CN114723632A - Part abnormal exposure image correction method and device based on texture information - Google Patents

Abstract

The invention discloses a method and a device for correcting abnormal exposure images of parts based on texture information, relating to the field of computer vision; the overexposed area and the underexposed area in the abnormal exposure image can be corrected simultaneously. The method mainly comprises the following steps: acquiring a first image and an exposure value of the first image; obtaining texture integrity and a correction necessity index of the first image according to the edge feature of the first image and the frequency of gray values in a gray histogram of the first image, and correcting the first image when the correction necessity index is larger than a preset first threshold; obtaining a lower limit and an upper limit of an adjusting value according to the texture integrity of the first image, and obtaining an exposure value range; adjusting the exposure value of the first image to obtain a plurality of second images with different exposure values; and calculating the fusion weight of the second images, and fusing the plurality of second images according to the fusion weight to obtain the corrected first image. The specific application scenarios of the invention are as follows: and correcting the abnormally exposed image.

Description

A method and device for correcting abnormal exposure images of parts based on texture information

technical field

The present application relates to the field of computer vision, in particular to a method and device for correcting abnormal exposure images of parts based on texture information.

Background technique

In the process of shooting parts, due to the influence of light intensity and light source angle, the obtained part image will have abnormal exposure phenomenon. Abnormal exposure includes overexposure and underexposure. Overexposure or underexposure will cause the obtained part image to fail. The complete texture details of the part are presented; at the same time, there is reflection on the surface of the part, so that there are many reflective areas in the captured part image, but by reducing the exposure value during shooting to reduce the reflective area, there will be a lot of darkness in the captured part image. Therefore, it is necessary to correct the part image with abnormal exposure, so that the captured part image presents the complete texture details of the part.

In order to solve the above problems in the prior art, usually by changing the overall exposure of the image, the overall exposure of the image reaches a more appropriate exposure, and this method will further increase the exposure of the overexposed part of the image, or The exposure of the underexposed part in the image is further reduced, the overexposed part and the underexposed part in the image cannot be corrected at the same time, and a better abnormal exposure image correction effect cannot be achieved.

SUMMARY OF THE INVENTION

In view of the above technical problems, the present invention provides a method and device for correcting abnormal exposure images of parts based on texture information.

In the first aspect, this paper proposes a method for correcting abnormal exposure images of parts based on texture information, including:

Acquire a first image and an exposure value of the first image, where the first image refers to an abnormally exposed image to be corrected.

According to the edge feature of the first image and the frequency of the gray value in the gray histogram of the first image, the texture integrity of the first image is obtained, and the necessary correction is obtained according to the texture integrity of the first image. The first image is corrected when the correction necessity index is greater than a preset first threshold.

The lower limit of the adjustment value and the upper limit of the adjustment value are obtained according to the texture integrity of the first image, and the range of exposure values is obtained according to the lower limit of the adjustment value, the upper limit of the adjustment value and the exposure value of the first image.

The exposure value of the first image is adjusted to obtain a plurality of second images with different exposure values, and the exposure values of the second images are within the exposure value range.

The texture integrity of each second image is obtained according to the method of obtaining the texture integrity of the first image, and the fusion weight of each second image is obtained according to the texture integrity of each second image.

The obtained fusion weights of all the second images are fused and superposed to obtain the pixel values of the first image, and the correction of the first image is completed.

Further, in the method for correcting abnormal exposure images of parts based on texture information, the texture integrity of the first image/second image is determined by the texture integrity of the bright area and the texture of the dark area of the first image/second image. The completeness is obtained, and the specific methods include:

Obtain a grayscale image of the first image/second image, and obtain a bright area image and a dark area image according to the grayscale image, the bright area image includes the bright area in the grayscale image, and the dark area image The area image contains dark areas in the grayscale image.

According to the texture information of the bright area image, the texture integrity of the bright area is obtained.

According to the texture information of the dark area image, the texture integrity of the dark area is obtained.

The texture integrity is obtained according to the texture integrity of the light area and the texture integrity of the dark area.

Further, in the method for correcting abnormal exposure images of parts based on texture information, the acquisition process of the texture integrity includes:

According to the texture features of the bright area image/dark area image, the texture richness and texture uniformity of the bright area image/dark area image are obtained.

