper deals with a novel crack detection technique based on NDT for cracks in walls suppressing the diversity and complexity of wall images. The detection technique begins with wall image acquisition. The acquired image is processed through two crack detectors which follow different edge tracking algorithms such as Hyperbolic Tangent (HBT) filtering and canny edge detection algorithm. The main advantage of the proposed model is that it combines the best features of both Canny’s filtering and HBT filtering techniques. It also fulfills the three necessary vital criteria, i.e. accurate edge detection, localization and minimal response, making the crack detection process more robust and reliable. The fusion of detector responses are performed using Haar Discrete Wavelet Transform (HDWT) and maximumapproximation with mean-detail image fusion algorithm to get more prominent detection of crack edges. The proposed system gives improved edge detection in images with superior edge localization and higher PSNR.