Radiographic testing is extensively used in non-destructive evaluation. However, the contrast of object defects in X-Ray images is generally weak compared to the image dynamic range, which limits defects visibility and makes the image inspection time consuming and tedious. To circumvent this issue, our work builds on a bilateral filter to extract and amplify the low-contrast local variations of the image, supposed to represent the object defects. A critical step of this approach lies in the selection of the bilateral filter range parameter, which sets a contrast upper-bound to the signals that are filtered out, to be scaled to a constant fraction of the rendering range. As an original contribution, we propose to set this parameter to maximize the tone-mapped quality index (TMQI) of the reconstructed image. Since the TMQI combines a multi-scale structural similarity criterion with a measure of image naturalness, its maximization both discourages the selection of a (too large) range parameter that penalizes structural similarity, and prevents the lack of naturalness associated to an excessive noise amplification caused by a too small range parameter. Image subjective quality assessment experiments not only demonstrate that our approach largely enhances defect visibility on real use cases, but also reveal that our recommended parameter is preferred by users to any reasonable alternative in a large majority of cases ( 90%). An objective evaluation based on the Image Discrete Entropy shows that the enhanced images compare favorably to the ones obtained with previous works devoted to High Dynamic Range image visualization
|