Image recognition of interference fringes in polishing by convolutional neural network with data augmentation by deep convolutional generative adversarial network

Chen Yi-Huei; Lin Wei-Ting; Liu Chun-Wei

首页> 外文期刊>Optical Engineering >Image recognition of interference fringes in polishing by convolutional neural network with data augmentation by deep convolutional generative adversarial network

【24h】

Image recognition of interference fringes in polishing by convolutional neural network with data augmentation by deep convolutional generative adversarial network

机译：基于深度卷积生成对抗网络数据增强的卷积神经网络抛光干涉条纹图像识别

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

With the growing need for high specification requirements for the latest manufacturing processes and optical designs of glass lenses, the technical requirements for lens polishing have increased. The manufacturing parameters must be adjusted in a timely manner to meet the required specifications. We use a Fizeau interferometer to classify and analyze interference fringes measured in the actual polishing process of glass lenses. Given the low incidence of interference fringes in practice, the training dataset contained a disproportionate ratio of data for each data type. To reduce the manufacturing cost and data collection time, this study focused on three common types of interference fringes in the manufacturing processes and integrated a deep convolutional generative adversarial network with convolutional neural networks (CNNs) for fringe type classification. The deep convolutional generative adversarial network was used to establish a data augmentation generator, and Jensen-Shannon divergence was employed to identify the epoch number that yielded distributions of interference fringe numbers closest to the real distributions; this approach could achieve the diversity of interference fringes in the generated images. Finally, the generated data were used to train the CNN models, and the accuracy of image recognition reached above 86%. (C) 2022 Society of Photo-Optical Instrumentation Engineers (SPIE)

机译：随着对玻璃镜片最新制造工艺和光学设计的高规格要求的需求不断增长，对镜片抛光的技术要求也越来越高。必须及时调整制造参数，以满足所需的规格。我们使用Fizeau干涉仪对玻璃镜片实际抛光过程中测量的干涉条纹进行分类和分析。鉴于干涉条纹在实践中的发生率较低，训练数据集包含每种数据类型的数据比例不成比例。为了降低制造成本和数据收集时间，本研究重点关注制造过程中常见的三种干涉条纹类型，并将深度卷积生成对抗网络与卷积神经网络（CNNs）相结合进行条纹类型分类。利用深度卷积生成对抗网络建立数据增强生成器，采用Jensen-Shannon散分辨出最接近真实分布的干涉条纹数分布的纪元数;该方法可以实现生成图像中干涉条纹的多样性。最后，利用生成的数据对CNN模型进行训练，图像识别准确率达到86%以上。（C） 2022 年光电仪器工程师协会（SPIE）

著录项

来源
《Optical Engineering》 |2022年第4期|045102-1-045102-13|共13页
作者
Chen Yi-Huei; Lin Wei-Ting; Liu Chun-Wei;
展开▼
作者单位

Natl Tsing Hua Univ;

展开▼
收录信息美国《科学引文索引》(SCI);美国《工程索引》(EI);
原文格式 PDF
正文语种英语
中图分类光学仪器;
关键词
interference fringes; Zernike polynomials; deep convolutional generative adversarial network; convolutional neural networks; CNN;

机译：干涉条纹;泽尼克多项式;深度卷积生成对抗网络;卷积神经网络;美国有线电视新闻网（CNN）;

相似文献

外文文献
中文文献

1. Embedding Image Through Generated Intermediate Medium Using Deep Convolutional Generative Adversarial Network [J] . Chuanlong Li, Yumeng Jiang, Marta Cheslyar 计算机、材料和连续体(英文) . 2018,第008期
2. Image Augmentation-Based Food Recognition with Convolutional Neural Networks [J] . Lili Pan, Jiaohua Qin, Hao Chen, 计算机、材料和连续体(英文) . 2019,第004期
3. Reports Outline Networks Study Findings from Nanchang University (Emotional design of bamboo chair based on deep convolution neural network and deep convolution generative adversarial network) [J] . Network Daily News . 2022,第4期

机译：Reports Outline Networks Study Findings from Nanchang University (Emotional design of bamboo chair based on deep convolution neural network and deep convolution generative adversarial network)
4. Hiroshima University Reports Findings in Networks (Image synthesis of effective atomic number images using a deep convolutional neural network-based generative adversarial network) [J] . Network Daily News . 2022,第30期

机译：Hiroshima University Reports Findings in Networks (Image synthesis of effective atomic number images using a deep convolutional neural network-based generative adversarial network)
5. Multiplanar analysis for pulmonary nodule classification in CT images using deep convolutional neural network and generative adversarial networks [J] . Yuya Onishi, Atsushi Teramoto, Masakazu TsujimotoTetsuya TsukamotoKuniaki SaitoHiroshi ToyamaKazuyoshi ImaizumiHiroshi Fujita International journal of computer assisted radiology and surgery. . 2020,第1期

机译：Multiplanar analysis for pulmonary nodule classification in CT images using deep convolutional neural network and generative adversarial networks
6. Flower Species Recognition Based on the Convolutional Neural Network [C] . Xu Xianchong, Gao Yuanyuan International Conference on Image, Vision and Computing . 2021

机译：Flower Species Recognition Based on the Convolutional Neural Network
7. InvariantObjectRecognitionUsingCircular Pairwise Convolutional Networks [O] . Choon Hui Teo, Yong Haur Tay, Universiti Tunku, 2010

机译：InvariantObjectRecognitionUsingCircular pairwise Convolutional Networks

Image recognition of interference fringes in polishing by convolutional neural network with data augmentation by deep convolutional generative adversarial network

摘要

著录项

相似文献

相关主题

期刊订阅