Thresholding Based on Maximum Weighted Object Correlation for Rail Defect Detection
スポンサーリンク
概要
- 論文の詳細を見る
Automatic thresholding is an important technique for rail defect detection, but traditional methods are not competent enough to fit the characteristics of this application. This paper proposes the Maximum Weighted Object Correlation (MWOC) thresholding method, fitting the features that rail images are unimodal and defect proportion is small. MWOC selects a threshold by optimizing the product of object correlation and the weight term that expresses the proportion of thresholded defects. Our experimental results demonstrate that MWOC achieves misclassification error of 0.85%, and outperforms the other well-established thresholding methods, including Otsu, maximum correlation thresholding, maximum entropy thresholding and valley-emphasis method, for the application of rail defect detection.
- 2012-07-01
著者
-
LUO Siwei
School of Computer and Information Technology, Beijing Jiaotong University
-
Luo Siwei
School Of Computer And Information Technol. Beijing Jiaotong Univ.
-
Huang Yaping
School Of Computer And Information Technology Beijing Jiaotong University
-
LI Qingyong
School of Computer and Information Technology, Beijing Jiaotong University
-
LIANG Zhengping
College of Computer Science and Software Engineering, Shenzhen University
関連論文
- A Fast Algorithm for Learning the Overcomplete Image Prior
- Contour Grouping and Object-Based Attention with Saliency Maps
- A Fast Algorithm for Learning the Overcomplete Image Prior
- Contour Grouping and Object-Based Attention with Saliency Maps
- A QoS-Enabled Double Auction Protocol for the Service Grid
- Visual Attention Guided Multi-Scale Boundary Detection in Natural Images for Contour Grouping
- An Association Rule Based Grid Resource Discovery Method
- Complex Cell Descriptor Learning for Robust Object Recognition
- Combining Boundary and Region Information with Bolt Prior for Rail Surface Detection
- Thresholding Based on Maximum Weighted Object Correlation for Rail Defect Detection
- Normalized Joint Mutual Information Measure for Ground Truth Based Segmentation Evaluation