Image distortion correction method and device

Abstract

The invention provides an image distortion correction method and device, and the method comprises the steps: carrying out optical distortion correction of a collected source image, and obtaining a first correction image; wherein the first corrected image comprises a background area and a portrait with tensile deformation, and the portrait with tensile deformation at least comprises a first human body area with tensile deformation and a second human body area with tensile deformation; performing algorithm constraint correction on the first human body region, the second human body region and thebackground region to obtain a second corrected image; enabling constraint terms adopted by algorithm constraint correction to constrain the first human body area, the second human body area and the background area, so that tensile deformation of the first human body area and the second human body area is respectively corrected, and image content penetrating through portraits in the background area has no fault phenomenon in human eye vision. According to the invention, natural image distortion correction can be realized, and the user experience is improved.

Description

[0001] technology neighborhood [0002] The present application relates to image processing technology, in particular to an image distortion correction method and device. Background technique [0003] With the development of information technology, terminals (such as mobile phones) integrate more and more functions, and the photography function has become one of the important functions of the terminal. In recent years, as the field of view of the terminal lens increases, the distortion of portrait images in the images captured by the terminal becomes more and more significant. [0004] Image distortion is due to the fact that the large field of view and short focal length optical system does not satisfy the pinhole model, and the focal height of the chief rays of different fields of view after passing through the optical system and the Gaussian image plane is not equal to the ideal image height, which makes the actual image point deviate from the ideal image point, thus The c...

AI Technical Summary

Problems solved by technology

[0006] However, since this scheme needs to calibrate the straight line on the source image, the final image correction effect will be affected by the detection accuracy of the straight line

In addition, this solution can only correct the portrait as a whole, resulting in the final portrait not really conforming to human vision, such as figure 1 The image on the left in (1) in (1) is the image before correction, and the image on the right is the image after correction. It can be seen that the body of the person on the left in the image after correction has not been corrected

In addition, this scheme is also prone to cause faults in the background area, such as figure 1 The left image in (2) in (2) is the image before correction, and the image on the right is the image after correction. It can be seen that the straight line content of the character background in the corrected image has faults and incoherence

[0007] Therefore, how to achieve more natural image distortion correction is still a severe technical challenge.

Images