An automatic search method for high-quality non-standard gamma curves

Abstract

The present invention is applicable to the technical fields of video monitoring and image processing, and provides an automatic search method for high-quality non-standard Gamma curves, the method comprising: selecting a gamma coordinate plane in a Gamma coordinate plane composed of an input gray value and an output gray value Perform cubic spline interpolation on n points to obtain multiple non-standard Gamma curves; obtain the video image without Gamma correction as the original image; use the non-standard Gamma curve obtained to correct the original image respectively, and calculate the corrected image Objective image index; set filter conditions according to the objective index of the image, and automatically search for high-quality non-standard Gamma curves. The method provided by the embodiment of the present invention can automatically search for a high-quality non-standard Gamma curve, which can obtain a better curve than adaptive Gamma correction. This high-quality non-standard Gamma curve can improve the dynamic range of the image and better improve the image at the same time. Illumination unevenness in overly dark areas and overly bright areas occurs.

Description

technical field [0001] The invention belongs to the technical field of video monitoring and image processing, and in particular relates to an automatic search method for high-quality non-standard Gamma curves. Background technique [0002] Gamma correction is a grayscale transformation, a transfer function introduced to overcome the nonlinear relationship of the human visual system for brightness perception; [0003] Due to the field of view and lighting conditions, the illuminance of the video image is often uneven, and sometimes some areas are too bright and some areas are too dark in the image at the same time. If you use the standard Gamma curve, you cannot take both of the above two into consideration. Condition. The non-standard gamma curves synthesized by some adaptive gamma correction methods are often not high-quality curves; while the artificial sampling method to construct non-standard gamma curves is time-consuming, laborious and inefficient. Standard gamma cur...

AI Technical Summary

Problems solved by technology

[0003] Due to the field of view and lighting conditions, the illuminance of the video image is often uneven, and sometimes some areas are too bright and some areas are too dark in the image at the same time. If you use the standard Gamma curve, you cannot take both of the above two into consideration. Happening

The non-standard Gamma curves synthesized by some adaptive Gamma correction methods are often not high-quality curves; and the artificial sampling method to construct non-standard Gamma curves is time-consuming, laborious and inefficient

Standard gamma curve correction can make the image appear "foggy"

Images