金属断口图像句法模式识别与分类方法

Recognition and Classification of Metal Fracture Surface Images Based on Syntax Pattern Recognition

针对金属断口图像 ,提出了一种基于句法模式识别理论的分类方法。该方法通过提取断口图像上反映出的形貌特征 ,并将这些特征量化成特征参数 ,分别定义不同类型断口的全图特征参数和典型特征块特征参数 ,可以较好地将不同类型的断口区分开来。分别对等轴塑坑、拉长塑坑、河流花样、腐蚀疲劳、韧性沿晶和韧性疲劳六类断口进行分类识别研究。实验结果表明 。

A new method of recognition and classification based on syntax pattern recognition theory was presented,which towards images of metal fracture surface. By quantitating configuration features of images and defining parameters of the whole images and typical blocks respectively, it is feasible to classify different fracture surfaces accurately.The new method was used to classify six typical fracture surface models: equiaxed dimples, eroded fatigue, stream design, elongated dimples, tenacity fatigue striations and intergranular cracking. Experimental results show that the method presented in the paper has high recognition rate.