CN114638765A - Low-illumination image enhancement method based on complementary gamma conversion - Google Patents

Abstract

The invention discloses a low-illuminance image enhancement method based on complementary gamma transformation, comprising the following steps: (1) Converting an original color image from RGB space to HSV space, and obtaining the illumination component V, hue component H, saturation of the image component S; (2) use complementary gamma transform function to process the luminance component V to obtain the enhanced luminance component V ^′ ; (3) convert the color image from the HSV space to the RGB space to obtain the enhanced image. The invention can effectively improve the image blur phenomenon caused by uneven illumination, so that the visual effect of the image is better, and at the same time, the high exposure part of the image is suppressed.

Description

A Low-Illumination Image Enhancement Method Based on Complementary Gamma Transform

technical field

The invention relates to the technical field of image processing, in particular to a low-illuminance image enhancement method based on complementary gamma transformation.

Background technique

Due to the limitation of image acquisition technology, imaging environment and other factors, it is sometimes very difficult to obtain high-quality images. Images captured in extreme weather conditions or at night often have low visibility, blurred details, and greatly reduced quality. Getting low-light images is almost inevitable. Therefore, it is necessary to enhance low-light images to meet our needs. In the prior art, the adaptive gamma correction enhancement map (AGCWD) of weighted distribution or the low-light image enhancement map (LIME) technology of illumination estimation are mostly used to enhance the image, but there are some high-level images in the images enhanced by the above technologies. exposed part.

SUMMARY OF THE INVENTION

Purpose of the invention: In view of the above shortcomings, the present invention provides a low-illumination image enhancement method based on complementary gamma transformation, which can effectively improve the image blur caused by uneven illumination, make the visual effect of the image better, and suppress the high exposure part of the image. .

Technical solution: In order to solve the above problems, a low-illumination image enhancement method based on complementary gamma transformation of the present invention includes the following steps:

(1) Convert the original color image from RGB space to HSV space, and obtain the illuminance component V, hue component H, and saturation component S of the image;

(2) The illuminance component V is processed by the complementary gamma transformation function to obtain the enhanced illuminance component V'; the formula of the complementary gamma transformation function is:

V'=a ₁ V ₁ +a ₂ V ₂

V ₁ =V ^r

V ₂ =1-(1-V) ^r

In the formula, r=2.2; a ₁ and a ₂ are weight coefficients;

(3) Convert the color image from HSV space to RGB space to obtain an enhanced image.

Further, the weight coefficient calculation formula in step (2) is as follows:

表示V_i的平均值。In the formula: i takes 1, 2;

represents the average value of _Vi .

Further, the formula for converting the original color image from RGB space to HSV space is:

Further, the formula for converting a color image from HSV space to RGB space is:

Wherein: h _i =[H/60]mod6,f=H/60- _hi , p=V′×(1-S), q=V′×(1-f×S), t=V′× (1-(1-f)×S).

Beneficial effects: Compared with the prior art, the significant advantage of the present invention is: by using the designed complementary gamma transform correction function to process the illuminance component V of the image, the brightness distribution of the image can be made more uniform, and the details of the image can be made more uniform. It is effectively enhanced, and the visual quality of the image is higher; and while the overall brightness of the enhanced image is improved, the high exposure part of the image is also suppressed, and the details are also enhanced to a certain extent.

Description of drawings

Fig. 1 shows the flow chart of the method of the present invention;

Fig. 2 is an image enhancement comparison diagram; Fig. 2 (a) is an original image; Fig. 2 (b) is an enhanced image of the present invention;

Figure 3 shows the comparison of the enhancement results of various algorithms; Figure 3(a) shows the original image, Figure 3(b) shows the enhancement map of adaptive gamma correction (AGCWD) using weighted distribution, and Figure 3 (c) shows the enhancement map of the low-light image enhancement map (LIME) using illumination estimation, and FIG. 3(d) shows the enhancement map of the present invention.

Detailed ways

The technical solutions of the present invention are further described below with reference to the accompanying drawings.

As shown in FIG. 1 , a method for enhancing low-illuminance images based on complementary gamma transformation according to the present invention specifically includes the following steps:

(1) Convert the original color image from RGB space to HSV space, and obtain the luminance component V, hue component H, and saturation component S of the image; the specific formula is:

where:

(2) Use the designed complementary gamma correction function to process the acquired illuminance component V:

(a) The traditional gamma correction function is used for the stretching formula of the V component, and the formula is:

V ₁ =V ^r

(b) The designed compensation formula for the V component is as follows:

V ₂ =1-(1-V) ^r

(c) The designed complementary gamma correction function is:

V'=a ₁ V ₁ +a ₂ V ₂

Among them, r=2.2; a ₁ and a ₂ are both weight coefficients; in order to make the algorithm self-adaptive and the value can be maintained in the [0,1] interval, the designed weight coefficient calculation formula is as follows:

表示V_i的平均值。Among them: i takes 1, 2;

represents the average value of _Vi .

(3) Convert the color image from HSV space to RGB space to obtain an enhanced image. The specific formula is:

Wherein: h _i =[H/60]mod6,f=H/60- _hi , p=V′×(1-S), q=V′×(1-f×S), t=V′× (1-(1-f)×S).

In order to verify the effectiveness of this algorithm, multiple image tests are used to compare the images before and after enhancement. As shown in Fig. 2(a), the original image has the characteristics of blur, uneven illumination, etc. As shown in Fig. 2(b), after the image enhancement processing is performed by the method of the present invention, the picture is clear and the image brightness is more uniform, which is consistent with the Compared with the original image, the enhancement effect is remarkable. As shown in Figure 3(a), the original image has the characteristics of blurring and uneven illumination. As shown in Figure 3(b) and Figure 3(c), although the overall brightness of the image is improved, there are some high exposures in the image. As shown in Figure 3(d), the method of the present invention can not only improve the overall brightness of the image, but also suppress the high exposure part of the image, and the details are also enhanced to a certain extent.

Claims (4)

1. a low-illumination image enhancement method based on complementary gamma transformation, is characterized in that, comprises the following steps: (1) Convert the original color image from RGB space to HSV space, and obtain the illuminance component V, hue component H, and saturation component S of the image; (2) The illuminance component V is processed by the complementary gamma transformation function to obtain the enhanced illuminance component V'; the formula of the complementary gamma transformation function is: V'=a ₁ V ₁ +a ₂ V ₂ V ₁ =V ^r V ₂ =1-(1-V) ^r In the formula, r=2.2; a ₁ and a ₂ are weight coefficients; (3) Convert the color image from HSV space to RGB space to obtain an enhanced image. 2. the low-illuminance image enhancement method based on complementary gamma transformation according to claim 1, is characterized in that, in step (2), weight coefficient calculation formula is as follows:

In the formula: i takes 1, 2;

represents the average value of _Vi . 3. the low-illuminance image enhancement method based on complementary gamma transformation according to claim 1, is characterized in that, the formula that original color image is converted from RGB space to HSV space is:

4. the low-illuminance image enhancement method based on complementary gamma transformation according to claim 1, is characterized in that, the formula that color image is converted from HSV space to RGB space is:

Wherein: h _i =[H/60]mod6,f=H/60- _hi , p=V′×(1-S), q=V′×(1-f×S), t=V′× (1-(1-f)×S).

Images