An Algorithm of Deformation Image Correction Based on Spatial Mapping  

作　　者：Xiangyu DENG Aijia ZHANG Jinhong YE 

机构地区：[1]College of Physics and Electronic Engineering,Northwest Normal University,Lanzhou 730070,China

出　　处：《Chinese Journal of Electronics》2024年第5期1326-1336,共11页电子学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(Grant No.61961037);the Industrial Support Plan of Education Department of Gansu Province(Grant No.2021CYZC-30).

摘　　要：The original image undergoes geometric deformation in terms of position,shape,size,and orientation due to the shooting angle or capturing process during image acquisition.This leads to inconveniences and significant challenges in various image processing fields such as image fusion,denoising,recognition,and segmentation.To enhance the processing ability and recognition accuracy of deformation images,an adaptive algorithm for correcting image deformities is proposed for quadrilaterals and triangles.Firstly,the deformation image undergoes preprocessing,and the contour of the image edge is extracted.Then,discrete points on the image edge are identified to accurately locate the edges.Finally,the deformation of the quadrilateral or triangle is transformed into a standard rectangular or equilateral triangular image using the proposed three-dimensional homography transformation algorithm.This effectively completes the conversion from an irregular image to a regular image in an adaptive manner.Numerous experiments demonstrate that the proposed algorithm surpasses traditional methods like Hough transform and Radon transform.It improves the effectiveness of correcting deformation in images,effectively addresses the issue of geometric deformation,and provides a new technical method for processing deformation images.

关 键 词：Image preprocessing Image vertex positioning Three-dimensional space Homography transformation Image correction 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]