CN111696052A - Underwater image enhancement method and system based on red channel weakness - Google Patents

Abstract

The invention discloses an underwater image enhancement method and system based on the attenuation of the red channel, which obtains the pixel values of the red channel, the green channel and the blue channel of the underwater image; Compensate the pixel values of the green channel and blue channel in the color compensation to obtain the color-compensated image; use the white balance algorithm to adjust the color of the color-compensated image. Advantages: the present invention compensates the pixel value of the red channel by using the green channel and the blue channel with relatively small underwater attenuation for the underwater image with severe red channel attenuation, and then adjusts the image color through the white balance algorithm; the present invention can Adaptively compensates the pixel value of the red channel to make it as close to the original value as possible without causing adverse phenomena such as color overexposure or artifacts.

Description

A method and system for underwater image enhancement based on red channel attenuation

technical field

The invention relates to an underwater image enhancement method and system based on red channel attenuation, and belongs to the technical field of image processing.

Background technique

Nowadays, resource exploitation on land is difficult to meet the needs of technological and economic development, and people have turned to the ocean, which occupies more than 70% of the earth's surface. The underwater environment is very complicated. First of all, seawater has different absorption characteristics for light of different wavelengths. After natural light or artificial light source travels for 2 meters in water, the red component will be completely absorbed, and only green and The blue component; secondly, there are various suspended particles in the seawater, and the light is affected by these suspended medium particles when it propagates. These reasons not only cause the background of the underwater image directly obtained by the image sensor to appear blue-green, but also cause the collected image to have low contrast, blurred edge details, uneven brightness, and poor sharpness.

There are many kinds of underwater image enhancement algorithms, which can be mainly divided into spatial domain method and transform domain method. Among them, the method of the spatial domain is to directly process the pixels on the image, which is generally the mapping process on the gray level, including histogram equalization and limited gray world hypothesis, white balance and Retinex enhancement theory. The transform domain method is to convert the spatial domain to the change domain through a certain mapping relationship, and process the image in favor of the characteristics of the change domain, and finally return to the spatial domain. Common transform domain methods include the use of Fourier transform and wavelet transform. However, although the existing algorithm improves the visual effect of underwater images to a certain extent, the phenomenon of image overexposure occurs when dealing with underwater images with severe red channel attenuation.

SUMMARY OF THE INVENTION

The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide an underwater image enhancement method and system based on the attenuation of the red channel.

In order to solve the above-mentioned technical problems, the present invention provides an underwater image enhancement method based on the attenuation of the red channel, and obtains the pixel values of the red channel, the green channel, and the blue channel of the underwater image;

For each pixel value of the red channel, the pixel value of the green channel and the blue channel in the pixel value field is compensated to obtain a color-compensated image;

Use the white balance algorithm to color-adjust the color-compensated image.

Further, after the step of acquiring the red channel, green channel, and blue channel pixel values of the underwater image, it also includes:

Normalize pixel values.

Further, the compensation formula used for compensation by the pixel values of the green channel and the blue channel in the pixel value field is as follows:

α+β=1

In the formula, I _{r, com} (x, y) represents the pixel value after red channel compensation; I _r (x, y), I _g (x, y) and I _b (x, y) represent the red channel, green The pixel values of the channel and blue channel; α and β are both a constant coefficient less than 1; I _g represents the normalized average value of the green channel in the pixel value field, and I _b represents the normalization of the blue channel in the pixel value field. average value.

Further, after the step of compensating through the pixel values of the green channel and the blue channel in the pixel value field, the step further includes:

Perform inverse normalization to synthesize the color-compensated image.

An underwater image enhancement system based on red channel attenuation, comprising:

The acquisition module is used to acquire the pixel values of the red channel, green channel and blue channel of the underwater image;

The compensation module is used to compensate each pixel value of the red channel through the pixel values of the green channel and the blue channel in the pixel value field to obtain a color-compensated image;

The adjustment module is used to adjust the color of the color-compensated image using the white balance algorithm.

Further, the acquisition module also includes:

The normalization processing module is used to normalize the pixel values.

Further, the compensation module includes a calculation module for performing compensation calculation on each pixel value of the red channel by the following formula:

α+β=1

In the formula, I _{r, com} (x, y) represents the pixel value after red channel compensation; I _r (x, y), I _g (x, y) and I _b (x, y) represent the red channel, green The pixel values of the channel and blue channel; α and β are both a constant coefficient less than 1; I _g represents the normalized average value of the green channel in the pixel value field, and I _b represents the normalization of the blue channel in the pixel value field. average value.

Further, the compensation module includes an inverse normalization processing module for performing inverse normalization and synthesizing the color-compensated image.

