论文阅读笔记《Automatic Fabric Defect Detection with a Multi-Scale Convolutional Denoising Autoencoder Net》
核心思想 本文提出一种多尺度卷积去噪自动编码器网络（MSCDAE）实现了对布匹纺织物缺陷的无监督检测，算法的思路其实并不复杂，作者使用正样本对卷积自动编码器（CAE）进行训练，使得其具备提取织物特征并重构织物图像的能力。当带有缺陷的样本输入到网络中时，由于缺陷处的特征与正常织物的特征不同，因此CAE并不能够重构缺陷处的图像，重构后的图像缺陷处将将重构后的图像与原始图像做差，缺陷处的差异会明显大
相关文章
- 1. 论文阅读笔记《Unsupervised fabric defect detection based on a deep convolutional GAN》
- 2. 论文阅读笔记《Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networ》
- 3. 论文阅读笔记《A High-Efficiency Fully Convolutional Networks for Pixel-Wise Surface Defect Detection》
- 4. 论文阅读笔记《A Surface Defect Detection Method Based on Positive Samples》
- 5. 论文阅读笔记：GAS---spam review detection with graph convolutional networks
- 6. [论文阅读]Object Detection With Deep Learning: A Review
- 7. 论文阅读笔记《Convolutional Neural Networks for Steel Surface Defect Detection from Photometric Stereo》
- 8. 【论文阅读】 Single-cell RNA-seq denoising using a deep count autoencoder.
- 9. 论文阅读笔记《Segmentation-based deep-learning approach for surface-defect detection》
- 10. 论文阅读笔记《Deep Active Learning for Civil Infrastructure Defect Detection and Classification》
- 更多相关文章...
- • RSS 阅读器 - RSS 教程
- • PHP 实例 - AJAX RSS 阅读器 - PHP教程
- • Tomcat学习笔记（史上最全tomcat学习笔记）
- • JDK13 GA发布：5大特性解读
相关标签/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 论文阅读笔记《Unsupervised fabric defect detection based on a deep convolutional GAN》
- 2. 论文阅读笔记《Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networ》
- 3. 论文阅读笔记《A High-Efficiency Fully Convolutional Networks for Pixel-Wise Surface Defect Detection》
- 4. 论文阅读笔记《A Surface Defect Detection Method Based on Positive Samples》
- 5. 论文阅读笔记：GAS---spam review detection with graph convolutional networks
- 6. [论文阅读]Object Detection With Deep Learning: A Review
- 7. 论文阅读笔记《Convolutional Neural Networks for Steel Surface Defect Detection from Photometric Stereo》
- 8. 【论文阅读】 Single-cell RNA-seq denoising using a deep count autoencoder.
- 9. 论文阅读笔记《Segmentation-based deep-learning approach for surface-defect detection》
- 10. 论文阅读笔记《Deep Active Learning for Civil Infrastructure Defect Detection and Classification》