Multiply the texture richness and the texture uniformity to obtain the texture integrity of the light area image/dark area image.

Further, in the method for correcting abnormal exposure images of parts based on texture information, the acquisition process of the texture richness includes:

In the bright area image/dark area image, the maximum value of the gray value in all pixels is subtracted from the minimum value of the gray value to obtain the width of the gray value.

According to the variance of the number of occurrences of different gray values in the gray histogram of the bright area image/dark area image, the degree of uniformity of the histogram is obtained.

Multiply the gray value width by the histogram uniformity to obtain texture richness.

Further, the method for correcting abnormal exposure images of parts based on texture information, and the method for obtaining the degree of texture uniformity, include:

Perform edge detection on the bright area image/dark area image to obtain the edge feature points of the bright area image/dark area image.

The number of edge feature points in the eight neighborhood pixels of edge feature points in the bright area image/dark area image, and the number of edge feature points in a total of nine pixel points of its own pixel point is taken as the frequency of edge feature points.

According to the frequency of the edge feature points of the line in the bright area image/dark area image, and the line distance feature of the edge feature point of the line, the uniformity of the line distribution of the edge feature points is obtained.

According to the frequency of the column edge feature points in the bright area image/dark area image, and the column distance feature of the column edge feature points, the uniformity of the column distribution of the edge feature points is obtained.

The uniformity of the texture is obtained by multiplying the uniformity of the row distribution of the edge feature points by the uniformity of the column distribution.

Further, in the method for correcting abnormal exposure images of parts based on texture information, the row distance feature refers to the distance between the edge feature point and other adjacent edge feature points in the same row, or the edge feature point to the bright area. The distance to the border of the image/dark area image.

The column distance feature refers to the distance between the edge feature point and other adjacent edge feature points in the same column, or the distance between the edge feature point and the boundary of the bright area image/dark area image.

Further, in the method for correcting abnormal exposure images of parts based on texture information, the obtained fusion weights of all second images are fused and superposed to obtain pixel values of the first image, and the correction of the first image is completed, include:

The fusion weight includes a dark area fusion weight and a bright area fusion weight.

Using the dark area fusion weight, weighted fusion is performed on the dark area in the grayscale image of the second image and the corresponding area in the second image.

Using the bright area fusion weight, weighted fusion is performed on the bright area in the grayscale image of the second image and the corresponding area in the second image.

In the second aspect, the present invention provides a device for correcting abnormal exposure images of parts based on texture information, including:

The image and exposure value acquisition module is configured to acquire a first image and an exposure value of the first image, where the first image refers to an abnormally exposed image to be corrected.

an image and exposure value acquisition module, configured to acquire a first image and an exposure value of the first image, where the first image refers to an abnormally exposed image to be corrected;

a first calculation module, configured to obtain the texture integrity of the first image according to the edge feature of the first image and the frequency of the gray value in the gray histogram of the first image, and according to the first image Obtaining a correction necessity index based on the texture integrity of the first image, and correcting the first image when the correction necessity index is greater than a preset first threshold;

The second calculation module is configured to obtain the lower limit of the adjustment value and the upper limit of the adjustment value according to the texture integrity of the first image, and obtain the lower limit of the adjustment value, the upper limit of the adjustment value and the exposure value of the first image according to the lower limit of the adjustment value, the upper limit of the adjustment value and the exposure value of the first image. exposure value range;

an image generation module, configured to adjust the exposure value of the first image to obtain a plurality of second images with different exposure values, and the exposure values of the second images are within the exposure value range;

A third computing module, configured to obtain the texture integrity of each of the second images according to the method of obtaining the texture integrity of the first image, and to obtain the texture integrity of each of the second images according to the texture integrity of each of the second images. the fusion weight of the second image;

The image correction module is used for fusing and superposing the obtained fusion weights of all the second images to obtain the pixel values of the first image, so as to complete the correction of the first image.