Beneficial effects achieved by the present invention:

The invention is based on the underwater image enhancement algorithm with the attenuation of the red channel, and compensates the pixel value of the red channel by using the green channel and the blue channel with relatively small underwater attenuation for the underwater image with serious red channel attenuation, and then uses the white balance algorithm to compensate the pixel value of the red channel. Adjust the color of the image. Experiments show that the algorithm can effectively solve the problem of color recovery of underwater images and improve the contrast of images.

Compared with the existing underwater image enhancement algorithm, the algorithm can adaptively compensate the pixel value of the red channel to make it close to the original value to the greatest extent, and at the same time, it will not produce unfavorable phenomena such as color overexposure or artifacts.

Description of drawings

Fig. 1 is the flow chart of the underwater image enhancement algorithm based on the weakening of the red channel of the present invention;

Figures 2(a) and 2(b), Figure 2(c), and Figure 2(d) are the original image, the red channel after compensation, the red channel grayscale histogram in the original image, and the red channel after compensation, respectively, according to the embodiment of the present invention. grayscale histogram;

Figures 3(a), 3(b), and 3(c) are respectively the effect comparison diagrams in the process of implementing the algorithm according to the embodiment of the present invention, in which Figure 3(a) is the original image, and Figure 3(b) is the supplementary red channel The latter picture, Figure 3(c) is the after picture of white balance.

Detailed ways

In order to make the purpose, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the following The described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

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

As shown in Figure 1, the present invention discloses an underwater image enhancement algorithm based on red channel attenuation, which specifically includes the following steps

(1) Obtain the red channel, green channel, and blue channel pixel values of the underwater image;

(2) For each pixel value of the red channel, compensation is performed by the pixel value of the green channel and the blue channel;

(3) Use the white balance algorithm to adjust the color-compensated image.

In the step (1), after acquiring the pixel values of the red channel, green channel, and blue channel of the underwater image, the pixel values are normalized, that is, the pixel values are normalized from [0, 255] to [0, 1] within the interval.

The specific scheme of color compensation in the step 2 is as follows:

Since the pixel values of the neighborhood are correlated, and the attenuation of the red channel is too serious compared to the blue channel and green channel of the underwater distorted image, the pixels of the red channel are compensated by the pixel values of the green channel and the blue channel in a certain pixel field. value, so that the red channel in the image is close to the original value. The specific formula is as follows:

α+β=1

表示该窗口中绿色通道的归一化平均值，

表示该窗口中蓝色通道的归一化平均值α在[0.7,1]区间内取值效果较好，本实验中取α为0.9，β为0.1，领域大小为3*3。In the formula, I _{r, com} (x, y) represents the pixel value after red channel compensation; I _r (x, y), I _g (x, y) and I _b (x, y) represent the red channel, green The pixel value of the channel and blue channel, α and β are a constant coefficient less than 1;

represents the normalized mean of the green channel in this window,

It means that the normalized average value α of the blue channel in this window is better in the [0.7,1] interval. In this experiment, α is 0.9, β is 0.1, and the field size is 3*3.

Further, after the pixel value of the red channel of the image is compensated, inverse normalization is performed on the pixel value of the red, green and blue channels, and the pixel value is multiplied by 255 and rounded down to obtain I _{r inverse} (x, y), I _{g inverse} (x, y), I _{b inverse} (x, y), and synthesize a new image.

White balance refers to the color reproduction of an image that is originally a white object. The following takes the grayscale world algorithm in white balance as an example to adjust the color of the image. When the color transition of the image is large, the gray-scale world hypothesis considers that the pixel averages of the three color channels of the image are approximately equal, that is, they have the same gray value.

The specific idea and calculation formula are as follows:

Assuming that I(x,y) is an image with M×N pixels, x and y are the specific positions of the pixels, and the average calculation formula of the three color channels of red, green, and blue is as follows:

K=(R _avg +G _avg +B _avg )/3

Among them, I _{r inverse} (x, y), I _{g inverse} (x, y), and I _{b inverse} (x, y) are the red, green, and blue channel pixel values after inverse normalization, and the values of the three RGB channels are rewritten respectively. for:

Then you can use the rewritten new channel to weight the original image to get a color-corrected image.

Correspondingly, the present invention also provides an underwater image enhancement system based on red channel attenuation, comprising:

The acquisition module is used to acquire the pixel values of the red channel, green channel and blue channel of the underwater image;

The compensation module is used to compensate each pixel value of the red channel through the pixel values of the green channel and the blue channel in the pixel value field to obtain a color-compensated image;

The adjustment module is used to adjust the color of the color-compensated image using the white balance algorithm.

