Image enhancement method based on multiple exposure generation and re-fusion frame

Abstract

The invention discloses an image enhancement method based on a multi-exposure generation and re-fusion frame and belongs to the technical field of image processing. The image enhancement method includes the steps of performing image illumination estimation based on images to obtain an image illumination map L; calculating an optimal exposure ratio sampling value set [kappa]* according to the imageillumination map L; generating a multi-exposure image set according to the camera model g and the sampling value set [kappa]*; performing visual quality evaluation on each image in the multi-exposureimage set to obtain a quality grayscale map; and performing fusion of the multi-exposure image set to obtain an enhanced image. According to the invention, the over bright or dark problems in a single exposure image during the process of camera taking an image can be solved, the obtained enhancement result has less contrast distortion, the visual information authenticity index VIF is larger, theillumination sequence error index LOE is smaller, with no obvious aperture or stroke marks, and a better visual experience can be obtained.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image enhancement method based on multi-exposure generation and re-fusion frame. Background technique [0002] Due to the limited dynamic range of the camera, the images captured in high dynamic scenes have the problem of being too dark locally. Take a person with his back to the sun as an example: if automatic exposure is used, the background is too bright and the person is too dark; if the person is well exposed by increasing the exposure time, increasing the aperture, or increasing the sensitivity, etc. The maximum brightness of the image is reached and it is white; if the background is well exposed by brightening the image by reducing the exposure time, reducing the aperture, or reducing the sensitivity, etc., the person is completely black due to the low brightness value. The existing technology cannot solve the problem of too bright and too dark in a single exp...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies of the above-mentioned prior art, the present invention provides an image enhancement method based on multi-exposure generation and refusion frame, by using the image enhancement method to modify the appearance of the image on the display or other physical supports, to solve the problem of the camera image capture process The problem of too bright and too dark in a single exposure image can get a better visual experience

[0006] An image enhancement method based on a multi-exposure generation refusion framework, which solves the problem of overbrightness and overdarkness in a single exposure image in the process of capturing an image by a camera by modifying the appearance of the image by using the image enhancement method, including the following steps:

Images