Design of multi-scale receptive field convolutional neural network for surface inspection of hot rolled steels

作者：

Highlights：

• We proposed a new framework based on Inception-V4 integrated with multi-scale respective field.

• AutoEncoders are trained to reduce the dimension of the multi-scale features extracted by the pre-trained model.

• A penalty term in the loss function to reconstruct the input image from the feature maps was added.

• The methods were tested with two different samples from online surface inspection system of steels.

摘要

•We proposed a new framework based on Inception-V4 integrated with multi-scale respective field.•AutoEncoders are trained to reduce the dimension of the multi-scale features extracted by the pre-trained model.•A penalty term in the loss function to reconstruct the input image from the feature maps was added.•The methods were tested with two different samples from online surface inspection system of steels.

论文关键词：AutoEncoder,Convolutional neural networks,Defect identification,Hot rolled steels,Surface inspection

论文评审过程：Received 28 March 2018, Revised 25 April 2019, Accepted 27 June 2019, Available online 3 July 2019, Version of Record 25 July 2019.

论文官网地址：https://doi.org/10.1016/j.imavis.2019.06.008