In view of the above technical problems, the present invention provides a method and device for correcting abnormal exposure images of parts based on texture information, which mainly include:

Obtain the first image and the exposure value of the first image, where the first image refers to the abnormally exposed image to be corrected; obtain the first image according to the edge feature of the first image and the frequency of the gray value in the gray histogram of the first image The texture integrity of the first image is obtained, and the correction necessity index is obtained according to the texture integrity of the first image. When the correction necessity index is greater than the preset first threshold, the first image is corrected; the adjustment value is obtained according to the texture integrity of the first image. The lower limit and the upper limit of the adjustment value are obtained, and the exposure value range is obtained according to the lower limit of the adjustment value, the upper limit of the adjustment value and the exposure value of the first image; the exposure value of the first image is adjusted to obtain a plurality of second images with different exposure values. The exposure value of the two images is within the exposure value range; the texture integrity of each second image is obtained according to the method of obtaining the texture integrity of the first image, and the texture integrity of each second image is obtained according to the texture integrity of each second image. The fusion weight of the image; the fusion weight of all the obtained second images is fused and superimposed to obtain the pixel value of the first image, and the correction of the first image is completed.

Compared with the prior art, the present invention has the beneficial effects of: using the texture information in the collected part images to determine whether there is abnormal exposure, it is possible to avoid unnecessary processing of images that do not need to be corrected; Exposure value range, weighted fusion of overexposed areas and underexposed areas in multiple images under different exposure values within the exposure value range, can correct the overexposed areas and underexposed areas in abnormally exposed images at the same time, It makes the image correction process more targeted and accurate.

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

FIG. 1 is a schematic flowchart of a method for correcting abnormal exposure images of parts based on texture information according to Embodiment 1 of the present invention.

FIG. 2 is a schematic flowchart of an image correction device for abnormal exposure of parts based on texture information according to Embodiment 2 of the present invention.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, but not to limit 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.

In the following description, for the purpose of illustration rather than limitation, specific details such as a specific system structure and technology are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

The terms "first" and "second" are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined with "first" and "second" may explicitly or implicitly include one or more of the features; in the description of this embodiment, unless otherwise specified, the meaning of "multiple" are two or more.

Example 1

Embodiment 1 of the present invention provides a method for correcting abnormal exposure images of parts based on texture information, as shown in FIG. 1 , including:

101. Acquire a first image and an exposure value of the first image, where the first image refers to an abnormally exposed image to be corrected.

The abnormal exposure image to be corrected, that is, the first image, is obtained by using an image acquisition device. The first image is in RGB format. RGB is a color standard. RGB is the color representing the three channels of red, green and blue.

102. Obtain the texture integrity of the first image according to the edge features of the first image and the frequency of the gray values in the gray histogram of the first image, and obtain the correction necessity index according to the texture integrity of the first image, when When the correction necessity index is greater than the preset first threshold, the first image is corrected.

In this embodiment, 102 specifically includes 1021 , 1022 and 1023 .

1021. Obtain a grayscale image of the first image, and obtain a bright area image and a dark area image according to the grayscale image.

Specifically, in order to segment the bright area and the dark area in the grayscale picture of the first image, the segmentation threshold range of the bright area and the segmentation threshold range of the dark area are given in this embodiment, wherein the grayscale segmentation threshold range of the bright area is is [204, 255], and the gray-scale segmentation threshold range of dark areas is [0, 51].

It should be noted that, in the grayscale image of the first image, the pixels whose grayscale values are in the threshold range [0, 51] are retained, and the pixels whose grayscale values are in the threshold range (51, 255) are retained. Set to 0 to get a dark area image.

Specifically, in the grayscale image of the first image, the pixels whose grayscale values are in the threshold range [204, 255] are reserved, and the pixels whose grayscale values are in the threshold range [0, 204) are set as 0, get the bright area image. The bright area image includes the bright area in the grayscale image of the first image, and the dark area image includes the dark area in the grayscale image of the first image.

Specifically, in this embodiment, the brightness information in the first image is obtained through the grayscale value of the image, and the bright area in the grayscale image of the first image corresponds to the overexposed area in the first image; the grayscale image of the first image corresponds to the overexposed area in the first image; The dark areas in correspond to the underexposed areas in the first image.

1022. Obtain the texture integrity of the bright region according to the texture information of the bright region image; and obtain the texture integrity of the dark region according to the texture information of the dark region image.

