著作(論文等)

基本情報

氏名 永田 寅臣
氏名(カナ) ナガタ フサオミ
氏名(英語) NAGATA Fusaomi

論文名

Detection of Minute Defects Using Transfer Learning-Based CNN Models

著者名

Kento Nakashima (M2), Fusaomi Nagata, Hiroaki Ochi, Akimasa Otsuka, Takeshi Ikeda, Keigo Watanabe, Maki K. Habib

掲載誌名等

, Artificial Life and Robotics, Springer

掲載年月

2021/01/28

Vol. 26,

No. 1,

開始頁

pp. 35

 

終了頁

41, 2021.

出版者(日本語)

 

出版者(英語)

 

発表形態

誌上、オンライン

概要

In this paper, a design and training tool for convolutional neural networks (CNNs) is introduced, which facilitates to construct transfer learning-based CNNs based on a series type network such as AlexNet, VGG16 and VGG19 or a directed acyclic graph (DAG) type network such as GoogleNet, Inception-v3 and IncResNetV2. Minute defect detection systems are developed for resin molded articles by transfer learning of AlexNet. AlexNet has the shallowest layer structure and the smallest number of weights within the six powerful networks, so that it is selected as the first CNN for evaluation. In the transfer learning process, after the last fully connected layers are replaced according to the number of categories needed for new tasks, an additional fine training is conducted using training images including small typical defects. In experiments, transfer learning-based AlexNet_6 and AlexNet_2 are obtained to deal with six and binary classification tasks, respectively. Then, our originally designed 15 layers CNNs named sssNet_6 and sssNet_2 are also prepared and trained for comparison. Finally, AlexNet_6 and sssNet_6, AlexNet_2 and sssNet_2 are quantitatively compared and evaluated through classification experiments, respectively.