Flaw Feature Analysis and Selection of X-ray Images of Carbon Products
-
摘要: 针对炭素制品X射线检测图像的特点，对缺陷及其特征提取与选择技术进行了研究。分析了炭素制品生产中易产生的缺陷类型及缺陷的成像特征，在此基础上，从缺陷样本中提取了19个特征值。以特征组合分类能力数学模型为适应度函数，设计了基于遗传算法的特征选择策略，实现了对缺陷原始特征量的优化选择。利用BP神经网络分类器及选择的特征值对缺陷进行了模式分类。研究结果表明，提出的选择方法是比较有效的，可以用于缺陷的识别与分类。Abstract: Regarding the characteristic of X-ray detection images of carbon material, flaw feature extraction and selection techniques are studied. Defect style and imaging character of carbon product that easy create in the course of produce are analyzed, based on that, nineteen features are extracted from flaw stylebook. Mathematics model of feature combination classification is regarded as fitness function, optimal selection of original flaw feature is realized with feature selection strategy based on genetic algorithm. Pattern classification of flaw is carried out with BP neural network and the feature selected. Experiment results show that, the method of feature selection is relatively effective, and it could be used for the recognition and classification of flaw.
-
Keywords:
- Carbon produce /
- X-ray image /
- Feature selection /
- Genetic algorithm
-
-
[1] 刚 铁，王东华.基于自适应形态学滤波的X射线图像的缺陷提取\[J\].机械工程学报,2001,37(5):85. [2] 刚 铁，吴 林.焊接缺陷的超声回波特征分析与模式识别\[J\].哈尔滨工业大学学报,1997,29(2):15-17. [3] 李 平，陈 锐，陆玉峻，等.石墨制品的超声波无损检测技术\[J\].炭素,1997,(4):32-36. [4] 任大海，尤 政.X射线检测中图像质量的改善\[J\].仪表技术与传感器,2001,(1):36-37. [5] Huang YS, Suen CY. A method of combining multiple expents for the recognition of unconstrained handwritten numerals\[J\]. IEEE Trans,1995,PAMI(11):90. [6] Liu H, Motoda H. Feature Selection for Knowledge Discovery and Data Mining\[M\]. New York: Kluwer academic publishers,1988. [7] Bertroni A Iberto, Dorigo Marco. Implicit parallelism in genetic algorithms\[J\]. Artificial Intelligence,1993,61(2):307-314.
计量
- 文章访问数: 1
- HTML全文浏览量: 0
- PDF下载量: 2
下载:
