铝合金的实验室盐雾试验腐蚀行为图像特征提取

Image Feature Extraction of Corrosion of Aluminum Alloy Laboratory Salt Spray Test

目的提取铝合金材料在盐雾箱试验中可以表征腐蚀程度的表面形貌图像特征量。方法首先,对采集于表面化学清洗过的试样原始图像进行图像增强等预处理,突出腐蚀部位;其次,基于数字图像处理的分形和小波分解方法提取出分形维数和小波能量特征值。结果与以质量损失量为基础的腐蚀深度特征值进行相关性对比,基于图像分析的特征提取法的准确度和精度比较高。结论该方法可以应用于对试样的腐蚀程度进行定性和定量分析,判断并预测试样的腐蚀速度。

Objective To extract surface morphology and image characteristics of aluminum alloy in salt spray box test. Methods Firstly, the samples collected from the original image surface were cleaned for image enhancement prepro-cessing and outstanding corrosion; secondly, digital image processing and fractal wavelet decomposition method were used to extract fractal dimension and wavelet energy. Results The accuracy and precision of the feature extraction method based on image analysis were relatively high. Conclusion This method can be applied to qualitative and quantitative analysis of the corrosion degree of specimens as well as judge and prediction of corrosion rate of samples.