跳至主導覽
跳至搜尋
跳過主要內容
國立中央大學 首頁
說明與常見問題
English
中文
首頁
人才檔案
研究單位
研究計畫
研究成果
資料集
榮譽/獲獎
學術活動
新聞/媒體
影響
按專業知識、姓名或所屬機構搜尋
FDD: a deep learning–based steel defect detectors
Fityanul Akhyar, Ying Liu, Chao Yung Hsu,
Timothy K. Shih
,
Chih Yang Lin
資訊工程學系
機械工程學系
研究成果
:
雜誌貢獻
›
期刊論文
›
同行評審
28
引文 斯高帕斯（Scopus）
總覽
指紋
指紋
深入研究「FDD: a deep learning–based steel defect detectors」主題。共同形成了獨特的指紋。
排序方式
重量
按字母排序
Keyphrases
Defect Detector
100%
Steel Defects
100%
Manufacturing Process
66%
Industrial Manufacturing
66%
Product Quality
33%
Detection Method
33%
Defect Detection
33%
Surface Defects
33%
Detection Accuracy
33%
Geometric Shape
33%
Training Process
33%
Automated Inspection Systems
33%
Scaling Technique
33%
High Quality Products
33%
Mean Average Precision
33%
Bounding Box
33%
Inference Process
33%
Cascade R-CNN
33%
Severstal
33%
Surface Defect Detection
33%
Steel Surface Defect Detection
33%
Deformable RoI Pooling
33%
Random Scaling
33%
Deformable Convolution
33%
Defect Inspection System
33%
Guided Anchoring
33%
Region Proposal
33%
Computer Science
Product Quality
100%
Inspection System
100%
Detection Method
50%
Convolutional Neural Network
50%
Detection Accuracy
50%
Training Process
50%
Scaling Technique
50%
Mean Average Precision
50%
Inference Process
50%
Baseline Architecture
50%
Deformable Convolution
50%
Engineering
Surface Defect
100%
Manufacturing Process
66%
Defect Detection
66%
Geometric Shape
33%
Input Image
33%
Product Quality
33%
Steel Surface
33%
High Quality Product
33%
Bounding Box
33%
Inference Process
33%
Convolutional Neural Network
33%
Material Science
Surface Defect
100%