It should be noted that the acquisition method of the texture integrity of the dark area in this embodiment is the same as the acquisition method of the texture integrity of the bright area, but the target image is different. The calculation method of the texture integrity specifically includes 10221, 10222 and 10223, the texture integrity can reflect the completeness of the texture in the image, and the texture integrity mainly includes the richness of the texture and the uniformity of the texture.

10221. Obtain the texture richness of the bright area image/dark area image.

Specifically, in this embodiment, the bright area image/dark area image is a bright area image or a dark area image. Due to the influence of light, part of the texture in the bright area or the dark area is lost, resulting in uneven texture distribution, so it is necessary to extract the texture uniformity.

First, in the bright area image/dark area image, the maximum value of the gray value in all pixels is subtracted from the minimum value of the gray value to obtain the width of the gray value.

It should be noted that the calculation methods for the texture richness of the bright area image and the dark area image are the same, and the method for obtaining the texture richness is specifically described below by taking the bright area image as an example.

Specifically, the maximum value of the gray value in the bright area image is subtracted from the minimum value of the gray value, and the width of the gray value of the bright area image is obtained as wl. The gray value width wa of the dark area image is obtained by subtracting the maximum value of the gray value and the minimum value of the gray value in the dark area image.

Secondly, according to the variance of the number of occurrences of different gray values in the gray histogram of the bright area image/dark area image, the uniformity of the histogram is obtained, and the richness of texture is mainly reflected in the histogram. The richer the degree information, the richer the texture features. Multiply the gray value width by the histogram uniformity to get the texture richness.

其中p(h_j)为亮区域图像的灰度直方图中第j个灰度值h_j对应的频率值，wl为亮区域图像的灰度值取值宽度。计算该亮区域图像的灰度直方图的频率的方差

因而亮区域的灰度直方图均匀程度为

Specifically, the grayscale histogram of the bright area image is obtained, and the frequency mean of the histogram is calculated

where p(h _j ) is the frequency value corresponding to the jth gray value h _j in the gray histogram of the bright area image, and wl is the width of the gray value of the bright area image. Calculate the variance of the frequency of the grayscale histogram of the bright area image

Therefore, the uniformity of the gray histogram of the bright area is

It should be noted that, according to the uniformity degree of the grayscale histogram of the grayscale image in the bright area, the uniformity degree jh2 of the grayscale histogram of the grayscale image in the dark area can be obtained by the same acquisition method.

Specifically, the texture integrity of the image in the bright area is ff1=wl*jh1, where wl is the gray value width of the image in the bright area, and jh1 is the uniformity of the gray histogram of the image in the bright area; meanwhile, the texture richness of the image in the dark area is ff2=wa*jh2, where wa is the gray value width of the dark area image, and jh2 is the uniformity of the gray histogram of the dark area image.

10222. Obtain the texture uniformity of the bright area image/dark area image.

Specifically, the uniformity of the texture is mainly reflected by the distance information between the texture pixels and the texture frequency difference information. The distance information of the texture is reflected by the distance size and distance deviation. The larger the texel distance is, the more uneven the texture distribution is. The larger the texel distance deviation of each row or column, the more uneven the texture distribution of the row or column. The greater the density difference of the pixel texture of each row or column, the more uneven the texture distribution of the row or column.

It should be noted that the calculation methods for the texture uniformity of the bright area image and the dark area image are the same, and the following takes the bright area image as an example to specifically describe the method for obtaining the texture uniformity.

First, edge detection is performed on the bright area image to obtain edge feature points in the bright area image. In this embodiment, the sober operator is used to process the edge feature points in the bright area image.

Then, the number of edge feature points in the eight neighborhood pixels of edge feature points in the bright area image and the number of edge feature points in a total of nine pixels of its own pixel points is used as the frequency of edge feature points; according to the frequency of edge feature points and the edge of the line The row distance feature of the feature points is used to obtain the row distribution uniformity of the edge feature points; the column distribution uniformity of the edge feature points is obtained according to the frequency of the edge feature points and the column distance feature of the column edge feature points.

Specifically, obtain the pixel distance between every two adjacent edge feature points: Assuming that in the kth row of the bright area image, there are two adjacent edge feature points at (k, i) and (k, j), this The distance between two edge feature points is d1 _kj =ji.

