WO2020168807A1 - 图像亮度的调节方法、装置、计算机设备和存储介质 - Google Patents
图像亮度的调节方法、装置、计算机设备和存储介质 Download PDFInfo
- Publication number
- WO2020168807A1 WO2020168807A1 PCT/CN2019/126817 CN2019126817W WO2020168807A1 WO 2020168807 A1 WO2020168807 A1 WO 2020168807A1 CN 2019126817 W CN2019126817 W CN 2019126817W WO 2020168807 A1 WO2020168807 A1 WO 2020168807A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- brightness
- difference
- target image
- reference image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
Definitions
- This application relates to the field of image processing technology, for example, to an image brightness adjustment method, an image brightness adjustment device, computer equipment, and computer-readable storage media.
- the brightness of an image it is sometimes necessary to adjust the brightness of an image so that the brightness of this image tends to be consistent with the brightness of the reference image. For example, after taking an image of an object through a multi-lens camera, since the position of the object taken by each camera is different, and it is affected by the light, the brightness of the image taken by each camera is generally different. Therefore, the brightness of the image needs to be adjusted to make The brightness of each image tends to be consistent to improve the overall imaging effect of the image.
- the traditional technology adjusts the brightness of the target image so that the brightness area of the target image is consistent with the brightness area of the reference image, it is easy to cause excessive image information loss and low image contrast after the brightness adjustment of the target image.
- the traditional technology has low robustness to adjust the image brightness.
- This application provides an image brightness adjustment method, an image brightness adjustment device, a computer device, and a computer-readable storage medium, so as to solve the technical problem of low robustness of traditional technology for adjusting image brightness.
- a method for adjusting image brightness including the steps:
- the brightness of the target image is adjusted based on the reference image through the brightness adjustment model.
- a device for adjusting image brightness includes:
- An obtaining module configured to obtain the content difference between the reference image and the target image, and obtain the brightness difference between the reference image and the target image;
- a determining module configured to determine an image difference type between the reference image and the target image according to the content difference degree and the brightness difference degree;
- An extraction module for extracting a brightness adjustment model that is compatible with the image difference type from a plurality of brightness adjustment models
- the adjustment module is configured to adjust the brightness of the target image based on the reference image through the brightness adjustment model.
- a computer device includes a processor and a memory, the memory stores a computer program, and the processor implements the following steps when the processor executes the computer program:
- Acquiring the content difference degree between the reference image and the target image acquiring the brightness difference degree between the reference image and the target image; determining the image difference type between the reference image and the target image according to the content difference degree and the brightness difference degree; A brightness adjustment model suitable for the image difference type is extracted from a plurality of brightness adjustment models; the brightness adjustment model is used to adjust the brightness of the target image based on the reference image.
- a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:
- Acquiring the content difference degree between the reference image and the target image acquiring the brightness difference degree between the reference image and the target image; determining the image difference type between the reference image and the target image according to the content difference degree and the brightness difference degree; A brightness adjustment model suitable for the image difference type is extracted from a plurality of brightness adjustment models; the brightness adjustment model is used to adjust the brightness of the target image based on the reference image.
- the above-mentioned image brightness adjustment method, device, computer equipment and storage medium obtain the content difference and brightness difference between the reference image and the target image, and then determine the image between the reference image and the target image according to the content difference and the brightness difference According to the difference type, a brightness adjustment model suitable for the image difference type is selected from a plurality of brightness adjustment models according to the image difference type, and the brightness adjustment of the target image is performed based on the reference image through the brightness adjustment model.
- This solution can determine the type of image difference based on the degree of content difference and brightness difference between images, and then adaptively select different brightness adjustment models to adjust the brightness of the image in combination with the type of image difference, and use the image difference type compatible
- the brightness adjustment model adjusts the image brightness, avoiding the problem of low image brightness adjustment robustness caused by using a single brightness adjustment algorithm to adjust the brightness of the reference image.
- FIG. 1 is an application scene diagram of a method for adjusting image brightness in an embodiment
- Figure 2 is a schematic diagram of a reference image and a target image in an embodiment
- Figure 3 is an effect diagram of an image brightness adjustment method in an embodiment
- Figure 4 is a schematic diagram of a reference image and a target image in another embodiment
- Figure 5 is an effect diagram of a method for adjusting image brightness in another embodiment
- FIG. 6 is a schematic flowchart of a method for adjusting image brightness in an embodiment
- Fig. 7 is a schematic diagram of image compression in an embodiment
- FIG. 8 is a schematic diagram of an effect of adjusting the brightness of a target image through a linear transformation model in an embodiment
- FIG. 9 is a schematic diagram of the principle of gray scale transformation of histogram matching in an embodiment
- FIG. 10 is a schematic diagram of the effect of adjusting the brightness of the target image through the histogram matching model in an embodiment
- FIG. 11 is a structural block diagram of a device for adjusting image brightness in an embodiment
- Fig. 12 is an internal structure diagram of a computer device in an embodiment.
- first ⁇ second ⁇ third involved in the embodiments of the present application only distinguishes similar objects, and does not represent a specific order for objects. Understandably, “first ⁇ second ⁇ “Third” can be interchanged in specific order or precedence when permitted. It should be understood that the objects distinguished by “first ⁇ second ⁇ third” can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.
- FIG. 1 is an application scenario diagram of the method for adjusting image brightness in an embodiment, which can be used by image capturing devices such as binocular cameras.
- the binocular camera can transmit the captured images to the terminal 100 with image processing capabilities, and the terminal 100 can be used to adjust the brightness of the collected images so that the brightness of the images captured by the binocular camera tends to Yu unanimous.
- the terminal 100 may include, but is not limited to, devices such as a personal computer, a notebook computer, and a tablet computer.
- the binocular camera may include a first camera 210 and a second camera 220.
- the first camera 210 and the second camera 220 generally photograph objects in the target area at different locations, and the target area includes object A. , Object B and object C, and because the positions of the images captured by the first camera 210 and the second camera 220 are different, the positions of the object A, object B, and object C in the images captured by the first camera 210 and the second camera 220 are also Different, and the position of the first camera 210 and the second camera 220 capturing images will also cause the two cameras to be affected by the light of the shooting environment to different degrees, so the images captured by the two cameras will be different in content and brightness. Make a certain difference.
- the terminal 100 can adjust the brightness of the images captured by the two cameras, so that the brightness of the images captured by the two cameras tends to be consistent.
- the image is a reference image
- the image captured by the second camera 220 is a target image. Then, the terminal 100 may use the reference image as a reference to adjust the brightness of the target image so that the brightness of the target image tends to be consistent with the reference image.
- the traditional technology When implementing the brightness adjustment method provided by the traditional technology, the applicant of this application found that the traditional technology usually adopts a single brightness adjustment algorithm to adjust the brightness between multiple images, that is to say, the traditional technology is actually not based on each image.
- the traditional technology is actually not based on each image.
- Features to adjust the brightness of the image but usually use the same brightness adjustment algorithm to adjust the brightness of each image, which often causes excessive image information loss and low image contrast after the brightness adjustment of the target image. happensing.
- Figure 2 is a schematic diagram of a reference image and a target image in an embodiment.
- image 201 is the reference image and image 202 is the target image.
- Traditional techniques generally adjust the brightness of the image 202 through linear transformation.
- Figure 3 is an effect diagram of the image brightness adjustment method in an embodiment.
- Image 301 is the image obtained after linear transformation of image 202. It can be seen that the image contrast of image 301 becomes lower. In this case, if the linear transformation is used, the image contrast will be reduced and the image quality will not be good.
- the brightness of the image 202 is adjusted by the histogram matching method, the adjustment result will be the image 302 shown in FIG. 3
- the image 302 shows that in this case, adjusting the brightness of the image 202 by means of histogram matching has a better effect than adjusting the brightness by means of linear transformation.
- FIG. 4 is a schematic diagram of the reference image and the target image in another embodiment, where the image 401 corresponds to the reference image, and the image 402 corresponds to the target image. If the histogram matching is used To adjust the brightness of the image 402 in a way, it will produce unnatural regions and textures.
- the adjustment result of the image 402 is the image 502 shown in FIG. 5, which is the effect of the image brightness adjustment method in another embodiment.
- the terminal 100 can determine the image difference type based on the content difference and the brightness difference between the images, and then adaptively select different brightness adjustment models to adjust the brightness of the image in combination with the image difference type. Adjust, and adjust the brightness of the image using the brightness adjustment model that is compatible with the image difference type, and improve the robustness of the brightness adjustment of the image.
- FIG. 6 is a schematic flowchart of the method for adjusting image brightness in an embodiment. This method can be applied to the terminal 100 shown in FIG.
- the image brightness adjustment method may include the following steps:
- Step S101 Obtain the content difference degree between the reference image and the target image, and obtain the brightness difference degree between the reference image and the target image.
- the reference image refers to an image used as a reference when adjusting the brightness of the target image, that is, the reference image is used as the reference image to adjust the brightness of the target image so that the brightness of the target image and the brightness of the reference image tend to be consistent.
- image 201 is a reference image
- image 202 is a target image.
- the terminal 100 When shooting the reference image and the target image, usually due to the different shooting positions, the image content and image brightness of the reference image and the target image are different.
- the terminal 100 before adjusting the brightness of the target image, the terminal 100 first obtains the reference image and the target image.
- the difference in content and brightness of the image refers to the degree of difference in the image content between multiple images.
- the image content can include the scene where the image was taken, the objects contained in the image, etc., and the same scene is shot from different angles.
- the image content is usually different, resulting in a certain degree of content difference. As shown in FIG.
