WO2019205751A1 - 图像增强方法 - Google Patents

图像增强方法 Download PDF

Info

Publication number
WO2019205751A1
WO2019205751A1 PCT/CN2019/072072 CN2019072072W WO2019205751A1 WO 2019205751 A1 WO2019205751 A1 WO 2019205751A1 CN 2019072072 W CN2019072072 W CN 2019072072W WO 2019205751 A1 WO2019205751 A1 WO 2019205751A1
Authority
WO
WIPO (PCT)
Prior art keywords
target image
algorithm
image enhancement
image
brightness
Prior art date
Application number
PCT/CN2019/072072
Other languages
English (en)
French (fr)
Inventor
路萍萍
邱海
Original Assignee
青岛海信移动通信技术股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 青岛海信移动通信技术股份有限公司 filed Critical 青岛海信移动通信技术股份有限公司
Publication of WO2019205751A1 publication Critical patent/WO2019205751A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00Image enhancement or restoration
    • G06T5/73Deblurring; Sharpening

Definitions

  • Embodiments of the present disclosure relate to the field of image processing technologies, and more particularly to image enhancement processing of a defogged image.
  • methods of image enhancement processing mainly include, for example, an automatic gradation method, an automatic contrast method, and the like.
  • the automatic gradation method first determines the upper/lower limit ratio of the image color, calculates a histogram of the image; then sets the pixel value of the pixel whose pixel value is lower than the lower limit ratio in the image to 0, and the pixel whose pixel value is higher than the upper limit ratio The value is set to 255 and the pixel values of the pixels whose pixel values are between the lower scale ratio and the upper scale ratio are linearly transformed.
  • the fixed color threshold cannot automatically adapt to the image.
  • calculating the histogram takes a long time.
  • Embodiments of the present disclosure provide an image enhancement method, apparatus, device, and storage medium for improving image enhancement effects on a defogged image and reducing complexity of image enhancement processing.
  • a first aspect of the embodiments of the present disclosure provides an image enhancement method, including:
  • Image enhancement processing is performed on the target image based on the target image enhancement algorithm.
  • the multiple preset image enhancement algorithms include: a linear transformation algorithm, an automatic transformation algorithm, a logarithmic transformation algorithm, and a gamma transformation algorithm.
  • the brightness characteristic of the target image includes an average brightness of the target image as a whole
  • a target image enhancement algorithm that is adapted to the brightness feature of the target image from a plurality of preset image enhancement algorithms, including:
  • the logarithmic transformation algorithm or the gamma transformation algorithm is the target image enhancement algorithm.
  • the brightness characteristic of the target image includes respective average brightness of different regions on the target image.
  • the image enhancement processing is repeatedly performed on the target image as a whole based on a plurality of target image enhancement algorithms respectively corresponding to different regions on the target image.
  • a second aspect of the embodiments of the present disclosure provides an image enhancement apparatus, including:
  • a defogging module configured to perform a defogging process on the first image to obtain a target image
  • a determining module configured to determine, according to a preset policy, a target image enhancement algorithm that is adapted to a brightness feature of the target image from among a plurality of preset image enhancement algorithms;
  • a processing module configured to perform image enhancement processing on the target image based on the target image enhancement algorithm.
  • the multiple preset image enhancement algorithms include: a linear transformation algorithm, an automatic transformation algorithm, a logarithmic transformation algorithm, and a gamma transformation algorithm.
  • the brightness characteristic of the target image includes an average brightness of the target image as a whole
  • the determining module includes:
  • a first determining submodule configured to determine that the automatic transform algorithm is a target image enhancement algorithm when an average brightness of the target image as a whole is less than a first preset threshold
  • the second determining submodule is configured to determine that the logarithmic transform algorithm or the gamma transform algorithm is the target image enhancement algorithm when the average brightness of the target image as a whole is greater than the first preset threshold and less than the second preset threshold.
  • the brightness characteristic of the target image includes an average brightness of different regions on the target image
  • the processing module includes:
  • a first processing submodule configured to perform image enhancement processing on the region based on a target image enhancement algorithm that is adapted to an average brightness of the region for different regions on the target image;
  • the second processing submodule is configured to repeatedly perform image enhancement processing on the target image as a whole based on a plurality of target image enhancement algorithms respectively corresponding to different regions on the target image.
  • a third aspect of the embodiments of the present disclosure provides a mobile terminal, including:
  • a memory for storing machine executable instructions and image data
  • the method of the first aspect described above is implemented when the processor executes the machine executable instructions.
  • a fourth aspect of embodiments of the present disclosure provides a computer readable non-volatile storage medium comprising instructions that, when executed on a processor, implement the method of the first aspect described above.
  • FIG. 1 is a flowchart of an image enhancement method according to an embodiment of the present disclosure.
