This paper proposes a corrected method of distorted image based on adaptive control. First, the adaptive control relationship of pixel point positions between distorted image and its corrected image is given by using ...This paper proposes a corrected method of distorted image based on adaptive control. First, the adaptive control relationship of pixel point positions between distorted image and its corrected image is given by using polynomial fitting, thus control point pairs between the distorted image and its corrected image are found. Secondly, the value of both image distortion centre and polynomial coefficient is obtained with least square method, thus the relationship of each control point pairs is deduced. In the course of distortion image processing, the gray value of the corrected image is changed into integer with bilinear interpolation. Finally, the experiments are performed to correct two distorted printed circuit board images. The results are perfect and the mean square errors of residual error are tiny.展开更多
基金Project supported by the Research Foundation of the State Key Laboratory,China(Grant No.9140C1406020708)the Program Research Foundation of Hunan Province Science-Technology Department,China(Grant No.2009FJ3187)the 11th Five Year Plan for Key Construction Academic Subject(Optics)of Hunan Province,China(Grant No.06GXCD02)
文摘This paper proposes a corrected method of distorted image based on adaptive control. First, the adaptive control relationship of pixel point positions between distorted image and its corrected image is given by using polynomial fitting, thus control point pairs between the distorted image and its corrected image are found. Secondly, the value of both image distortion centre and polynomial coefficient is obtained with least square method, thus the relationship of each control point pairs is deduced. In the course of distortion image processing, the gray value of the corrected image is changed into integer with bilinear interpolation. Finally, the experiments are performed to correct two distorted printed circuit board images. The results are perfect and the mean square errors of residual error are tiny.