- the first image is obtained by capturing the target area 300 by the first camera 210
- the second image is obtained by capturing the target area 300 by the second camera 220. Since the first camera 210 and the second camera 220 capture the target area 300 when the The angle and position of is different, and the image content in the first image and the second image also have a certain difference.
- the brightness difference degree refers to the degree of difference in brightness between multiple images, and the reference image may be brighter or darker than the target image.
- the image 201 has a higher brightness than the image 202, and the brightness difference between the image 201 and the image 202 is also greater.
- the image 401 and the image 402 shown in Figure 4 the image 401 and the image 402 The brightness difference is smaller.
- Step S102 Determine the image difference type between the reference image and the target image according to the content difference degree and the brightness difference degree.
- This step is mainly to determine the type of image difference between the two images based on the difference in content and brightness between the reference image and the target image.
- the type of image difference can include multiple types, such as the content between the reference image and the target image.
- the difference is large and the brightness difference is also large, the content difference between the reference image and the target image is large but the brightness difference is small, the content difference between the reference image and the target image is small, but the brightness difference is large and the content difference between the reference image and the target image is small
- the brightness difference is also small, etc., and different contents and brightness differences can also be divided to further enrich the difference types of the image.
- Step S103 Extract a brightness adjustment model suitable for the type of image difference from a plurality of brightness adjustment models.
- This step mainly considers that if a single brightness adjustment model is used to adjust the brightness of various images, it is likely to cause low image contrast and loss of image information. Therefore, the terminal 100 can pre-store multiple brightness adjustment models, and each The brightness adjustment model can be used to adjust the brightness of the reference image under different image difference types. Therefore, in this step, after the image difference type between the reference image and the target image is determined, it can be adapted from the pre-stored image difference type according to the image difference type. Among the multiple brightness adjustment models, a brightness adjustment model suitable for the image difference type is selected, so that the brightness adjustment model is subsequently used to perform brightness adjustment processing on the reference image.
- the image shown in Figure 2 and Figure 4 is used to illustrate this step.
- the image 201 shown in Figure 2 is the reference image, and the image 202 is the target image.
- the image difference type between the image 201 and the image 202 is that the brightness difference is large.
- the content difference is small.
- the image 301 and the image 302 shown in FIG. 3 are the images obtained by linear transformation and histogram matching of the image 202 respectively.
- the visible image 302 has a better brightness adjustment effect than the image 301.
- the image 401 and the image 402 shown in 4 belong to the image difference type with small content difference and small brightness difference.
- the images obtained after linear transformation and histogram matching of the image 402 are the image 501 and the image 502 shown in FIG. 5, respectively.
- the visible image 501 has a better brightness adjustment effect than the image 502. Therefore, the linear transformation algorithm and the histogram matching algorithm can be encapsulated into a linear transformation model and a histogram matching model respectively, and stored in the terminal 100 in advance.
- the terminal 100 can extract the histogram.
- the image matching model is used to adjust the brightness of the reference image.
- a linear transformation model can be extracted to adjust the brightness of the reference image.
- step S104 the brightness of the target image is adjusted based on the reference image through the brightness adjustment model.
- the brightness adjustment model is used to adjust the brightness of the target image based on the reference image, so that the brightness of the target image and the reference image tend to be consistent.
- the above image brightness adjustment method is to obtain the content difference and brightness difference between the reference image and the target image, and then determine the image difference type between the reference image and the target image according to the content difference and the brightness difference, and then according to the image difference
- the type selects a brightness adjustment model that is compatible with the image difference type from a plurality of brightness adjustment models, and performs brightness adjustment on the target image based on the reference image through the brightness adjustment model.
- This solution can determine the type of image difference based on the degree of content difference and brightness difference between images, and then adaptively select different brightness adjustment models to adjust the brightness of the image in combination with the type of image difference, and use the image difference type compatible
- the brightness adjustment model adjusts the image brightness, avoiding the problem of low image brightness adjustment robustness caused by using a single brightness adjustment algorithm to adjust the brightness of the reference image.
- the step of obtaining the content difference between the reference image and the target image may include:
- This embodiment mainly calculates the Hamming distance based on the hash value of the reference image and the target image, thereby determining the content difference between the reference image and the target image according to the Hamming distance, realizing the quantification of the content difference, which is beneficial to more accuracy To obtain the content difference between the reference image and the target image.
- I ref for the reference image and the target image I obj can judge a degree of difference between the reference image and the target image I ref I obj dHash as perceived by the hashing algorithm, the following steps:
- FIG. 7 is a schematic diagram of image compression in an embodiment.
- the input image 701 can be compressed into a 9 ⁇ 8 size image 702, and the reference image I ref and the target image I obj can be compressed into a 9 ⁇ 8 size compression
- the figure is conducive to expressing the hash values of the reference image I ref and the target image I obj by 64 numbers in the subsequent steps, so as to facilitate the terminal 100 to calculate the hash values.
- I small (i, j) represents the pixel value of the i-th row and j-th column of I small , 0 ⁇ j ⁇ 9, 0 ⁇ i ⁇ 8, after the above formula is calculated, 64 composed of 0 and 1 can be obtained.
- the 64 numbers can form a series of numbers to represent the hash value b i,j of the corresponding image.
- the hash value represents the image content information contained after the image is abstracted. For example, the image as shown in Figure 7 702 is calculated according to the above formula, and you can get: 0001101010010000010100100011011000010110010001010010111101101011, and this string of numbers can be used as the hash value of the image 702.
- each reference image and the target image I ref I obj compression calculated according to the above formula, b ref is obtained first hash value and second hash value b obj and the reference image I ref I obj of the target image, Then you can calculate the Hamming distance H(b ref ,b obj ) between the first hash value b ref and the second hash value b obj .
- the Hamming distance is the difference between the two number strings.
- the second and fourth digits are different, so the Hamming distance of these two strings of numbers is 2, and the size of the Hamming distance indicates the difference between the content of the reference image I ref and the target image I obj Difference degree, the greater the Hamming distance, the greater the content difference degree.
- This embodiment quantifies the content difference between the two images by calculating the Hamming distance between the reference image and the target image, which improves the accuracy of obtaining the content difference between the reference image and the target image, and facilitates accurate selection in subsequent steps
- the corresponding brightness adjustment model is used to adjust the brightness of the reference image, which further increases the robustness of the image brightness adjustment.
- the step of obtaining the brightness difference between the reference image and the target image may include:
- the first average brightness value of the reference image is acquired, and the second average brightness value of the target image is acquired; the brightness difference degree is determined according to the difference between the first average brightness value and the second average brightness value.
- the brightness difference between the two images is mainly determined based on the difference between the average brightness values of the reference image and the target image.
- the average pixel value of the reference image and the target image can be calculated separately: the first average brightness value mean (I ref ) and the second average brightness value mean (I obj ), and then according to the first average brightness value mean (I ref )
- the difference between the second average brightness value mean(I obj ) and the brightness difference between the reference image and the target image is calculated.
- the brightness difference can be expressed as:
- This embodiment quantifies the brightness difference between the two images based on the difference between the average brightness values of the reference image and the target image, improves the accuracy of obtaining the brightness difference between the reference image and the target image, and compares the average brightness of the image.
- the calculation of the value is simple and quick, and it also helps to improve the efficiency of obtaining the brightness difference.
- the step of determining the image difference type between the reference image and the target image according to the content difference degree and the brightness difference degree may include:
- the content difference degree is compared with the first threshold, and the brightness difference degree is compared with the second threshold; if the content difference degree is less than the first threshold and the brightness difference degree is less than the second threshold, the image difference type is determined as the reference image and the target image The content difference is small and the brightness difference is small.
- the content difference degree and brightness difference degree between the reference image and the target image can be compared with the first threshold and the second threshold respectively, and the image difference type between the reference image and the target image can be obtained according to the comparison result.
- the difference between the reference image and the target image is The content difference is small and the brightness difference is small.
- the image difference type is that the content difference between the reference image and the target image is large and the brightness difference is small.
- the image difference type is a large content difference and a large brightness difference between the reference image and the target image.
- the image difference type is that the content difference between the reference image and the target image is small and the brightness difference is large.
- the Hamming distance H (b ref , b obj ) can be taken as the content difference degree between the reference image and the target image, and the difference between the first average brightness value mean (I ref ) and the second average brightness value mean (I obj )
- is the brightness difference between the reference image and the target image, then H(b ref ,b obj ) and
- H(b ref ,b obj ) is less than Threshold H and
- the first threshold H and the second threshold Threshold mean can be both set to 30, and the specific values of the first threshold H and the second threshold Threshold mean can be selected according to the actual task of brightness adjustment, if in certain relatively stable scene illumination, the method may prefer to use a linear transformation to adjust the brightness of the image can be improved adaptation to a first threshold and a second threshold value threshold H threshold mean values.
- the step of extracting a brightness adjustment model adapted to the type of image difference from a plurality of brightness adjustment models may include:
- the linear transformation model is extracted from the multiple brightness adjustment models to adjust the brightness of the target image.
- a linear transformation model is extracted from a plurality of brightness adjustment models as a linear transformation model for adjusting the brightness of the target image.
- the linear transformation model can perform linear transformation processing on the input image to adjust the brightness of the image, the specific method is as follows:
- a and b are transformation parameters, which can be defined as:
- std(I ref ) represents the mean square error of the pixel value of the reference image I ref
- std(I obj ) represents the mean square error of the pixel value of the target image I obj
- mean(I ref ) the mean value of the pixel value of the reference image I ref
- mean( I obj ) The average value of the pixel values of the target image I obj .
- the brightness value of the target image is adjusted through the linear transformation model.
- Figure 8 for the specific brightness adjustment effect, which is an implementation.
- the image 801 corresponds to the reference image
- the image 802 corresponds to the target image
- the image 803 corresponds to the image obtained after linear transformation of the image 802. It can be seen that the reference image When the content difference with the target image is small and the brightness difference is small, the brightness value of the target image is better adjusted.
- the step of extracting a brightness adjustment model adapted to the type of image difference from a plurality of brightness adjustment models may include:
- the type of image difference is that the content difference between the reference image and the target image is large and the brightness difference is small, the content difference between the reference image and the target image is large and the brightness difference is large, or the content difference between the reference image and the target image is small and the brightness difference is small If the degree is large, the histogram matching model is extracted from the multiple brightness adjustment models to adjust the brightness of the target image.
- This embodiment is mainly used when the image difference type between the reference image and the difference image is that the content difference is large and the brightness difference is small, the content difference is large and the brightness difference is large, or the content difference is small and the brightness difference is large.
- the histogram matching model adjusts the brightness of the target image, and the histogram matching model can perform histogram matching processing on the input image to adjust the brightness of the image.
- histogram matching function is transformed by histogram of the target image I obj, so I obj consistent target image histogram and the reference image I ref, so that the brightness of the two images, and The contrast tends to be the same, the specific method is as follows:
- the probability density function pdf is:
- n l represents the number of pixels with a pixel value of l in image I
- N represents the total number of pixels in image I
- pdf(l) represents the probability that a pixel with pixel value l appears in image I
- image I The cumulative distribution function is:
- the cumulative distribution function can be used to represent the cumulative normalized histogram of the image I. Therefore, the reference image I ref and the target image I obj can be calculated to obtain the respective cumulative distribution functions cdf ref and cdf obj . Refer to FIG.
- a mapping function T(l obj ) can be obtained.
- each pixel of the target image I obj is gray-scale transformed.
- a histogram-matched image can be obtained.
- the type of image difference between the reference image and the difference image is large content difference and small brightness difference, large content difference and large brightness difference or small content difference. And when the brightness difference is large, the reference image is better adjusted, as shown in FIG.
- the image 901 corresponds to the reference image
- the image 902 corresponds to the target image
- the image 903 corresponds to the image obtained after the histogram matching of the image 902. It can be seen that the brightness of the target image can be adjusted by the histogram matching method to achieve the comparison of the brightness value of the target image. Good adjustment effect.
- FIG. 11 is a structural block diagram of the device for adjusting image brightness in an embodiment.
- the device for adjusting image brightness may include:
- the obtaining module 101 is configured to obtain the content difference between the reference image and the target image, and obtain the brightness difference between the reference image and the target image;
- the determining module 102 is configured to determine the image difference type between the reference image and the target image according to the content difference degree and the brightness difference degree;
- the extraction module 103 is configured to extract a brightness adjustment model that is compatible with the image difference type from a plurality of brightness adjustment models;
- the adjustment module 104 is configured to adjust the brightness of the target image based on the reference image through the brightness adjustment model.
- the obtaining module 101 may include:
- the first obtaining unit is used to obtain the first hash value of the reference image and obtain the second hash value of the target image; according to the first hash value and the second hash value, calculate the Hamming distance between the reference image and the target image ; Determine the content difference degree according to the Hamming distance.
- the obtaining module 101 may include:
- the second acquiring unit is configured to acquire the first average brightness value of the reference image and acquire the second average brightness value of the target image; determine the brightness difference degree according to the difference between the first average brightness value and the second average brightness value.
- the determining module 102 may include:
- the comparing unit is configured to compare the content difference degree with a first threshold, and compare the brightness difference degree with a second threshold;
- the first determining unit is configured to determine that the image difference type is that the content difference between the reference image and the target image is small and the brightness difference is small if the content difference is less than the first threshold and the brightness difference is less than the second threshold.
- the extraction module 103 may include:
- the first adjustment unit is configured to, if the image difference type is that the content difference between the reference image and the target image is small and the brightness difference is small, extract a linear transformation model from a plurality of brightness adjustment models to adjust the brightness of the target image.
- it may further include:
- the second determining unit is configured to determine that the image difference type is that the content difference between the reference image and the target image is large and the brightness difference is small if the content difference is greater than the first threshold and the brightness difference is less than the second threshold;
- the third determining unit is configured to determine that if the content difference degree is greater than the first threshold and the brightness difference degree is greater than the second threshold value, the image difference type is determined to be that the content difference between the reference image and the target image is large and the brightness difference is large;
- the fourth determining unit is configured to determine that the image difference type is that the content difference between the reference image and the target image is small and the brightness difference is large if the content difference is less than the first threshold and the brightness difference is greater than the second threshold.
- the extraction module 103 may include:
- the second adjusting unit is used if the image difference type is that the content difference between the reference image and the target image is large and the brightness difference is small, the content difference between the reference image and the target image is large and the brightness difference is large, or the difference between the reference image and the target image If the content difference is small and the brightness difference is large, the histogram matching model is extracted from the multiple brightness adjustment models to adjust the brightness of the target image.
- the image brightness adjustment device of this application corresponds to the image brightness adjustment method of this application one-to-one.
- the image brightness adjustment device please refer to the above definition of the image brightness adjustment method.
- the technical features and beneficial effects described in the embodiments are all applicable to the embodiments of the image brightness adjustment device, and will not be repeated here.
- Each module in the above-mentioned image brightness adjustment device can be implemented in whole or in part by software, hardware, and a combination thereof.
- the above modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
- a computer device is provided.
- the computer device may be a terminal, and its internal structure diagram may be as shown in FIG. 12, which is an internal structure diagram of the computer device in an embodiment.
- the computer equipment includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide calculation and control capabilities.
- the memory of the computer device includes a non-volatile storage medium and an internal memory.
- the non-volatile storage medium stores an operating system and a computer program.
- the internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium.
- the network interface of the computer device is used to communicate with an external terminal through a network connection.
- the computer program is executed by the processor to realize an image brightness adjustment method.
- the display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen
- the input device of the computer equipment can be a touch layer covered on the display screen, or it can be a button, a trackball or a touchpad set on the computer equipment shell , It can also be an external keyboard, touchpad, or mouse.
- FIG. 12 is only a block diagram of part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
- the specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.
- a computer device including a processor and a memory, the memory stores a computer program, and the processor implements the following steps when executing the computer program:
- Obtain the content difference between the reference image and the target image obtain the brightness difference between the reference image and the target image; determine the image difference type between the reference image and the target image according to the content difference and the brightness difference; from multiple brightness adjustment models The brightness adjustment model adapted to the image difference type is extracted; the brightness adjustment model is used to adjust the brightness of the target image based on the reference image.
- the processor further implements the following steps when executing the computer program:
- the processor further implements the following steps when executing the computer program:
- the first average brightness value of the reference image is acquired, and the second average brightness value of the target image is acquired; the brightness difference degree is determined according to the difference between the first average brightness value and the second average brightness value.
- the processor further implements the following steps when executing the computer program:
- the content difference degree is compared with the first threshold, and the brightness difference degree is compared with the second threshold; if the content difference degree is less than the first threshold and the brightness difference degree is less than the second threshold, the image difference type is judged to be the reference image and the target image The content difference is small and the brightness difference is small.
- the processor further implements the following steps when executing the computer program:
- the linear transformation model is extracted from the multiple brightness adjustment models to adjust the brightness of the target image.
- the processor further implements the following steps when executing the computer program:
- the image difference type is determined as the content difference between the reference image and the target image is large and the brightness difference is small; if the content difference is greater than the first threshold and the brightness difference If the degree of difference is greater than the second threshold, the image difference type is determined as the content difference between the reference image and the target image is large and the brightness difference is large; if the content difference is less than the first threshold and the brightness difference is greater than the second threshold, then the image difference type is determined The content difference between the reference image and the target image is small and the brightness difference is large.
- the processor further implements the following steps when executing the computer program:
- the type of image difference is that the content difference between the reference image and the target image is large and the brightness difference is small, the content difference between the reference image and the target image is large and the brightness difference is large, or the content difference between the reference image and the target image is small and the brightness difference is small If the degree is large, the histogram matching model is extracted from the multiple brightness adjustment models to adjust the brightness of the target image.
- the above-mentioned computer equipment through the computer program running on the processor, can determine the image difference type based on the content difference and the brightness difference between the images, and then adaptively select different brightness adjustment models to perform the image processing based on the image difference type. Brightness adjustment, and adjust the image brightness by using a brightness adjustment model adapted to the image difference type, avoiding the problem of low image brightness adjustment robustness caused by using a single brightness adjustment algorithm to adjust the brightness of the reference image.
- Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
- Volatile memory may include random access memory (RAM) or external cache memory.
- RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
- a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:
- Obtain the content difference between the reference image and the target image obtain the brightness difference between the reference image and the target image; determine the image difference type between the reference image and the target image according to the content difference and the brightness difference; from multiple brightness adjustment models The brightness adjustment model adapted to the image difference type is extracted; the brightness adjustment model is used to adjust the brightness of the target image based on the reference image.
- the computer program further implements the following steps when being executed by the processor:
- the computer program further implements the following steps when being executed by the processor:
- the first average brightness value of the reference image is acquired, and the second average brightness value of the target image is acquired; the brightness difference degree is determined according to the difference between the first average brightness value and the second average brightness value.
- the computer program further implements the following steps when being executed by the processor:
- the content difference degree is compared with the first threshold, and the brightness difference degree is compared with the second threshold; if the content difference degree is less than the first threshold and the brightness difference degree is less than the second threshold, the image difference type is determined as the reference image and the target image The content difference is small and the brightness difference is small.
- the computer program further implements the following steps when being executed by the processor:
- the linear transformation model is extracted from the multiple brightness adjustment models to adjust the brightness of the target image.
- the computer program further implements the following steps when being executed by the processor:
- the image difference type is determined as the content difference between the reference image and the target image is large and the brightness difference is small; if the content difference is greater than the first threshold and the brightness difference If the degree of difference is greater than the second threshold, the image difference type is determined as the content difference between the reference image and the target image is large and the brightness difference is large; if the content difference is less than the first threshold and the brightness difference is greater than the second threshold, then the image difference type is determined The content difference between the reference image and the target image is small and the brightness difference is large.
- the computer program further implements the following steps when being executed by the processor:
- the type of image difference is that the content difference between the reference image and the target image is large and the brightness difference is small, the content difference between the reference image and the target image is large and the brightness difference is large, or the content difference between the reference image and the target image is small and the brightness difference is small If the degree is large, the histogram matching model is extracted from the multiple brightness adjustment models to adjust the brightness of the target image.
- the above-mentioned computer-readable storage medium through its stored computer program, can determine the type of image difference based on the degree of content difference and brightness difference between images, and then adaptively select different brightness adjustment models to adjust the brightness of the image in combination with the type of image difference. Adjust, and adjust the image brightness by using the brightness adjustment model that is compatible with the image difference type, avoiding the problem of low image brightness adjustment robustness caused by using a single brightness adjustment algorithm to adjust the brightness of the reference image.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
一种图像亮度的调节方法、装置、计算机设备和存储介质，获取参考图像与目标图像的内容差异度和亮度差异度，然后根据该内容差异度和亮度差异度确定参考图像和目标图像之间的图像差异类型，接着根据该图像差异类型从多个亮度调节模型中选择与该图像差异类型相适应的亮度调节模型，并通过该亮度调节模型基于参考图像对目标图像进行亮度调节。
Description
本公开要求在2019年02月19日提交中国专利局、申请号为201910121620.3的中国专利申请的优先权，以上申请的全部内容通过引用结合在本公开中。
本申请涉及图像处理技术领域，例如涉及一种图像亮度的调节方法、图像亮度的调节装置、计算机设备和计算机可读存储介质。
在图像处理中，有时需要对一张图像的亮度进行调节，使得这张图像的亮度与参考图像的亮度趋于一致。例如在通过多目摄像头拍摄物体的图像后，由于各个摄像头拍摄物体的位置不同，受到光线的影响也不同，因此各个摄像头拍摄的图像的亮度一般也不同，因此需要对图像的亮度进行调节，使得各张图像的亮度趋于一致，以提高图像的整体成像效果。
然而，传统技术在对目标图像的亮度进行调节使得该目标图像与参考图像的亮度区域一致时，容易使目标图像在进行亮度调节后发生过多的图像信息丢失、图像对比度变低等情况，导致传统技术对图像亮度进行调节的鲁棒性低。
发明内容
本申请提供一种图像亮度的调节方法、图像亮度的调节装置、计算机设备和计算机可读存储介质，以解决传统技术对图像亮度进行调节的鲁棒性低的技术问题。
一种图像亮度的调节方法，包括步骤：
获取参考图像与目标图像的内容差异度，获取所述参考图像与目标图像的亮度差异度；
根据所述内容差异度和亮度差异度确定所述参考图像与目标图像之间的图像差异类型；
从多个亮度调节模型中提取与所述图像差异类型相适应的亮度调节模型；
通过所述亮度调节模型基于所述参考图像对所述目标图像的亮度进行调节。
一种图像亮度的调节装置，包括：
获取模块，用于获取参考图像与目标图像的内容差异度，获取所述参考图像与目标图像的亮度差异度；
确定模块，用于根据所述内容差异度和亮度差异度确定所述参考图像与目标图像之间的图像差异类型；
提取模块，用于从多个亮度调节模型中提取与所述图像差异类型相适应的亮度调节模型；
调节模块，用于通过所述亮度调节模型基于所述参考图像对所述目标图像的亮度进行调节。
一种计算机设备，包括处理器和存储器，所述存储器存储有计算机程序，所述处理器执行所述计算机程序时实现如下步骤：
获取参考图像与目标图像的内容差异度，获取所述参考图像与目标图像的亮度差异度；根据所述内容差异度和亮度差异度确定所述参考图像与目标图像之间的图像差异类型；从多个亮度调节模型中提取与所述图像差异类型相适应的亮度调节模型；通过所述亮度调节模型基于所述参考图像对所述目标图像的亮度进行调节。
一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现如下步骤：
获取参考图像与目标图像的内容差异度，获取所述参考图像与目标图像的亮度差异度；根据所述内容差异度和亮度差异度确定所述参考图像与目标图像之间的图像差异类型；从多个亮度调节模型中提取与所述图像差异类型相适应的亮度调节模型；通过所述亮度调节模型基于所述参考图像对所述目标图像的亮度进行调节。
上述图像亮度的调节方法、装置、计算机设备和存储介质，获取参考图像与目标图像的内容差异度和亮度差异度，然后根据该内容差异度和亮度差异度确定参考图像和目标图像之间的图像差异类型，接着根据该图像差异类型从多个亮度调节模型中选择与该图像差异类型相适应的亮度调节模型，并通过该亮度调节模型基于参考图像对目标图像进行亮度调节。该方案能够基于图像之间的内容差异度和亮度差异度确定图像差异类型，进而结合图像差异类型适应性地选择不同的亮度调节模型对图像进行亮度调节，并利用与该图像差异类型相适应的亮度调节模型调节图像亮度，避免采用单一的亮度调节算法对参考图像进行亮度调节带来的图像亮度调节鲁棒性低的问题。
图1为一个实施例中图像亮度的调节方法的应用场景图；
图2为一个实施例中参考图像和目标图像的示意图；
图3为一个实施例中图像亮度的调节方法的效果图；
图4为另一个实施例中参考图像和目标图像的示意图；
图5为另一个实施例中图像亮度的调节方法的效果图；
图6为一个实施例中图像亮度的调节方法的流程示意图；
图7为一个实施例中图像压缩的示意图；
图8为一个实施例中通过线性变换模型调节目标图像亮度的效果示意图；
图9为一个实施例中直方图匹配的灰度变换的原理示意图；
图10为一个实施例中通过直方图匹配模型调节目标图像亮度的效果示意图；
图11为一个实施例中图像亮度的调节装置的结构框图；
图12为一个实施例中计算机设备的内部结构图。
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。
需要说明的是，本申请实施例所涉及的术语“第一\第二\第三”仅仅是是区别类似的对象，不代表针对对象的特定排序，可以理解地，“第一\第二\第三”在允许的情况下可以互换特定的顺序或先后次序。应该理解“第一\第二\第三”区分的对象在适当情况下可以互换，以使这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。
本申请提供的图像亮度的调节方法，可以应用于如图1所示的应用场景中，图1为一个实施例中图像亮度的调节方法的应用场景图，可以通过如双目摄像头等图像拍摄设备对目标区域300中的物体进行拍摄，双目摄像头可以将拍摄的图像传输给具有图像处理能力的终端100，终端100可以用于对采集的图像进行亮度调节，使得双目摄像头拍摄的图像亮度趋于一致。其中，终端100可以包括但不限于是个人计算机、笔记本电脑和平板电脑等设备。
具体来说，双目摄像头可以包括第一摄像头210和第二摄像头220，第一摄像头210和第二摄像头220一般会在不同的位置点对目标区域中的物体进行拍摄，目标区域中包括物体A、物体B和物体C，而由于第一摄像头210和第二摄像头220拍摄图像的位置不同，物体A、物体B和物体C在第一摄像头210和第二摄像头220拍摄得到的图像中的位置也不相同，而且第一摄像头210和第二摄像头220拍摄图像的位置不同也会引起两个摄像头受到拍摄环境的光线的影响程度也不相同，所以两个摄像头拍摄的图像在内容和亮度上均会产生一定的差异。一般来说，第一摄像头210和第二摄像头220拍摄图像时相距的距离越近，两个摄像头拍摄的图像内容和受光线的影响程度也越相似，当两个摄像头距离越远，差异通常越大。如图1所示，当第二摄像头220从原来的位置移动到虚线框230所示的位置时，与第一摄像头210拍摄的图像在内容和亮度上的差异也会变大。
终端100在获取第一摄像头210和第二摄像头220拍摄的图像后，可以对两个摄像头拍摄的图像进行亮度调节，使得两个摄像头拍摄的图像的亮度趋于一致，设第一摄像头210拍摄的图像为参考图像，第二摄像头220拍摄的图像为目标图像，则终端100可以以参考图像为基准，调节目标图像的亮度，使得目标图像的亮度与参考图像趋于一致。
在实施传统技术提供的亮度调节方法时，本申请的申请人发现，传统技术通常采用单一的亮度调节算法来调节多张图像之间的亮度，也就是说传统技术实际上没有基于各张图像的 特点来对图像的亮度进行调节，而是通常采用同一种亮度调节算法来调节各张图像的亮度，这往往会使目标图像在进行亮度调节后发生过多的图像信息丢失、图像对比度变低等情况。
如图2所示，图2为一个实施例中参考图像和目标图像的示意图，设图像201为参考图像，图像202为目标图像，传统技术一般会通过线性变换的方式来调节图像202的亮度，如图3所示，图3为一个实施例中图像亮度的调节方法的效果图，图像301即为对图像202进行线性变换后得到的图像，可以看到，图像301的图像对比度变低了，在这种情况下如果采用线性变换则会降低图像对比度变低，成像质量并不好，如果通过直方图匹配的方式来对图像202进行亮度调节，则调节结果为如图3所示的图像302，图像302表明在这种情况下采用直方图匹配的方式来调节图像202的亮度具有比线性变换的方式进行亮度调节更好的效果。
对于如图4所示的图像401和图像402，图4为另一个实施例中参考图像和目标图像的示意图，其中，图像401对应于参考图像，图像402对应于目标图像，如果采用直方图匹配的方式来对图像402进行亮度调节则会产生不自然的区域和纹理，对图像402的调节结果为如图5所示的图像502，图5为另一个实施例中图像亮度的调节方法的效果图，可以看到，使用直方图匹配对图像402进行亮度调节后，会在图像502中产生太多不自然的区域和纹理，但采用线性变换的方式来对图像402进行亮度调节，则调节结果为如图5所示的图像501，可见在这种情况之下采用线性变换的效果会更好，因此如果采用传统技术提供的通过单一亮度调节算法来调节图像的亮度，容易造成图像对比度低、图像信息丢失等情况，导致对图像亮度进行调节的鲁棒性低。
本申请实施例提供的图像亮度的调节方法，终端100可以基于图像之间的内容差异度和亮度差异度确定图像差异类型，进而结合图像差异类型适应性地选择不同的亮度调节模型对图像进行亮度调节，并利用与该图像差异类型相适应的亮度调节模型调节图像亮度，提高对图像进行亮度调节的鲁棒性。
在一个实施例中，提供了一种图像亮度的调节方法，参考图6，图6为一个实施例中图像亮度的调节方法的流程示意图，该方法可以应用于图1所示的终端100对图像进行亮度调节，该图像亮度的调节方法可以包括以下步骤：
步骤S101，获取参考图像与目标图像的内容差异度，获取所述参考图像与目标图像的亮度差异度。
其中，参考图像是指用于对目标图像进行亮度调节时作为基准的图像，即以参考图像作为基准图像，调节目标图像的亮度，使得目标图像的亮度与参考图像的亮度趋于一致。如图2所示，图像201是参考图像，图像202是目标图像，在对图像202进行亮度调节时，以图像201作为基准，调节图像202的亮度，使得图像202的亮度与图像201的亮度区域一致。
在拍摄参考图像和目标图像时通常会由于拍摄位置不同，导致参考图像和目标图像的图像内容和图像亮度不同，本步骤可以在对目标图像的亮度进行调节之前，终端100先获取参考图像和目标图像的内容差异度和亮度差异度。其中，内容差异度是指多张图像之间的图像内容的差异程度，图像内容可以包括图像拍摄的场景、图像中包含的物体等等，而从不同角度对同一场景进行拍摄，拍摄得到图像的图像内容通常会不同，从而产生了一定的内容差异度。如图1所示，通过第一摄像头210拍摄目标区域300得到第一图像，通过第二摄像头220拍摄目标区域300得到第二图像，由于第一摄像头210和第二摄像头220拍摄目标区域300时拍摄的角度、位置不同，第一图像和第二图像中的图像内容也具有一定差异。
而亮度差异度是指多张图像之间的亮度的差异程度，而参考图像相对于目标图像来说，可能会偏亮一些，也可能会偏暗一些。如图2所示，图像201相对于图像202来说亮度较高，图像201和图像202的亮度差异度也较大，对于如图4所示的图像401和图像402，图像401与图像402的亮度差异度则较小。
步骤S102，根据内容差异度和亮度差异度确定参考图像与目标图像之间的图像差异类型。
本步骤主要是根据参考图像和目标图像之间的内容差异度以及亮度差异度来确定两张图像之间的图像差异类型，图像差异类型可以包括多种，例如参考图像和目标图像之间的内容差异大且亮度差异也大、参考图像和目标图像之间的内容差异大但亮度差异小、参考图像和目标图像之间的内容差异小但亮度差异大和参考图像和目标图像之间的内容差异小且亮度差异也小等等，还可以对不同的内容和亮度的差异程度进行划分以进一步丰富图像的差异类型。
步骤S103，从多个亮度调节模型中提取与图像差异类型相适应的亮度调节模型。
本步骤主要是考虑到如果采用单一的亮度调节模型来对各种图像的亮度进行调节，则容易产生图像对比度低、图像信息丢失等情况，所以终端100可以预先存储多个亮度调节模型，而各个亮度调节模型可以用于对不同图像差异类型下的参考图像进行亮度调节，因此，本步骤可以在确定参考图像与目标图像之间的图像差异类型以后，根据该图像差异类型适应性地从预存的多个亮度调节模型当中选取与该图像差异类型相适应的亮度调节模型，以便后续利用该亮度调节模型来对参考图像进行亮度调节处理。
以如图2和图4所示的图像来对本步骤进行说明，如图2所示的图像201为参考图像，而图像202为目标图像，图像201和图像202的图像差异类型为亮度差异大而内容差异小，如图3所示的图像301和图像302分别是对图像202进行线性变换和直方图匹配得到的图像，可见图像302相比于图像301具有更好的亮度调节效果，而如图4所示的图像401和图像402则属于内容差异小且亮度差异小的图像差异类型，对图像402进行线性变换和直方图匹配后得到的图像分别为如图5所示的图像501和图像502可见图像501相比于图像502具有更好 的亮度调节效果。因此，可以将线性变换算法和直方图匹配算法分别封装成线性变换模型和直方图匹配模型，并预先存储在终端100中，当图像差异类型为亮度差异大而内容差异小时，终端100可以提取直方图匹配模型来对参考图像进行亮度调节，当图像差异类型为内容差异小且亮度差异小时，则可以提取线性变换模型来对参考图像进行亮度调节。
步骤S104，通过亮度调节模型基于参考图像对目标图像的亮度进行调节。
本步骤主要是在提取与图像差异类型相适应的亮度调节模型后，通过该亮度调节模型基于参考图像来对目标图像的亮度进行调节，使得目标图像的亮度与参考图像的亮度趋于一致。
上述图像亮度的调节方法，获取参考图像与目标图像的内容差异度和亮度差异度，然后根据该内容差异度和亮度差异度确定参考图像和目标图像之间的图像差异类型，接着根据该图像差异类型从多个亮度调节模型中选择与该图像差异类型相适应的亮度调节模型，并通过该亮度调节模型基于参考图像对目标图像进行亮度调节。该方案能够基于图像之间的内容差异度和亮度差异度确定图像差异类型，进而结合图像差异类型适应性地选择不同的亮度调节模型对图像进行亮度调节，并利用与该图像差异类型相适应的亮度调节模型调节图像亮度，避免采用单一的亮度调节算法对参考图像进行亮度调节带来的图像亮度调节鲁棒性低的问题。
在一个实施例中，获取参考图像与目标图像的内容差异度的步骤可以包括：
获取参考图像的第一哈希值，获取目标图像的第二哈希值；根据第一哈希值和第二哈希值，计算参考图像与目标图像的汉明距离；根据汉明距离确定内容差异度。
本实施例主要是基于参考图像和目标图像的哈希值计算汉明距离，从而根据汉明距离确定参考图像与目标图像之间的内容差异度，实现对内容差异度的量化，有利于更准确地得到参考图像与目标图像的内容差异度。
对于参考图像I
ref和目标图像I
obj，可以通过如dHash感知哈希算法来判断参考图像I
ref和目标图像I
obj之间的内容差异度，步骤如下：
对于任意输入的图像I(可以是参考图像I
ref和目标图像I
obj)，可以先将该图像I按照一定的压缩比例进行压缩，如压缩为9×8大小的压缩图I
small，如图7所示，图7为一个实施例中图像压缩的示意图，可以将输入的图像701压缩成9×8大小的图像702，而将参考图像I
ref和目标图像I
obj压缩成9×8大小的压缩图，有利于在后续步骤当中通过64个数表示参考图像I
ref和目标图像I
obj的哈希值，方便终端100对该哈希值进行运算。
而对于压缩图I
small的每一行像素，可以按照如下公式进行计算：
其中，I
small(i,j)表示I
small的第i行第j列的像素值，0≤j＜9,0≤i＜8，经过上述公式计算后，可以得到由0和1组成的64个数，这64个数可以组成一串数表示相应图像的哈希值b
i,j，该哈希值代表的是图像抽象后所包含的图像内容信息，例如将如图7所示的图像702按照上述公式进行计算，可以得到：0001101010010000010100100011011000010110010001010010111101101011，该串数字可以作为图像702的哈希值。
因此，可以分别对参考图像I
ref和目标图像I
obj进行压缩，按照上述公式进行计算，获得参考图像I
ref和目标图像I
obj的第一哈希值b
ref和第二哈希值b
obj，然后可以计算第一哈希值b
ref和第二哈希值b
obj之间的汉明距离H(b
ref,b
obj)，汉明距离计算的是两个数字串之间的不相同的位数，例如对于1001和1100，第二和第四位不同，所以这两串数字的汉明距离为2，而汉明距离的大小则说明了参考图像I
ref和目标图像I
obj之间内容的差异度，汉明距离越大，说明内容差异度越大。
本实施例通过计算参考图像和目标图像的汉明距离来对两张图像之间的内容差异度进行量化，提高了获取参考图像和目标图像的内容差异度的准确度，有利于后续步骤准确选择相应的亮度调节模型来对参考图像进行亮度调节，进一步增加图像亮度调节的鲁棒性。
在一个实施例中，获取参考图像与目标图像的亮度差异度的步骤可以包括：
获取参考图像的第一平均亮度值，获取目标图像的第二平均亮度值；根据第一平均亮度值和第二平均亮度值的差值，确定亮度差异度。
本实施例主要是基于参考图像和目标图像的平均亮度值的差值来确定两张图像的亮度差异度。其中，可以分别计算参考图像和目标图像各自的平均像素值：第一平均亮度值mean(I
ref)和第二平均亮度值mean(I
obj)，然后根据第一平均亮度值mean(I
ref)和第二平均亮度值mean(I
obj)的差值计算参考图像与目标图像的亮度差异度，亮度差异度可以表示为：|mean(I
ref)-mean(I
obj)|。
本实施例基于参考图像与目标图像的平均亮度值之间的差值来量化两张图像的亮度差异度，提高了获取参考图像和目标图像的亮度差异度的准确度，而且对图像的平均亮度值的计算简单快捷，还有助于提高获取亮度差异度的效率。
在一个实施例中，根据内容差异度和亮度差异度确定参考图像与目标图像之间的图像差异类型的步骤可以包括：
将内容差异度与第一阈值进行比较，将亮度差异度与第二阈值进行比较；若内容差异度小于第一阈值且亮度差异度小于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度小。
本实施例中，可以将参考图像与目标图像之间的内容差异度以及亮度差异度分别与第一阈值、第二阈值进行比较，根据比较结果可以获取参考图像与目标图像之间的图像差异类型。
其中，如果参考图像与目标图像之间的内容差异度小于第一阈值，且参考图像与目标图像之间的亮度差异度小于第二阈值，则可以判断参考图像与目标图像之间的差异情况为内容差异度小且亮度差异度小。
若内容差异度大于第一阈值且亮度差异度小于第二阈值，则可以判断图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度小。
若内容差异度大于第一阈值且亮度差异度大于第二阈值，则可以判断图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度大。
