期刊
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
卷 68, 期 12, 页码 4787-4797出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIM.2019.2899478
关键词
Inspection; Surface treatment; Training; Metals; Task analysis; Instruments; Visualization; Adaptive multiscale image collection (AMIC); convolutional neural networks (CNNs); image classification; surface inspection
资金
- National Natural Science Foundation of China [91748131, 61379097, 61771471, U1613213]
- China Postdoctoral Science Foundation [2018M641523]
- National Key Research and Development Plan of China [2017YFB1300202]
- Youth Innovation Promotion Association Chinese Academy of Sciences [2015112]
Surface flaw inspection is of great importance for quality control in the field of manufacture. In this paper, a novel surface flaw inspection algorithm is proposed based on adaptive multiscale image collection (AMIC) using convolutional neural networks. First, the inspection networks are pretrained with ImageNet data set. Second, the AMIC is established, which consists of adaptive multiscale image extraction and with-contour local extraction from training images. Through the AMIC, the training data set is greatly augmented, and labels of images can be accomplished automatically without artificial consumption. Then, transfer learning is performed with the AMIC established from training data set. Finally, an automatic surface flaw inspection instrument for large-volume metal components embedded with the proposed inspection algorithm is designed. Experiments with small metal components are performed to analyze the influence of parameters, and comparative experiments are carried out. The inspecting precisions for indentation, scratch, and pitted surface of the proposed method are 97.3, 99.5, and 100, respectively. The experimental results demonstrate the effectiveness of the proposed method in the detection of various surface flaws.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据