The BP neural network method for errors correction in image

摘要：

Due to different levels and characteristic deformation existing in any images, it is difficult to select an appropriate model to correct effectively. Considering BP neural network is a high and nonlinear complicated system which can approach at any precision, we attempt to use it for image geometric correction. In Ms paper, errors correction of scanning map by BP neural network as an example was discussed. The result shows that the accuracy of scanning map corrected by the BP neural network is higher man by normal function fitting.

关键词： errors correction fitting BP Neural Network accuracy

作者: Zhang Juqing Nie Jianliang Xin Yafang

作者单位: School of Geology Engineering and Geomatics, Changan University, Yanta Road Xian, China,710054 Geodetic Data Processing Center, State Bureau of Surveying and Mapping, Youyi Road, Xian,China, 710

会议类型: 国际会议

会议名称: 2011 Fourth International Conference on Intelligent Computation Technology and Automation(2011年第四届智能计算技术与自动化国际会议 ICICTA 2011)

会议地点: 深圳

会议语种:英文

页码: 259-262

在线出版日期: 2011-03-28（万方平台首次上网日期，不代表论文的发表时间）