A response distortion correction method of Intensified Complementary Metal Oxide Semiconductor (ICMOS) camera is proposed. First, the Fixed Pattern Noise (FPN) is removed from the original input image captured by the ICMOS camera. Second, the response correction using the traditional method, i.e., the polynomial fitting technique, is considered to eliminate the error to some extent. Third, a response correction using the machine learning-based method is proposed to decrease the error further. A kind of Improve Adaptive Genetic Algorithm-Support Vector Regression (IAGA-SVR) is designed to improve the computation effect of SVR. The inputs of IAGA-SVR include the manufacturing and response parameters of ICMOS camera; the output of it is the error compensation item. Extensive experiment results have shown that our proposed method can improve the response correction accuracy than the traditional and other improved optimal algorithm-based methods.
Response Distortion Correction of ICMOS Camera Using Improved Support Vector Regression
Lect. Notes Electrical Eng.
International Conference on Man-Machine-Environment System Engineering ; 2023 ; Beijing, China October 20, 2023 - October 23, 2023
2023-09-05
8 pages
Article/Chapter (Book)
Electronic Resource
English
Improved SMO algorithm of nonlinear regression support vector machine
British Library Online Contents | 2014
|DISTORTION CORRECTION FOR VEHICLE SURROUND VIEW CAMERA PROJECTIONS
European Patent Office | 2019
|Vehicle-mounted camera apparatus and image distortion correction method
European Patent Office | 2024
|VEHICLE-MOUNTED CAMERA APPARATUS AND IMAGE DISTORTION CORRECTION METHOD
European Patent Office | 2022
|Automatic radial distortion correction in zoom lens video camera
British Library Online Contents | 2010
|