It should be noted that when there are no other edge feature points between the edge feature point at (k, l) in the bright area image and the image boundary, the pixel distance between the edge features is: the closest point to the image boundary distance, at this time d1 _kl =min(l, Ml), where M is the number of columns of the image.

Further, the distance sequence between the edge feature points in the kth row in the bright area image can be obtained; by using the frequency of the edge feature points, the sequence composed of the frequency of the edge feature points in the kth row in the bright area image can be obtained, and the bright area image can be further calculated. The mean distance of the line edge feature points in the area image and the distance deviation of the edge feature points.

亮区域图像中第k行的边缘特征点间的距离偏差为

其中d1_kh为亮区域图像中第行的第h个边缘特征点的距离值，此处r边缘特征点之间的距离序列中边缘特征点的距离值的个数。Specifically, the average distance between the edge feature points in the k-th row in the bright area image is

The distance deviation between the edge feature points of the kth row in the bright area image is

Among them, d1 _kh is the distance value of the h-th edge feature point in the bright area image, where r is the distance between edge feature points in the distance sequence between edge feature points. The number of distance values.

其中M为亮区域图像中的列数，f1_kg为亮区域第k行第g列位置处边缘特征的频率值，

为第k行像素的频率均值。It should be noted that the frequency deviation of the edge feature point of the kth row in the bright area image is

where M is the number of columns in the bright area image, f1 _kg is the frequency value of the edge feature at the position of the k-th row and the g-th column of the bright area,

is the frequency mean of the pixels in the kth row.

其中σd1_k为亮区域图像中第k行边缘特征点的距离偏差，σf1_k为亮区域图像中第k行边缘特征的频率偏差。

为亮区域图像中第k行边缘特征点的距离均值。Secondly, the distribution uniformity of the edge feature points of the kth row in the bright area image

where σd1 _k is the distance deviation of the edge feature points in the kth row in the bright area image, and σf1 _k is the frequency deviation of the kth row edge feature in the bright area image.

is the mean distance of edge feature points in the kth row in the bright area image.

此处Jy1_q为亮区域第q行边缘特征分布均匀程度，N为频率图像的行数，进一步可以得到亮区域图像中的列像素的边缘特征分布均匀程度均值

亮区域图像的边缘分布均匀程度为

最后将边缘特征点的行分布均匀程度与列分布均匀程度相乘，获得亮区域图像的纹理均匀程度Jy2。Further, the average distribution uniformity of the edge features of the row pixels in the bright area image is

Here Jy1 _q is the uniformity of the edge feature distribution of the qth row in the bright area, and N is the number of rows in the frequency image. Further, the mean value of the uniformity of the edge feature distribution of the column pixels in the bright area image can be obtained.

The uniformity of the edge distribution of the bright area image is

Finally, the uniformity of the row distribution of the edge feature points is multiplied by the uniformity of the column distribution to obtain the texture uniformity of the bright area image Jy2.

Further, using the same acquisition method as the image texture uniformity degree of the bright area, the texture uniformity degree Jy2 of the dark area can be obtained.

10223. Multiply the texture richness and texture uniformity to obtain the texture integrity of the bright area image/dark area image.

The texture integrity of the bright area is Wz1=ff1*Jy1, where ff1 is the texture richness of the bright area image, and Jy1 is the texture uniformity of the bright area image; the texture integrity of the dark area is Wz2=ff2*Jy2, where ff2 is The texture richness of the dark area image, Jy2 is the texture uniformity of the dark area image.

1023. Obtain the texture integrity of the first image according to the texture integrity of the bright area and the texture integrity of the dark area.

Specifically, the texture integrity of the bright area and the texture integrity of the dark area are added to obtain the texture integrity of the first image, and the texture integrity can reflect the texture information of the first image, that is, the abnormally exposed image.

It should be noted that the reciprocal of the texture integrity of the first image is the correction necessity index, and the correction necessity index can reflect the necessity of correcting the first image, and it is determined whether the correction necessity index is greater than the preset first threshold. If the determination result is yes, the first image needs to be corrected, and if the determination result is no, it means that the image does not have abnormal exposure, and subsequent corrections are not required.

