Assessment of Computerized Method for Correction of Optical Distortion of Facial Images

Abstract

The availability of software developed to correct the distortion associated with non-metric cameras was examined using a test chart composed of 63 gridiron dots and two CCD cameras: a commercially available camera as the reference and an actual surveillance camera installed in a bank. The software was designed to calculate distortion parameters such as the radial and tangential distortion coe‹cients and the principal points. Constant parameter values were obtained when test charts were taken at six positions in the lensˆeld. The average of displacement errors between the 63 dots on the corrected image and those on the presumed ideal image was measured. In the reference camera, a pre-correction error of 1.24 mm decreased to 0.08 mm after correction. In the surveillance camera the error decreased from 7.92 mm to 0.33 mm. The present method was compared with two others: the graph method and the Open CV method. The former uses a distortion graph, which indicates the distortion level () at several locations from the center to the radial direction of the lensˆeld. The latter is a free camera calibration software tool, developed by Intel Co. for the calculation of the intrinsic camera parameters of video camera lenses. The present method was associated with smaller error values than either of the other two methods. It is therefore suggested that this method could usefully be applied to distortion correction of facial images taken by surveillance cameras.

Effect of Barrel Distortion and Super-Resolution for Single-View-Based Ear Biometrics Rotated in Depth

“…Hence, accounting for this effect is necessary for admissibility of photometric evidence. Concerning the effect of barrel distortions of surveillance images, Biwasaka [4] has reported its effect on face images. However, a similar study for ears has not been reported in the literature.…”

“…Whereas masks and sunglasses often purposely obscure facial features, ear shape can be all that is required to identify subjects in surveillance images [2] [3]. Regarding the admissibility of evidence of surveillance camera images, resolution, barrel distortion [4], and the differences in the angle of shot [2][3] become problems. Hence, accounting for these problems is necessary for computer systems acceptable for the forensic community.…”

Application of computerised correction method for optical distortion of two-dimensional facial image in superimposition between three-dimensional and two-dimensional facial images

“…The Dist-Rugle software was also used to calculate the average displacement of the co-ordinates between the dots of the corrected chart image and those of the presumed ideal image for following the quantitative evaluation [8]. The computer-assisted facial image identification system developed by Yoshino et al [2,3] was employed.…”

“…Correction of the original 2D facial images taken by each camera was performed according to the distortion parameter of each lens [8]. The Dist-Rugle software was also used to calculate the average displacement of the co-ordinates between the dots of the corrected chart image and those of the presumed ideal image for following the quantitative evaluation [8].…”

“…Although the perspective is due to the shooting distance regardless of the type of camera lens [5], the use of wide-angle lenses results in varying levels of distortion. Therefore, we developed computerised correction methods to counter the distortion of surveillance camera images [6][7][8]. Software was developed to reduce distortion by calculating distortion parameters such as the distortion coefficient, principle point, and the focal length by the axes of the camera lens.…”