基于图像的珍珠表面细微破损检测技术

Based on Image Pearl Surface Subtle Damage Detection Technology

研究珍珠表面破损检测问题,提高检测的准确性。针对珍珠表面十分光滑,细微的破损时常发生,传统的图像检测或者肉眼检测很难保证珍珠表面细微破损被准确检测出来。造成检测的准确率不高的问题,为了解决这一问题,提出采用计算机视觉图像的珍珠表面细微破损检测方法。通过去除图像中的噪声和一些干扰测量的部分。采用非规则破损表面的测量方法,通过精密测量珍珠图像映射圆表面的像素缺失度,完成珍珠表面细微破损检测。实验证明,上述方案切实可行,可以达到较高的精度,取得了令人满意的效果。

Research pearl surface damage detection, and improve the accuracy of the test. The breakages of pearl surface happen frequently, the traditional image detection or naked eye test was difficult to ensure the accurate pearl detection of subtle surface damages, causing the low testing accuracy. In order to solve this problem, this paper put forward a subtle damage detection method of pearl surfaces based on computer vision. Through removing the noises of the images and some interferences, using the rules of the damaged surface measurement method, and the precise measurement of pearl images of missing pixels of the surface, the surface damage detection was finished. The experimental results prove that the scheme is feasible, and can achieve high precision, and satisfactory results have been obtained.