X-rays are widely used for the detection of defects in industry, the grayscale value distribute of the image is uneven, due to scattering and other reasons, which brings inconvenience for threshold segmentation of defect detection. In this paper, a grayscale value compensation algorithm is proposed by analyzing the gray value distribution of X-ray images, which makes the gray values distribution of the X-ray image tend to be even and provides a great foundation for separating the defects quickly. The algorithm can reduce the influence of the non-uniformity of gray-scale distribution of X-ray image, it is proved by experiment on defects segmentation inside of BGA which used single threshold, and it makes the image grayscale value distribution tends to be uniform, so that facilitate the subsequent separation of defects as well.
展开▼
