Contrast Enhancement of Industrial Radiography Images by Gabor Filtering with Automatic Noise Thresholding

Abstract

The defect detection procedure of a radiographic image is a very important task. This is because of its importance regarding the safety of different industrial equipment. The defect detection procedures must reveal the defect region with the edges preserved. The radiography images are degraded by different noises caused by photon x-ray scattering, data acquisition and system errors. Due to the noise, radiography experts may encounter certain difficulties when extracting the defect region in the noisy images. This article presents a novel implementation of the Gabor filtering algorithm to improve contrast and denoise radiography images and detect the defects. Gabor filtering with automatic detection of noise level is a powerful contrast enhancement algorithm, but it tends to remove specific details from the processed images passing them off as noise. The performance of the proposed approach, the region defect, is revealed in radiographic images of different welded specimens. Results show major improvement not only in the noise attenuation, but also in the preservation of small details and the defect region.