论文部分内容阅读
红外热图具有高噪声、低对比度的特点,设计了图像增强环节解决该问题。对红外热图的频段分布和频段来源进行了分析,确定了有效频段为检测对象红外特性带来的高频段,并确定了增强该频段能量为图像增强环节的目标。针对红外热图频段的分布特点,基于处理目标,使用灰度值调整和巴特沃斯滤波对图像进行了处理,通过图像显示和大律法分割图像两种方法来检验图像增强效果。结果表明:经过设计增强环节,图像的对比度增强,噪声降低,对缺陷的分割更加准确,验证了增强方法的有效性,为更加准确地进行缺陷识别和尺寸定量计算打下了基础。
Infrared heat map with high noise, low contrast features, designed to enhance the image to solve this problem. The frequency band distribution and band source of the infrared heat map are analyzed, the effective frequency band is determined to be the high frequency band of the infrared property of the detection object, and the target of enhancing the energy of this frequency band as the image enhancement link is determined. According to the distribution characteristics of the frequency band of the infrared heat map, the image is processed using the gray value adjustment and Butterworth filtering based on the processing target. Two methods of image display and large-scale image segmentation are used to test the image enhancement effect. The results show that the contrast of the image is enhanced, the noise is reduced and the segmentation of the defect is more accurate after the design enhancement. The validity of the enhancement method is verified, which lays the foundation for the more accurate defect identification and size calculation.