103. Obtain the lower limit of the adjustment value and the upper limit of the adjustment value according to the texture integrity of the first image, and obtain the exposure value range according to the lower limit of the adjustment value, the upper limit of the adjustment value and the exposure value of the first image.

调整值上限

其中Wz1为亮区域的纹理完整性，Wz2为暗区域的纹理完整性，

为常量参数可根据实施者具体需要进行选取。Specifically, α is the lower limit of the adjustment value, β is the upper limit of the adjustment value, α is related to the texture information of the overexposed area in the first image, and β is related to the texture information of the underexposed area in the first image; when the texture information in the bright area is missing When it is more serious, the exposure value of the bright area should be reduced; when the texture information in the dark area is more serious, the exposure value of the dark area should be increased. In this embodiment, the lower limit of the adjustment value

Adjustment value cap

where Wz1 is the texture integrity of the bright area, Wz2 is the texture integrity of the dark area,

The constant parameters can be selected according to the specific needs of the implementer.

Further, the exposure value range can be obtained, [Bg-α, Bg+β, where Bg is the exposure value of the abnormally exposed image, that is, the first image.

104. Adjust the exposure value of the first image to obtain multiple second images with different exposure values within the exposure value range.

Specifically, according to the exposure value range obtained in 103, multiple second pictures with different exposure values can be obtained on the basis of the first image. The difference between the obtained second image and the first image is that the exposure value is different, and all the second images The exposure values of the images are all within the exposure value range.

105. Obtain the texture integrity of each second image according to the method of acquiring the texture integrity of the first image, and obtain the fusion weight of each second image according to the texture integrity of each second image.

Further, by using the method for acquiring the texture integrity of the image in this embodiment 102, the texture integrity of the bright area image and the texture integrity of the dark area image corresponding to each second image can be obtained.

第a张第二图像对于欠曝区域的融合权重

其中v表示第二图像的总数。It should be noted that the bright area in the grayscale image of the first image corresponds to the overexposed area in the first image, and the dark area in the grayscale image of the first image corresponds to the underexposed area in the first image, then the ath The fusion weight of the second image for the overexposed area is:

The fusion weight of the second image a for the underexposed area

where v represents the total number of second images.

106. Perform fusion and superposition on the obtained fusion weights of all the second images to obtain pixel values of the first image, and complete the correction of the first image.

Specifically, according to the fusion weight of the second image, the overexposed area and the underexposed area in the first image are fused, the normal area in the first image remains unchanged, and the obtained image is the corrected first image .

其中

表示第一图像的灰度图像中亮区域的像素点，在第a张第二图像中对应的像素点的像素值；第一图像中的欠曝区域中像素值的修正方式为

其中

表示第一图像的灰度图像中的暗区域的像素点，在第a张第二图像中对应的像素点的像素值；Xs¹为第一图像中过曝区域经过修正后的像素值，Xs²为第一图像中欠曝区域经过修正后的像素值。It should be noted that the correction method of the pixel value in the overexposed area in the first image is as follows:

in

Indicates the pixel value of the pixel point in the bright area in the grayscale image of the first image, and the pixel value of the corresponding pixel point in the second image a; the correction method of the pixel value in the underexposed area in the first image is as follows

in

Indicates the pixel point of the dark area in the grayscale image of the first image, the pixel value of the corresponding pixel point in the second image a; Xs ¹ is the corrected pixel value of the overexposed area in the first image, Xs ² is the corrected pixel value of the underexposed area in the first image.

Compared with the prior art, the present invention has the beneficial effects of: using the texture information in the collected part images to determine whether there is abnormal exposure, it is possible to avoid unnecessary processing of images that do not need to be corrected; Exposure value range, weighted fusion of overexposed areas and underexposed areas in multiple images under different exposure values within the exposure value range, can correct the overexposed areas and underexposed areas in abnormally exposed images at the same time, It makes the image correction process more targeted and accurate.

Example 2

Embodiment 2 of the present invention provides a method and device for correcting abnormal exposure images of parts based on texture information, as shown in FIG. 2 , including:

The image and exposure value acquisition module 21 is configured to acquire a first image and an exposure value of the first image, where the first image refers to an abnormally exposed image to be corrected.

