| 基于BP神经网络的船舶焊缝缺陷图像识别 |
| |
| 引用本文： | 高岚,胡亮,罗乐,田凯伟.基于BP神经网络的船舶焊缝缺陷图像识别[J].武汉理工大学学报(信息与管理工程版),2012,34(3):271-274. |
| |
| 作者姓名： | 高岚 胡亮 罗乐 田凯伟 |
| |
| 作者单位： | 1. 武汉理工大学能源与动力工程学院,湖北武汉,430063
2. 广东省深圳市海事局,广东深圳,518000 |
| |
| 摘 要： | 提出了一种基于BP神经网络的船舶焊缝缺陷图像识别的方法,通过对船舶焊缝图像进行预处理,提取出有用的目标缺陷,再进行缺陷特征参数计算,将特征参数和焊缝缺陷类型分别作为输入层和输出层,利用BP算法设计3层结构的神经网络,对样本进行训练和识别。实验结果表明,BP神经网络能较准确地识别出船舶焊缝缺陷。
|
| 关 键 词： | BP神经网络 图像识别 图像预处理 特征参数 船舶焊缝缺陷 |
Recognition of Ship Weld Flaw Image Based on BP Neural Networks |
| |
| GAO Lan
,
HU Liang
,
LUO Le
,
TIAN Kaiwei.Recognition of Ship Weld Flaw Image Based on BP Neural Networks[J].Journal of Wuhan University of Technology(Information & Management Engineering),2012,34(3):271-274. |
| |
| Authors: | GAO Lan HU Liang LUO Le TIAN Kaiwei |
| |
| Affiliation: | GAO Lan:Prof.;School of Energy and Power Engineering,WUT,Wuhan 430063,China. |
| |
| Abstract: | A method of image recognition of ship weld flaw based on BP neural networks was proposed.The pretreatment of the ship weld image was conducted to extract the useful target disfigurement,calculate the characteristic parameters of the disfigurement.And then the characteristic parameters and the weld disfigurement types were used as the input and output layers.The BP algorithm was used to design a three structure′s neural networks,training and recognizing the samples.The experimental result indicates that BP neural networks can more accurately identify the ship weld flaw. |
| |
| Keywords: | BP neural networks image recognition image pretreatment characteristic parameters ship weld flaw |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
