Multi-feature fusion based classification algorithm of surface disease image of concrete structure(PDF)
长安大学学报（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]
- Issue:
- 2021年3期
- Page:
- 64-74
- Research Field:
- 桥梁与隧道工程
- Publishing date:
Info
- Title:
- Multi-feature fusion based classification algorithm of surface disease image of concrete structure
- Author(s):
- YANG Yang; WANG Lianfa; ZHANG Yufeng; HAN Xiaojian
- (1. State key Laboratory on Safety and Health for Inservice Long Span Bridge, Nanjing 210012, Jiangsu, China;2. Key Laboratory of Large Span Bridge Health Inspection & Diagnosis Technology, Ministry of Communications,Nanjing 210012, Jiangsu, China; 3. Center of Data Measured by Structural Health Monitoring System ofLongspan Bridge of Jiangsu, Nanjing 210012, Jiangsu, China;)
- Keywords:
- bridge engineering; classification algorithm; multifeature fusion; disease image; concrete structure; SVM
- PACS:
- -
- DOI:
- -
- Abstract:
- To improve the accuracy and efficiency of disease image classification at concrete surface diseases of cracking, bare bar corrosion and defect, and reduce labor cost, one type of disease image classification algorithm of concrete structure surface based on multifeature fusion was proposed. For this algorithm, texture features, gray histogram features, and color features of disease image were extracted and support vector machine (SVM) was employed as classifier. Three disease classification models were developed, and the three types of image features were taken as training samples, respectively. The algorithm of term weighting was adopted to evaluate the weight of each type of image features, then the classification models and the weights were combined to calculate the reliability value of disease image classification. According to the minimal error rule, the image was classified as the disease type associated with maximum reliability value. Seven feature fusion alternatives were generated by combination of the three types of features, with which three single feature algorithm models and four multifeature fusion algorithm models were developed with 2 400 image training samples for testing the accuracy of the proposed algorithm. The results show that the classification accuracy of multifeature fusion algorithm model is higher than that of single feature algorithm model. The optimal effect is obtained with the algorithm model fused all the three types of features using polynomial kernel function, with which the average classification accuracy reached 84%, and about 7% higher than single feature algorithm models. Depending on the comprehensive information provided by multifeature fusion of disease image, the classification algorithm model fused with texture features, gray histogram features, and color features raised the classification accuracy of bare bar corrosion and defect diseases to 88%. Furthermore, multifeature fusion algorithm model appears a better stability on disease classification when comparing with single feature algorithm model. The research is an effective method for the classification of concrete surface disease, can enhance the efficiency of disease image processing and classification accuracy. 2 tabs, 6 figs, 28 refs.
Last Update: 2021-06-04