The first calculation module 22 is configured to obtain the texture integrity of the first image according to the edge features of the first image and the frequency of the gray value in the gray histogram of the first image, and obtain the texture integrity of the first image according to the texture integrity of the first image. Correcting the necessity index, and correcting the first image when the correction necessity index is greater than the preset first threshold.

The second calculation module 23 is configured to obtain the lower limit of the adjustment value and the upper limit of the adjustment value according to the texture integrity of the first image, and obtain the exposure value range according to the lower limit of the adjustment value, the upper limit of the adjustment value and the exposure value of the first image.

The image generation module 24 is configured to adjust the exposure value of the first image to obtain a plurality of second images with different exposure values, and the exposure values of the second images are within the exposure value range.

The third calculation module 25 is configured to obtain the texture integrity of each second image according to the method of obtaining the texture integrity of the first image, and obtain the fusion of each second image according to the texture integrity of each second image Weights.

The image correction module 26 is configured to fuse and superimpose the obtained fusion weights of all the second images to obtain the pixel values of the first image, and complete the correction of the first image.

To sum up, compared with the prior art, the beneficial effects of the present invention are: using the texture information in the collected part images to determine whether there is abnormal exposure, it is possible to avoid unnecessary processing of images that do not need to be corrected; The exposure value range is obtained from the texture information of the image, and the over-exposed and under-exposed areas in multiple images under different exposure values within the exposure value range are weighted and fused, and the over-exposed areas and under-exposed areas in abnormally exposed images can be fused. Areas are corrected at the same time, making the image correction process more targeted and accurate.

Words such as "including", "comprising", "having", etc. referred to herein are open-ended words meaning "including but not limited to" and are used interchangeably therewith. As used herein, the words "or" and "and" refer to and are used interchangeably with the word "and/or" unless the context clearly dictates otherwise. As used herein, the word "such as" refers to and is used interchangeably with the phrase "such as but not limited to".

It should also be pointed out that in the method and system of the present invention, each component or each step can be decomposed and/or recombined. These disaggregations and/or recombinations should be considered equivalents of the present disclosure.

The above-mentioned embodiments are only examples for clear description, and do not limit the protection scope of the present invention. For those of ordinary skill in the art, changes or modifications in other different forms can also be made on the basis of the above description, and it is not necessary and impossible to list all the implementations here. All the same or similar designs as the present invention fall within the protection scope of the present invention.

Claims (8)

