基于图像形态学的焊缝区域提取与对比度提升技术

Research on Weld Region Extraction and Contrast Enhancement Based on Image Morphology

铝板焊接后可使用X射线进行焊缝内部缺陷检测,由于X射线成像存在噪声多、对比度低、焊缝区域边缘模糊、焊缝区域与背景区域灰度分布较为相似等问题,使用传统边缘检测方法效果欠佳。提出了一种自动提取焊缝区域并提高其对比度的方法,通过去噪处理、边缘检测、形态学操作等步骤,最终确定焊缝区域位置,并对焊缝区域内像素值进行线性变换,提高了焊缝区域的对比度。实验结果表明,该方法针对大批量的铝板X射线图片,都能够自动提高焊缝区域的对比度,具有良好的鲁棒性和准确性。

After aluminum plate is welded,X-ray can be used to detect the internal defects of weld.Due to the problems of noise,low contrast,fuzzy edge of weld area and uneven brightness distribution in X-ray image,the effect of traditional edge detection method is not good.Therefore,this paper proposes a method to automatically extract weld area and improve its contrast.Through the steps of denoising,edge detection and morphology operation,the weld area position is finally determined,and the pixel value in the weld area is linearly transformed to improve the contrast of the weld area.The experimental results show that this method can automatically improve the contrast of weld area for a large number of aluminum plate X-ray images,and has good robustness and accuracy.