摘要
为准确分割金刚石颗粒图像,基于空洞卷积网络构建图像语义分割模型。以自建的小型金刚石颗粒图像数据集为基础,对所建模型的批处理规模、卷积层过滤器数量和膨胀系数等超参数进行调优。对比调优后的空洞卷积网络与传统的全局阈值法、自适应阈值法对金刚石颗粒图像的分割能力。研究结果表明:批处理规模、卷积层过滤器数量和膨胀系数等参数对网络的分割能力有重要影响;空洞卷积网络在0.965的精确度下可达到0.966的召回率,性能明显高于传统方法的,尤其是较好地解决了金刚石颗粒上亮斑的归类问题。
For precise segmentation of diamond images,a semantic segmentation model was constructed based on dilated convolutional neural network.A small-scale data set of diamond images was established.The hyper parameters of the model,including batch size,number of filters and dilation coefficient,were optimized.The segmentation results obtained with dilated convolutional network were compared with those acquired by thresholding method and adaptive thresholding method.The results show that batch size,number of filters and dilation coefficient have important effects on the segmentation ability of the constructed model.It is also found that dilated convolutional network can achieve a recall value of 0.966 at the level of 0.965 precision,which is much higher than those of traditional methods.Especially,it is able to classify effectively the bright spots in diamond images.
作者
潘秉锁
潘文超
刘子玉
PAN Bingsuo;PAN Wenchao;LIU Ziyu(Faculty of Engineering,China University of Geosciences(Wuhan),Wuhan 430074,China)
出处
《金刚石与磨料磨具工程》
CAS
北大核心
2019年第6期20-24,共5页
Diamond & Abrasives Engineering
基金
国家自然科学基金面上项目(41872187)
关键词
金刚石图像
空洞卷积网络
图像分割
深度学习
diamond image
dilated convolutional network
image segmentation
deep learning
