人工神经网络在金相图像分割中的应用研究

Study on artificial neuronal networks applied on microstructure segmentation from metallographic images

利用多层感知器神经网络和自组织映射神经网络对球墨铸铁、可锻铸铁和灰铸铁的金相图像进行了分割提取。通过对比以上两种方法分割后的图像质量和定量分析样本图像中的石墨结构、珍珠岩/铁氧体结构所占的百分含量后发现,多层感知器网络分割提取的结果与样本实际的结果更加接近,而自组织映射神经网络分割提取的结果则不够理想。据此,可以推断多层感知器网络是实现金属图像分割自动化提取和精确性分析的有效工具。

This paper presents a comparative analysis between muhilayer perceptron and self-organizing map topologies applied to segment microstructures from metallographic images. Thirty samples of cast irons were considered for experimental comparison and the results obtained by muhilayer perceptron neural network were very similar to the ones resultant by visual human inspection. However, the results obtained by self-organizing map neural network were not so good. Indeed, muhilayer perceptron neural network always segmented ef？ciently the microstructures of samples in analysis, what did not occur when self-organizing map neural network was considered. From the experiments done, we can conclude that multilayer perceptron network is an adequate tool to be used in Material Science fields to accomplish microstructural analysis from metallographic images in a fully automatic and accurate manner.