1. a method for correcting abnormal exposure images of parts based on texture information, is characterized in that, comprising: acquiring a first image and an exposure value of the first image, where the first image refers to an abnormally exposed image to be corrected; According to the edge feature of the first image and the frequency of the gray value in the gray histogram of the first image, the texture integrity of the first image is obtained, and the necessary correction is obtained according to the texture integrity of the first image. a necessity index, when the correction necessity index is greater than a preset first threshold, the first image is corrected; Obtain the lower limit of the adjustment value and the upper limit of the adjustment value according to the texture integrity of the first image, and obtain the range of exposure values according to the lower limit of the adjustment value, the upper limit of the adjustment value and the exposure value of the first image; Adjusting the exposure value of the first image to obtain a plurality of second images with different exposure values, where the exposure values of the second images are within the exposure value range; Obtain the texture integrity of each second image according to the method of obtaining the texture integrity of the first image, and obtain the fusion weight of each second image according to the texture integrity of each second image; The obtained fusion weights of all the second images are fused and superposed to obtain the pixel values of the first image, and the correction of the first image is completed. 2 . The method for correcting abnormal exposure images of parts based on texture information according to claim 1 , wherein the texture integrity of the first image/second image is determined by the bright area of the first image/second image. 3 . The texture integrity and the texture integrity of the dark area are obtained, and the specific methods include: Obtain a grayscale image of the first image/second image, and obtain a bright area image and a dark area image according to the grayscale image, the bright area image includes the bright area in the grayscale image, and the dark area image the area image contains dark areas in the grayscale image; According to the texture information of the bright area image, obtain the texture integrity of the bright area; According to the texture information of the dark area image, obtain the texture integrity of the dark area; The texture integrity is obtained according to the texture integrity of the light area and the texture integrity of the dark area. 3. The method for correcting abnormal exposure images of parts based on texture information according to claim 2, wherein the acquisition process of the texture integrity comprises: Obtain the texture richness and texture uniformity of the bright area image/dark area image according to the texture characteristics of the bright area image/dark area image; Multiply the texture richness and the texture uniformity to obtain the texture integrity of the light area image/dark area image. 4. The method for correcting abnormal exposure images of parts based on texture information according to claim 3, wherein the acquisition process of the texture richness comprises: In the bright area image/dark area image, the maximum value of the gray value in all pixels is subtracted from the minimum value of the gray value to obtain the width of the gray value; According to the variance of the number of occurrences of different gray values in the gray histogram of the bright area image/dark area image, the uniformity of the histogram is obtained; Multiply the gray value width by the histogram uniformity to obtain texture richness. 5. The method for correcting abnormal exposure images of parts based on texture information according to claim 3, wherein the method for obtaining the uniformity of the texture comprises: Perform edge detection on the bright area image/dark area image to obtain the edge feature points of the bright area image/dark area image; The number of edge feature points in the eight neighborhood pixel points of the edge feature points in the bright area image/dark area image, and the number of edge feature points in a total of nine pixel points of its own pixel points are used as the frequency of edge feature points; According to the frequency of the edge feature points of the line in the bright area image/dark area image, and the line distance feature of the edge feature point of the line, the uniformity of the line distribution of the edge feature points is obtained; According to the frequency of the edge feature points of the column in the bright area image/dark area image, and the column distance feature of the edge feature point of the column, the uniformity of the column distribution of the edge feature points is obtained; The uniformity of the texture is obtained by multiplying the uniformity of the row distribution of the edge feature points by the uniformity of the column distribution. 6 . The method for correcting abnormal exposure images of parts based on texture information according to claim 5 , wherein the row distance feature refers to the distance between an edge feature point and other adjacent edge feature points in the same row. 7 . , or the distance from the edge feature point to the boundary of the bright area image/dark area image; The column distance feature refers to the distance between the edge feature point and other adjacent edge feature points in the same column, or the distance between the edge feature point and the boundary of the bright area image/dark area image. 7 . The method for correcting abnormal exposure images of parts based on texture information according to claim 1 , wherein the fusion weights of all the second images obtained are fused and superposed to obtain the pixel values of the first image, and the comparison is completed. 8 . The correction of the first image includes: The fusion weight includes a dark area fusion weight and a bright area fusion weight; Using the dark area fusion weight, weighted fusion is performed on the dark area in the grayscale image of the second image and the corresponding area in the second image; Using the bright area fusion weight, weighted fusion is performed on the bright area in the grayscale image of the second image and the corresponding area in the second image. 8. A device for correcting abnormal exposure images of parts based on texture information, comprising: an image and exposure value acquisition module, configured to acquire a first image and an exposure value of the first image, where the first image refers to an abnormally exposed image to be corrected; The first calculation module is configured to obtain the texture integrity of the first image according to the edge feature of the first image and the frequency of the gray value in the gray histogram of the first image, and according to the first image Obtaining a correction necessity index based on the texture integrity of the first image, and correcting the first image when the correction necessity index is greater than a preset first threshold; The second calculation module is configured to obtain the lower limit of the adjustment value and the upper limit of the adjustment value according to the texture integrity of the first image, and obtain the lower limit of the adjustment value, the upper limit of the adjustment value and the exposure value of the first image according to the lower limit of the adjustment value, the upper limit of the adjustment value and the exposure value of the first image. exposure value range; an image generation module, configured to adjust the exposure value of the first image to obtain a plurality of second images with different exposure values, and the exposure values of the second images are within the exposure value range; a third computing module, configured to obtain the texture integrity of each of the second images according to the method of obtaining the texture integrity of the first image, and to obtain the texture integrity of each of the second images according to the texture integrity of each of the second images the fusion weight of the second image; The image correction module is used for fusing and superposing the obtained fusion weights of all the second images to obtain the pixel values of the first image, so as to complete the correction of the first image.

Images