Adaptive classifier for steel strip surface defects

2016 International Conference on Communication, Image and Signal Processing

物理学;无线电电子学;计算机科学

Jiang, Mingming^1 ; Li, Guangyao^1 ; Xie, Li^1 ; Xiao, Mang^1 ; Yi, Li^1

College of Electronics and Information Engineering, Tongji University, Shanghai

201804, China^1

关键词: Adaptive classifiers;    Bayes Classifier;    Bayes kernel;    Classification results;    Defects detection;    Random subspaces;    Real-world modeling;    Small samples;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/787/1/012019/pdf
DOI  :  10.1088/1742-6596/787/1/012019

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

Surface defects detection system has been receiving increased attention as its precision, speed and less cost. One of the most challenges is reacting to accuracy deterioration with time as aged equipment and changed processes. These variables will make a tiny change to the real world model but a big impact on the classification result. In this paper, we propose a new adaptive classifier with a Bayes kernel (BYEC) which update the model with small sample to it adaptive for accuracy deterioration. Firstly, abundant features were introduced to cover lots of information about the defects. Secondly, we constructed a series of SVMs with the random subspace of the features. Then, a Bayes classifier was trained as an evolutionary kernel to fuse the results from base SVMs. Finally, we proposed the method to update the Bayes evolutionary kernel. The proposed algorithm is experimentally compared with different algorithms, experimental results demonstrate that the proposed method can be updated with small sample and fit the changed model well. Robustness, low requirement for samples and adaptive is presented in the experiment.