摘要
传统图像拼接多对图像匹配点间的距离做最小化调整,并设计目标函数来实现对图像失真的拼接,但多灰度失真图像在这个过程中,容易受到图像灰度值失真变化的影响,会增大误差。提出基于非线性方程的多灰度失真图像拼接系统设计,依据像素失真后非线性变化的规律,设计了以图像解码模块和图像拼接模块为中心的失真图像拼接算法;采用物像平面的坐标映射算法,对多灰度失真图像的横、纵坐标做精确地转换,并依据灰度响应曲线的反函数,实现图像灰度失真的拼接。实验结果表明,提出的算法设计误差小、图像拼接精度高,能够获得较好的多灰度失真图像拼接效果。
In the traditional image mosaic,the distance between matching points of multiple images is minimized and objective function is designed to realize the mosaic of image distortions. However,in this process,the multi-grayscale distortion image is easily affected by the distortion of the image＇s gray value and error will be increased. In this paper,the mosaic system design of multi-grayscale distortion image based on nonlinear equation is proposed. According to the non-linear variation after pixel distortion,a mosaic algorithm of image distortion is designed based on image decoding module and image mosaic module. Using the coordinate mapping algorithm of image plane,the horizontal and vertical coordinates of the multi-grayscale distortion image are accurately converted,and the gray-scale distortion of the image is spliced according to the inverse function of the gray response curve. The experimental results show that the proposed algorithm has small design errors and high image mosaic accuracy,which can achieve good multi-grayscale distortion image mosaic effect.
出处
《中国电子科学研究院学报》
北大核心
2017年第6期662-667,共6页
Journal of China Academy of Electronics and Information Technology
基金
2017年山西省高等学校教学改革创新项目:基于大数据条件下会计实践教学模式的改革和创新(J2017130)
关键词
非线性方程
多灰度
失真图像
系统设计
nonlinear equation
multi-grayscale
distortion image
system design
