論文閱讀筆記《Automatic Fabric Defect Detection with a Multi-Scale Convolutional Denoising Autoencoder Net》
核心思想 本文提出一種多尺度卷積去噪自動編碼器網絡（MSCDAE）實現了對布匹紡織物缺陷的無監督檢測，算法的思路其實並不複雜，作者使用正樣本對卷積自動編碼器（CAE）進行訓練，使得其具備提取織物特徵並重構織物圖像的能力。當帶有缺陷的樣本輸入到網絡中時，由於缺陷處的特徵與正常織物的特徵不同，因此CAE並不能夠重構缺陷處的圖像，重構後的圖像缺陷處將將重構後的圖像與原始圖像做差，缺陷處的差異會明顯大
相關文章
- 1. 論文閱讀筆記《Unsupervised fabric defect detection based on a deep convolutional GAN》
- 2. 論文閱讀筆記《Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networ》
- 3. 論文閱讀筆記《A High-Efficiency Fully Convolutional Networks for Pixel-Wise Surface Defect Detection》
- 4. 論文閱讀筆記《A Surface Defect Detection Method Based on Positive Samples》
- 5. 論文閱讀筆記：GAS---spam review detection with graph convolutional networks
- 6. [論文閱讀]Object Detection With Deep Learning: A Review
- 7. 論文閱讀筆記《Convolutional Neural Networks for Steel Surface Defect Detection from Photometric Stereo》
- 8. 【論文閱讀】 Single-cell RNA-seq denoising using a deep count autoencoder.
- 9. 論文閱讀筆記《Segmentation-based deep-learning approach for surface-defect detection》
- 10. 論文閱讀筆記《Deep Active Learning for Civil Infrastructure Defect Detection and Classification》
- 更多相關文章...
- • RSS 閱讀器 - RSS 教程
- • PHP 實例 - AJAX RSS 閱讀器 - PHP教程
- • Tomcat學習筆記（史上最全tomcat學習筆記）
- • JDK13 GA發佈：5大特性解讀
相關標籤/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。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. 論文閱讀筆記《Unsupervised fabric defect detection based on a deep convolutional GAN》
- 2. 論文閱讀筆記《Automatic Metallic Surface Defect Detection and Recognition with Convolutional Neural Networ》
- 3. 論文閱讀筆記《A High-Efficiency Fully Convolutional Networks for Pixel-Wise Surface Defect Detection》
- 4. 論文閱讀筆記《A Surface Defect Detection Method Based on Positive Samples》
- 5. 論文閱讀筆記：GAS---spam review detection with graph convolutional networks
- 6. [論文閱讀]Object Detection With Deep Learning: A Review
- 7. 論文閱讀筆記《Convolutional Neural Networks for Steel Surface Defect Detection from Photometric Stereo》
- 8. 【論文閱讀】 Single-cell RNA-seq denoising using a deep count autoencoder.
- 9. 論文閱讀筆記《Segmentation-based deep-learning approach for surface-defect detection》
- 10. 論文閱讀筆記《Deep Active Learning for Civil Infrastructure Defect Detection and Classification》