A method based on moving least squares for XRII image distortion correction

Authors

  • Yan Shiju,

    1. Institute of Biomedical Manufacturing and Life Quality Engineering, School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, China
    Search for more papers by this author
    • a)

      Author to whom correspondence should be addressed. Electronic mail: yanshijv@sjtu.edu.cn; Telephone: 086-021-34206078; Fax: 086-021-34206815

  • Wang Chengtao,

    1. Institute of Biomedical Manufacturing and Life Quality Engineering, School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, China
    Search for more papers by this author
  • Ye Ming

    1. Institute of Biomedical Manufacturing and Life Quality Engineering, School of Mechanical Engineering, Shanghai Jiaotong University, Shanghai, China
    Search for more papers by this author

Abstract

This paper presents a novel integrated method to correct geometric distortions of XRII (x-ray image intensifier) images. The method has been compared, in terms of mean-squared residual error measured at control and intermediate points, with two traditional local methods and a traditional global methods. The proposed method is based on the methods of moving least squares (MLS) and polynomial fitting. Extensive experiments were performed on simulated and real XRII images. In simulation, the effect of pincushion distortion, sigmoidal distortion, local distortion, noise, and the number of control points was tested. The traditional local methods were sensitive to pincushion and sigmoidal distortion. The traditional global method was only sensitive to sigmoidal distortion. The proposed method was found neither sensitive to pincushion distortion nor sensitive to sigmoidal distortion. The sensitivity of the proposed method to local distortion was lower than or comparable with that of the traditional global method. The sensitivity of the proposed method to noise was higher than that of all three traditional methods. Nevertheless, provided the standard deviation of noise was not greater than 0.1 pixels, accuracy of the proposed method is still higher than the traditional methods. The sensitivity of the proposed method to the number of control points was greatly lower than that of the traditional methods. Provided that a proper cutoff radius is chosen, accuracy of the proposed method is higher than that of the traditional methods. Experiments on real images, carried out by using a 9 in. XRII, showed that residual error of the proposed method (0.2544±0.2479pixels) is lower than that of the traditional global method (0.4223±0.3879pixels) and local methods (0.4555±0.3518pixels and 0.3696±0.4019pixels, respectively).

Ancillary