The said acquisition module also includes:

The normalization processing module is used to normalize the pixel values after acquiring the pixel values of the red channel, the green channel and the blue channel of the underwater image.

The compensation module includes a calculation module for performing compensation calculation on each pixel value of the red channel by the following formula:

α+β=1

表示该像素值领域中绿色通道的归一化平均值，

表示该像素值领域中蓝色通道的归一化平均值。In the formula, I _{r, com} (x, y) represents the pixel value after red channel compensation; I _r (x, y), I _g (x, y) and I _b (x, y) represent the red channel, green The pixel value of the channel and blue channel; α and β are both a constant coefficient less than 1;

represents the normalized mean of the green channel in this field of pixel values,

Represents the normalized mean of the blue channel in this field of pixel values.

The compensation module includes an inverse normalization processing module, which is used to perform inverse normalization after compensation is performed by the pixel values of the green channel and the blue channel in the pixel value field to synthesize a color-compensated image.

The white balance algorithm used can also adopt algorithms such as gray edge (gray edge), shades of gray (gray shadow), max rgb (maximum rgb).

In order to verify the effectiveness of this algorithm, the color recovery test is used to test the images before and after restoration, as shown in Figure 2(a), 2(b), 2(c), 2(d), 3( a), 3(b), 3(c).

a color recovery test

The images and color swatches enhanced by the contrast algorithm, the swatches with chromatic aberration are restored correctly.

b Multi-image test

The original image is characterized by blur, low contrast, and uneven color. After algorithm processing, the picture is clear, the color of the image is balanced, and the contrast is improved. Compared with the original image, the enhancement effect is remarkable.

As will be appreciated by those skilled in the art, the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions The apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

These computer program instructions can also be loaded on a computer or other programmable data processing device to cause a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process such that The instructions provide steps for implementing the functions specified in the flow or blocks of the flowcharts and/or the block or blocks of the block diagrams.

As mentioned above, the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand: The technical solutions described in the embodiments are modified, or some technical features thereof are equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (8)

1. An underwater image enhancement method based on red channel attenuation is characterized in that,

acquiring pixel values of a red channel, a green channel and a blue channel of an underwater image;

for each pixel value of the red channel, compensating through the pixel values of the green channel and the blue channel in the field of the pixel value to obtain an image after color compensation;

and performing color adjustment on the image after color compensation by using a white balance algorithm.

2. The red channel attenuation-based underwater image enhancement method according to claim 1, wherein the step of obtaining the pixel values of the red channel, the green channel, and the blue channel of the underwater image is further followed by the steps of:

and carrying out normalization processing on the pixel values.

3. The underwater image enhancement method based on red channel attenuation according to claim 1, characterized in that the compensation formula for the pixel values of the green channel and the blue channel in the pixel value field is as follows:

α+β＝1

in the formula I_r,com(x, y) represents the red channel compensated pixel value; i is_r(x,y)、I_g(x, y) and I_b(x, y) represent pixel values for the red channel, green channel, and blue channel, respectively, α and β are each a constant less than 1;

representing the normalized average of the green channel in the pixel value domain,

representing the normalized average of the blue channel in the pixel value domain.

4. The method of claim 1, wherein the step of compensating for the pixel values of the green channel and the blue channel in the pixel value field further comprises:

and carrying out inverse normalization and synthesizing the image after color compensation.

5. An underwater image enhancement system based on red channel fading, comprising:

the acquisition module is used for acquiring pixel values of a red channel, a green channel and a blue channel of the underwater image;

the compensation module is used for compensating each pixel value of the red channel through the pixel values of the green channel and the blue channel in the field of the pixel value to obtain an image after color compensation;

and the adjusting module is used for adjusting the color of the image after the color compensation by using a white balance algorithm.

6. The red channel attenuation-based underwater image enhancement system of claim 5, wherein the acquisition module further comprises:

and the normalization processing module is used for performing normalization processing on the pixel values.

7. The red channel attenuation-based underwater image enhancement method according to claim 5, wherein the compensation module comprises a calculation module for performing compensation calculation on each pixel value of the red channel by the following formula:

α+β＝1

in the formula I_r,com(x, y) represents the red channel compensated pixel value; i is_r(x,y)、I_g(x, y) and I_b(x, y) represent pixel values for the red channel, green channel, and blue channel, respectively, α and β are each a constant less than 1;

representing the normalized average of the green channel in the pixel value domain,

representing the normalized average of the blue channel in the pixel value domain.

8. The red channel attenuation-based underwater image enhancement system according to claim 1, wherein said compensation module includes an inverse normalization processing module for performing inverse normalization to synthesize a color compensated image.

Images