若内容差异度小于第一阈值且亮度差异度大于第二阈值，则可以判断图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度大。
可以将汉明距离H(b
ref,b
obj)作为参考图像与目标图像之间的内容差异度，将第一平均亮度值mean(I
ref)和第二平均亮度值mean(I
obj)的差值|mean(I
ref)-mean(I
obj)|作为参考图像与目标图像之间的亮度差异度，则可以将H(b
ref,b
obj)和|mean(I
ref)-mean(I
obj)|分别与第一阈值Threshold
H和第二阈值Threshold
mean进行比较，若H(b
ref,b
obj)小于Threshold
H且|mean(I
ref)-mean(I
obj)|小于Threshold
mean，则判断参考图像与目标图像之间的差异情况为内容差异度小且亮度差异度小；若H(b
ref,b
obj)大于Threshold
H且|mean(I
ref)-mean(I
obj)|小于Threshold
mean，则判断参考图像与目标图像之间的差异情况为内容差异度大且亮度差异度小；若H(b
ref,b
obj)大于Threshold
H且|mean(I
ref)-mean(I
obj)|大于Threshold
mean，则判断参考图像与目标图像之间的差异情况为内容差异度大且亮度差异度大；若H(b
ref,b
obj)小于Threshold
H且|mean(I
ref)-mean(I
obj)|大于Threshold
mean，则判断参考图像与目标图像之间的差异情况为内容差异度小且亮度差异度大。
在一般情况下，可以将第一阈值Threshold
H和第二阈值Threshold
mean都设为30，而第一阈值Threshold
H和第二阈值Threshold
mean的具体数值可以根据亮度调节的实际任务来进行选 取，如果在某些光照比较稳定的场景，可能会更偏向于使用线性变换的方法来对图像进行亮度调节，则可以适应性提高第一阈值Threshold
H和第二阈值Threshold
mean的取值。
在一个实施例中，从多个亮度调节模型中提取与图像差异类型相适应的亮度调节模型的步骤可以包括：
若图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度小，则从多个亮度调节模型中提取线性变换模型用于对目标图像的亮度进行调节。
本实施例主要是在参考图像和差异图像的图像差异类型为内容差异度小且亮度差异度小时，从多个亮度调节模型中提取线性变换模型作为对目标图像的亮度进行调节的线性变换模型。该线性变换模型可以对输入的图像进行线性变换处理，调节图像的亮度，具体方式如下：
对于参考图像I
ref和目标图像I
obj，可以通过如下线性变换来使得参考图像I
ref和目标图像I
obj的亮度值趋于一致：
I′
obj＝a*I
obj+b
通过上述线性变换，可以使得变换后的目标图像I′
obj的像素值均值和像素值均方差与参考图像I
ref一致，从而达到使得目标图像I
obj的亮度和对比度与参考图像I
ref一致的效果，而a和b分别为变换参数，可以定义为：
a＝std(I
ref)/std(I
obj)
b＝mean(I
ref)-a*mean(I
obj)
其中，std(I
ref)表示参考图像I
ref的像素值均方差，std(I
obj)表示目标图像I
obj的像素值均方差，mean(I
ref)参考图像I
ref的像素值均值，mean(I
obj)目标图像I
obj的像素值均值。
本实施例在参考图像与目标图像的内容差异度小且亮度差异度小的情况下，通过线性变换模型对目标图像的亮度值进行调节，具体的亮度调节效果参考图8，图8为一个实施例中通过线性变换模型调节目标图像亮度的效果示意图，图像801对应于参考图像，图像802对应于目标图像，而图像803则对应于对图像802进行线性变换后得到的图像，可见能够在参考图像与目标图像的内容差异度小且亮度差异度小的情况下对目标图像的亮度值进行较好地调节。
在一个实施例中，从多个亮度调节模型中提取与图像差异类型相适应的亮度调节模型的步骤可以包括：
若图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度小、参考图像与目标图像的内容差异度大且亮度差异度大或参考图像与目标图像的内容差异度小且亮度差异度 大，则从多个亮度调节模型中提取直方图匹配模型用于对目标图像的亮度进行调节。
本实施例主要是在参考图像和差异图像的图像差异类型为内容差异度大且亮度差异度小、内容差异度大且亮度差异度大或内容差异度小且亮度差异度大的情况下，采用直方图匹配模型对目标图像的亮度进行调节，该直方图匹配模型可以对输入的图像进行直方图匹配处理，调节图像的亮度。
对于参考图像I
ref和目标图像I
obj，直方图匹配的作用是通过变换目标图像I
obj的直方图，使得目标图像I
obj与参考图像I
ref的直方图一致，从而使得两张图像的亮度和对比度趋于一致，具体方式如下：
对于图像I(可以包括参考图像I
ref和目标图像I
obj)，其概率密度函数pdf为：
其中，n
l表示图像I中像素值为l的像素的数量，N表示图像I中像素的总数量，pdf(l)表示像素值为为l的像素在图像I中出现的概率，图像I的累积分布函数为：
该累积分布函数可以用于表示图像I的累计归一化直方图。因此，可以对参考图像I
ref和目标图像I
obj进行计算，获得各自的累积分布函数cdf
ref和cdf
obj，参考图9，图9为一个实施例中直方图匹配的灰度变换的原理示意图，对于目标图像I
obj中的每一个像素值l
obj，在cdf
ref(l
ref)中进行搜索，使得cdf
obj(l
obj)≈cdf
ref(l
ref)，即搜索出最靠近cdf
obj(l
obj)的值的cdf
ref(l
ref)，并获得在参考图像I
ref上对应的像素值l
ref。
对于目标图像I
obj中的每一个像素值进行如上处理后，可以得到一个映射函数T(l
obj)，根据映射函数T(l
obj)对目标图像I
obj的每一个像素进行灰度变换，就可以得到一张直方图匹配后的图像，本实施例能够在参考图像和差异图像的图像差异类型为内容差异度大且亮度差异度小、内容差异度大且亮度差异度大或内容差异度小且亮度差异度大的情况下，对参考图像进行较好地调节，如图10所示，图10为一个实施例中通过直方图匹配模型调节目标图像亮度的效果示意图，图像901对应于参考图像，图像902对应于目标图像，而图像903则对应于对图像902进行直方图匹配后得到的图像，可见采用直方图匹配的方式对目标图像进行亮度调节，能够实现对目标图像的亮度值进行较好调节的效果。
在一个实施例中，提供了一种图像亮度的调节装置，参考图11，图11为一个实施例中 图像亮度的调节装置的结构框图，该图像亮度的调节装置可以包括：
获取模块101，用于获取参考图像与目标图像的内容差异度，获取参考图像与目标图像的亮度差异度；
确定模块102，用于根据内容差异度和亮度差异度确定参考图像与目标图像之间的图像差异类型；
提取模块103，用于从多个亮度调节模型中提取与图像差异类型相适应的亮度调节模型；
调节模块104，用于通过亮度调节模型基于参考图像对目标图像的亮度进行调节。
在一个实施例中，获取模块101可以包括：
第一获取单元，用于获取参考图像的第一哈希值，获取目标图像的第二哈希值；根据第一哈希值和第二哈希值，计算参考图像与目标图像的汉明距离；根据汉明距离确定内容差异度。
在一个实施例中，获取模块101可以包括：
第二获取单元，用于获取参考图像的第一平均亮度值，获取目标图像的第二平均亮度值；根据第一平均亮度值和第二平均亮度值的差值，确定亮度差异度。
在一个实施例中，确定模块102可以包括：
比较单元，用于将内容差异度与第一阈值进行比较，将亮度差异度与第二阈值进行比较；
第一判断单元，用于若内容差异度小于第一阈值且亮度差异度小于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度小。
在一个实施例中，提取模块103可以包括：
第一调节单元，用于若图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度小，则从多个亮度调节模型中提取线性变换模型用于对目标图像的亮度进行调节。
在一个实施例中，还可以包括：
第二判断单元，用于若内容差异度大于第一阈值且亮度差异度小于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度小；
第三判断单元，用于若内容差异度大于第一阈值且亮度差异度大于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度大；
第四判断单元，用于若内容差异度小于第一阈值且亮度差异度大于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度大。
在一个实施例中，提取模块103可以包括：
第二调节单元，用于若图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度小、参考图像与目标图像的内容差异度大且亮度差异度大或参考图像与目标图像的内容差 异度小且亮度差异度大，则从多个亮度调节模型中提取直方图匹配模型用于对目标图像的亮度进行调节。
本申请的图像亮度的调节装置与本申请的图像亮度的调节方法一一对应，关于图像亮度的调节装置的具体限定可以参见上文中对于图像亮度的调节方法的限定，在上述图像亮度的调节方法的实施例阐述的技术特征及其有益效果均适用于图像亮度的调节装置的实施例中，在此不再赘述。上述图像亮度的调节装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。
在一个实施例中，提供了一种计算机设备，该计算机设备可以是终端，其内部结构图可以如图12所示，图12为一个实施例中计算机设备的内部结构图。该计算机设备包括通过系统总线连接的处理器、存储器、网络接口、显示屏和输入装置。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质、内存储器。该非易失性存储介质存储有操作系统和计算机程序。该内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该计算机设备的网络接口用于与外部的终端通过网络连接通信。该计算机程序被处理器执行时以实现一种图像亮度的调节方法。该计算机设备的显示屏可以是液晶显示屏或者电子墨水显示屏，该计算机设备的输入装置可以是显示屏上覆盖的触摸层，也可以是计算机设备外壳上设置的按键、轨迹球或触控板，还可以是外接的键盘、触控板或鼠标等。
本领域技术人员可以理解，图12中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
在一个实施例中，提供了一种计算机设备，包括处理器和存储器，所述存储器存储有计算机程序，所述处理器执行所述计算机程序时实现以下步骤：
获取参考图像与目标图像的内容差异度，获取参考图像与目标图像的亮度差异度；根据内容差异度和亮度差异度确定参考图像与目标图像之间的图像差异类型；从多个亮度调节模型中提取与图像差异类型相适应的亮度调节模型；通过亮度调节模型基于参考图像对目标图像的亮度进行调节。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：
获取参考图像的第一哈希值以及目标图像的第二哈希值；根据第一哈希值和第二哈希值计算参考图像与目标图像的汉明距离；根据汉明距离确定内容差异度。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：
获取参考图像的第一平均亮度值，获取目标图像的第二平均亮度值；根据第一平均亮度值和第二平均亮度值的差值，确定亮度差异度。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：
将内容差异度与第一阈值进行比较，将亮度差异度与第二阈值进行比较；若内容差异度小于第一阈值且亮度差异度小于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度小。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：
若图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度小，则从多个亮度调节模型中提取线性变换模型用于对目标图像的亮度进行调节。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：
若内容差异度大于第一阈值且亮度差异度小于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度小；若内容差异度大于第一阈值且亮度差异度大于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度大；若内容差异度小于第一阈值且亮度差异度大于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度大。
在一个实施例中，处理器执行计算机程序时还实现以下步骤：
若图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度小、参考图像与目标图像的内容差异度大且亮度差异度大或参考图像与目标图像的内容差异度小且亮度差异度大，则从多个亮度调节模型中提取直方图匹配模型用于对目标图像的亮度进行调节。
上述计算机设备，通过所述处理器上运行的计算机程序，能够基于图像之间的内容差异度和亮度差异度确定图像差异类型，进而结合图像差异类型适应性地选择不同的亮度调节模型对图像进行亮度调节，并利用与该图像差异类型相适应的亮度调节模型调节图像亮度，避免采用单一的亮度调节算法对参考图像进行亮度调节带来的图像亮度调节鲁棒性低的问题。
本领域普通技术人员可以理解实现如上任一项实施例所述的图像亮度的调节方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步DRAM(SDRAM)、双 数据率SDRAM(DDRSDRAM)、增强型SDRAM(ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus)直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。
据此，在一个实施例中提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被处理器执行时实现以下步骤：
获取参考图像与目标图像的内容差异度，获取参考图像与目标图像的亮度差异度；根据内容差异度和亮度差异度确定参考图像与目标图像之间的图像差异类型；从多个亮度调节模型中提取与图像差异类型相适应的亮度调节模型；通过亮度调节模型基于参考图像对目标图像的亮度进行调节。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：
获取参考图像的第一哈希值，获取目标图像的第二哈希值；根据第一哈希值和第二哈希值，计算参考图像与目标图像的汉明距离；根据汉明距离确定内容差异度。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：
获取参考图像的第一平均亮度值，获取目标图像的第二平均亮度值；根据第一平均亮度值和第二平均亮度值的差值，确定亮度差异度。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：
将内容差异度与第一阈值进行比较，将亮度差异度与第二阈值进行比较；若内容差异度小于第一阈值且亮度差异度小于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度小。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：
若图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度小，则从多个亮度调节模型中提取线性变换模型用于对目标图像的亮度进行调节。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：
若内容差异度大于第一阈值且亮度差异度小于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度小；若内容差异度大于第一阈值且亮度差异度大于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度大；若内容差异度小于第一阈值且亮度差异度大于第二阈值，则判断图像差异类型为参考图像与目标图像的内容差异度小且亮度差异度大。
在一个实施例中，计算机程序被处理器执行时还实现以下步骤：
若图像差异类型为参考图像与目标图像的内容差异度大且亮度差异度小、参考图像与目标图像的内容差异度大且亮度差异度大或参考图像与目标图像的内容差异度小且亮度差异度 大，则从多个亮度调节模型中提取直方图匹配模型用于对目标图像的亮度进行调节。
上述计算机可读存储介质，通过其存储的计算机程序，能够基于图像之间的内容差异度和亮度差异度确定图像差异类型，进而结合图像差异类型适应性地选择不同的亮度调节模型对图像进行亮度调节，并利用与该图像差异类型相适应的亮度调节模型调节图像亮度，避免采用单一的亮度调节算法对参考图像进行亮度调节带来的图像亮度调节鲁棒性低的问题。
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述。
Claims (10)
- 一种图像亮度的调节方法，包括步骤：获取参考图像与目标图像的内容差异度，获取所述参考图像与目标图像的亮度差异度；根据所述内容差异度和亮度差异度确定所述参考图像与目标图像之间的图像差异类型；从多个亮度调节模型中提取与所述图像差异类型相适应的亮度调节模型；通过所述亮度调节模型基于所述参考图像对所述目标图像的亮度进行调节。
- 根据权利要求1所述的图像亮度的调节方法，其中，所述获取参考图像与目标图像的内容差异度的步骤包括：获取所述参考图像的第一哈希值；获取所述目标图像的第二哈希值；根据所述第一哈希值和第二哈希值，计算所述参考图像与目标图像的汉明距离；根据所述汉明距离确定所述内容差异度。
- 根据权利要求1所述的图像亮度的调节方法，其中，所述获取所述参考图像与目标图像的亮度差异度的步骤包括：获取所述参考图像的第一平均亮度值；获取所述目标图像的第二平均亮度值；根据所述第一平均亮度值和第二平均亮度值的差值，确定所述亮度差异度。
- 根据权利要求1所述的图像亮度的调节方法，其中，所述根据所述内容差异度和亮度差异度确定所述参考图像与目标图像之间的图像差异类型的步骤包括：将所述内容差异度与第一阈值进行比较，将所述亮度差异度与第二阈值进行比较；若所述内容差异度小于第一阈值且所述亮度差异度小于第二阈值，则判断所述图像差异类型为所述参考图像与目标图像的内容差异度小且亮度差异度小。
- 根据权利要求4所述的图像亮度的调节方法，其中，所述从多个亮度调节模型中提取与所述图像差异类型相适应的亮度调节模型的步骤包括：若所述图像差异类型为所述参考图像与目标图像的内容差异度小且亮度差异度小，则从所述多个亮度调节模型中提取线性变换模型用于对所述目标图像的亮度进行调节。
- 根据权利要求4所述的图像亮度的调节方法，，还包括步骤：若所述内容差异度大于第一阈值且所述亮度差异度小于第二阈值，则判断所述图像差异类型为所述参考图像与目标图像的内容差异度大且亮度差异度小；若所述内容差异度大于第一阈值且所述亮度差异度大于第二阈值，则判断所述图像差异类型为所述参考图像与目标图像的内容差异度大且亮度差异度大；若所述内容差异度小于第一阈值且所述亮度差异度大于第二阈值，则判断所述图像差异类型为所述参考图像与目标图像的内容差异度小且亮度差异度大。
- 根据权利要求6所述的图像亮度的调节方法，其中，所述从多个亮度调节模型中提取与所述图像差异类型相适应的亮度调节模型的步骤包括：若所述图像差异类型为所述参考图像与目标图像的内容差异度大且亮度差异度小、所述参考图像与目标图像的内容差异度大且亮度差异度大或所述参考图像与目标图像的内容差异度小且亮度差异度大，则从所述多个亮度调节模型中提取直方图匹配模型用于对所述目标图像的亮度进行调节。
- 一种图像亮度的调节装置，包括：获取模块，用于获取参考图像与目标图像的内容差异度，获取所述参考图像与目标图像的亮度差异度；确定模块，用于根据所述内容差异度和亮度差异度确定所述参考图像与目标图像之间的图像差异类型；提取模块，用于从多个亮度调节模型中提取与所述图像差异类型相适应的亮度调节模型；调节模块，用于通过所述亮度调节模型基于所述参考图像对所述目标图像的亮度进行调节。
- 一种计算机设备，包括处理器和存储器，所述存储器存储有计算机程序，其中，所述处理器执行所述计算机程序时实现权利要求1至7任一项所述的图像亮度的调节方法的步骤。
- 一种计算机可读存储介质，其上存储有计算机程序，其中，所述计算机程序被处理器执行时实现权利要求1至7任一项所述的图像亮度的调节方法的步骤。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910121620.3A CN109859142B (zh) | 2019-02-19 | 2019-02-19 | 图像亮度的调节方法、装置、计算机设备和存储介质 |
| CN201910121620.3 | 2019-02-19 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2020168807A1 true WO2020168807A1 (zh) | 2020-08-27 |
Family
ID=66898228
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2019/126817 Ceased WO2020168807A1 (zh) | 2019-02-19 | 2019-12-20 | 图像亮度的调节方法、装置、计算机设备和存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109859142B (zh) |
| WO (1) | WO2020168807A1 (zh) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109859142B (zh) * | 2019-02-19 | 2021-06-22 | 广州视源电子科技股份有限公司 | 图像亮度的调节方法、装置、计算机设备和存储介质 |
| CN113031675B (zh) * | 2021-03-05 | 2022-03-29 | 中南大学 | 一种可见光自适应调控方法、系统、装置和存储介质 |
| CN113610934B (zh) * | 2021-08-10 | 2023-06-27 | 平安科技（深圳）有限公司 | 图像亮度调整方法、装置、设备及存储介质 |
| CN116630186B (zh) * | 2023-05-22 | 2026-04-07 | 陕西科技大学 | 用于模板匹配的图像亮度自适应调节方法及目标识别方法 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853498A (zh) * | 2009-03-31 | 2010-10-06 | 华为技术有限公司 | 图像合成方法及图像处理装置 |
| US20160189379A1 (en) * | 2014-12-25 | 2016-06-30 | Vivotek Inc. | Image calibrating method for stitching images and related camera and image processing system with image calibrating function |
| CN105976325A (zh) * | 2016-06-29 | 2016-09-28 | 上海小蚁科技有限公司 | 用于调整多个图像的明亮度的方法 |
| CN107862669A (zh) * | 2017-11-24 | 2018-03-30 | 深圳市安健科技股份有限公司 | 一种拼接图像亮度调节的方法及装置 |
| CN109194872A (zh) * | 2018-10-24 | 2019-01-11 | 深圳六滴科技有限公司 | 全景图像像素亮度校正方法、装置、全景相机和存储介质 |
| CN109859142A (zh) * | 2019-02-19 | 2019-06-07 | 广州视源电子科技股份有限公司 | 图像亮度的调节方法、装置、计算机设备和存储介质 |
Family Cites Families (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1244075C (zh) * | 2002-06-20 | 2006-03-01 | 成都威斯达芯片有限责任公司 | 可编程自适应的图像质量非线性增强处理装置及其处理方法 |
| AU2005202791A1 (en) * | 2004-07-15 | 2006-02-02 | Canon Kabushiki Kaisha | Image brightness adjustment using hyperbolic tone mappings |
| CN101441763B (zh) * | 2008-11-11 | 2012-05-16 | 浙江大学 | 基于颜色传递的多色调图像统一调整方法 |
| CN101651806A (zh) * | 2009-09-04 | 2010-02-17 | 青岛海信电器股份有限公司 | 一种画面亮度调节方法及电视机 |
| CN101655976B (zh) * | 2009-09-10 | 2011-11-09 | 浙江工商大学 | 基于控制点修正的多视角图像亮度校正方法 |
| US8922704B2 (en) * | 2010-09-01 | 2014-12-30 | Apple Inc. | Techniques for collection of auto-focus statistics |
| US8786625B2 (en) * | 2010-09-30 | 2014-07-22 | Apple Inc. | System and method for processing image data using an image signal processor having back-end processing logic |
| CN102930493B (zh) * | 2011-08-12 | 2017-08-08 | 索尼公司 | 防篡改的图像处理方法和装置 |
| TWI497320B (zh) * | 2011-11-14 | 2015-08-21 | Novatek Microelectronics Corp | 色調對應方法及影像處理裝置 |
| US8953882B2 (en) * | 2012-05-31 | 2015-02-10 | Apple Inc. | Systems and methods for determining noise statistics of image data |
| CN104299204A (zh) * | 2013-07-17 | 2015-01-21 | 王垒 | 直方图局部影像对比增强的方法与装置 |
| CN103617596A (zh) * | 2013-10-12 | 2014-03-05 | 中山大学 | 一种基于流型转换的图像色彩风格变换方法 |
| CN104572965A (zh) * | 2014-12-31 | 2015-04-29 | 南京理工大学 | 基于卷积神经网络的以图搜图系统 |
| CN104598883B (zh) * | 2015-01-21 | 2018-02-16 | 西安理工大学 | 一种多摄像机监控网络中目标再识别的方法 |
| CN104678963B (zh) * | 2015-02-03 | 2017-07-21 | 葛武 | 一种基于计算机视觉的采集仪表设备信息的系统及方法 |
| CN106448608B (zh) * | 2015-03-11 | 2020-05-12 | 海信视像科技股份有限公司 | 一种针对mura问题的屏幕亮度调整方法、装置及电视机 |
| CN105069042A (zh) * | 2015-07-23 | 2015-11-18 | 北京航空航天大学 | 基于内容的无人机侦察图像数据检索方法 |
| US10019925B2 (en) * | 2015-08-06 | 2018-07-10 | Mediatek Inc. | Electronic device capable of displaying and performing color compensation and color compensation method |
| US9857953B2 (en) * | 2015-11-17 | 2018-01-02 | Adobe Systems Incorporated | Image color and tone style transfer |
| CN106204513B (zh) * | 2016-08-15 | 2019-07-05 | 厦门美图之家科技有限公司 | 图像处理的方法、装置和系统 |
| CN108924525B (zh) * | 2018-06-06 | 2021-07-06 | 平安科技（深圳）有限公司 | 图像亮度调整方法、装置、计算机设备及存储介质 |
| CN108961175B (zh) * | 2018-06-06 | 2023-04-07 | 平安科技（深圳）有限公司 | 人脸亮度调整方法、装置、计算机设备及存储介质 |
-
2019
- 2019-02-19 CN CN201910121620.3A patent/CN109859142B/zh active Active
- 2019-12-20 WO PCT/CN2019/126817 patent/WO2020168807A1/zh not_active Ceased
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101853498A (zh) * | 2009-03-31 | 2010-10-06 | 华为技术有限公司 | 图像合成方法及图像处理装置 |
| US20160189379A1 (en) * | 2014-12-25 | 2016-06-30 | Vivotek Inc. | Image calibrating method for stitching images and related camera and image processing system with image calibrating function |
| CN105976325A (zh) * | 2016-06-29 | 2016-09-28 | 上海小蚁科技有限公司 | 用于调整多个图像的明亮度的方法 |
| CN107862669A (zh) * | 2017-11-24 | 2018-03-30 | 深圳市安健科技股份有限公司 | 一种拼接图像亮度调节的方法及装置 |
| CN109194872A (zh) * | 2018-10-24 | 2019-01-11 | 深圳六滴科技有限公司 | 全景图像像素亮度校正方法、装置、全景相机和存储介质 |
| CN109859142A (zh) * | 2019-02-19 | 2019-06-07 | 广州视源电子科技股份有限公司 | 图像亮度的调节方法、装置、计算机设备和存储介质 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109859142A (zh) | 2019-06-07 |
| CN109859142B (zh) | 2021-06-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110163235B (zh) | 图像增强模型的训练、图像增强方法、装置和存储介质 | |
| US11373275B2 (en) | Method for generating high-resolution picture, computer device, and storage medium | |
| CN108364267B (zh) | 图像处理方法、装置及设备 | |
| WO2020168807A1 (zh) | 图像亮度的调节方法、装置、计算机设备和存储介质 | |
| WO2021115242A1 (zh) | 一种超分辨率图像处理方法以及相关装置 | |
| US11367196B2 (en) | Image processing method, apparatus, and storage medium | |
| WO2020052476A1 (zh) | 特征点定位方法、存储介质和计算机设备 | |
| WO2019232860A1 (zh) | 图像亮度调整方法、装置、计算机设备及存储介质 | |
| CN108537155A (zh) | 图像处理方法、装置、电子设备及计算机可读存储介质 | |
| CN113179421B (zh) | 视频封面选择方法、装置、计算机设备和存储介质 | |
| CN106408518B (zh) | 图像融合方法、装置及终端设备 | |
| CN108846807A (zh) | 光效处理方法、装置、终端及计算机可读存储介质 | |
| CN116645527A (zh) | 图像识别方法、系统、电子设备和存储介质 | |
| WO2023151511A1 (zh) | 模型训练方法、图像去摩尔纹方法、装置及电子设备 | |
| WO2022194079A1 (zh) | 天空区域分割方法、装置、计算机设备和存储介质 | |
| CN113888429A (zh) | 图像提亮方法和装置、电子设备 | |
| CN111080571B (zh) | 摄像头遮挡状态检测方法、装置、终端和存储介质 | |
| WO2021169625A1 (zh) | 网络翻拍照片的检测方法、装置、计算机设备及存储介质 | |
| CN108513069A (zh) | 图像处理方法、装置、存储介质及电子设备 | |
| CN110688926B (zh) | 主体检测方法和装置、电子设备、计算机可读存储介质 | |
| CN111754521A (zh) | 图像处理方法和装置、电子设备及存储介质 | |
| CN108259767A (zh) | 图像处理方法、装置、存储介质及电子设备 | |
| CN109040579A (zh) | 一种拍摄控制方法、终端及计算机可读介质 | |
| CN111681201A (zh) | 图像处理方法、装置、计算机设备及存储介质 | |
| CN111860372B (zh) | 基于人工智能的表情包生成方法、装置、设备及存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19915611 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19915611 Country of ref document: EP Kind code of ref document: A1 |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 19915611 Country of ref document: EP Kind code of ref document: A1 |