  • FIG. 2 is a flowchart of an image enhancement method according to an embodiment of the present disclosure.
  • FIG. 3 is a flowchart of an image enhancement method according to an embodiment of the present disclosure.
  • FIG. 4 is a schematic structural diagram of an image enhancement apparatus according to an embodiment of the present disclosure.
  • FIG. 5 is a schematic structural diagram of an image enhancement apparatus according to an embodiment of the present disclosure.
  • FIG. 6 is a schematic structural diagram of an image enhancement apparatus according to an embodiment of the present disclosure.
  • FIG. 7 is a schematic structural diagram of a terminal device according to an embodiment of the present disclosure.
  • image defogging methods may have image enhancement based methods and physical model based methods.
  • image defogging algorithms with dark channel priors.
  • Embodiments of the present disclosure provide an image enhancement method.
  • the method can be performed by an image enhancement device that is mounted on a terminal having image processing functions, such as a cell phone, a traffic camera, and the like.
  • FIG. 1 is a flowchart of an image enhancement method according to an embodiment of the present disclosure. As shown in FIG. 1 , the method includes the following steps.
  • Step 101 Perform a defogging process on the first image to obtain a target image.
  • the name of the “first image” in this embodiment is only used to distinguish the image to be defogged from other images, and does not have other meanings.
  • the target image refers to an image obtained after the first image has undergone dehazing.
  • the preliminary image defogging process may be performed on the first image according to a preset image defogging algorithm to obtain a target image after the defogging process.
  • the target image is subjected to image enhancement processing using an image enhancement method according to an embodiment of the present disclosure to obtain a desired image.
  • the image dehazing algorithm employed is not limited.
  • the image enhancement method of the present disclosure can be applied to almost all images obtained after dehazing.
  • Step 102 Determine, according to a preset policy, a target image enhancement algorithm that is adapted to the brightness feature of the target image from the plurality of preset image enhancement algorithms.
  • the luminance characteristics of the target image involved in the embodiment include average luminance information of the entire target image, or average luminance information of different regions on the target image.
  • the image enhancement algorithms involved in this embodiment include, but are not limited to, a linear transformation algorithm, an automatic transformation algorithm, a logarithmic transformation algorithm, and a gamma transformation algorithm.
  • the image enhancement algorithm according to this embodiment can be understood as a grayscale transformation algorithm.
  • the gradation transformation algorithm refers to a method of changing the gradation value of each pixel in the source image pixel by pixel according to a certain transformation condition according to a certain transformation relationship.
  • the gradation transformation algorithm can be divided into a linear transformation algorithm and a nonlinear transformation algorithm.
  • linear transformation algorithm can be expressed by the following expression (1):
  • x represents any pixel in the target image
  • I(x) represents the gray value of the pixel x.
  • the gradation value of the linearly transformed pixel x is represented, a represents the slope of the linear transformation function of the above formula (1), b represents the vertical intercept, and a and b are constants.
  • the nonlinear transform algorithm includes, for example, an automatic transform algorithm, a logarithmic transform algorithm, a gamma transform algorithm, and the like.
  • the gamma transform algorithm may be represented by the following expression (2):
  • I(x) represents the gray value of the pixel point x in the target image
  • c and r are normal numbers.
  • logarithmic transformation algorithm may be represented by the following expression (3):
  • the logarithmic transformation algorithm can map a narrow gray value in the target image to a wide gray range, and map a wide grayscale interval to a narrower range.
  • the grayscale interval which extends the value of the dark pixel, compresses the value of the high grayscale, and enhances the low grayscale detail in the image.
  • the automatic transformation algorithm may be represented by the following expression (4):
  • the amount of gray value increase of the pixel in the target image is symmetric with respect to 0.5, and the growth amount gradually increases in the interval of [0, 0.5], and the growth amount becomes smaller in the interval of [0.5, 1], thereby realizing The image as a whole becomes brighter.
  • the preset policy referred to in this embodiment refers to a correspondence between a preset image enhancement algorithm and a target image brightness feature.
  • the image enhancement process may be performed on the target image by using an automatic transformation algorithm.
  • the image enhancement processing may be performed on the target image by using a logarithmic transformation algorithm or a gamma transformation algorithm.
  • the image of the target image may be performed by using a linear transformation algorithm.
  • an image brightness feature can also correspond to multiple image enhancement algorithms, thereby using multiple image enhancements.
  • the algorithm implements image enhancement processing on the target image.
  • Step 103 Perform image enhancement processing on the target image based on the target image enhancement algorithm.
  • the target image is obtained by performing a defogging process on the first image, and the target image enhancement algorithm that is adapted to the brightness feature of the target image is determined from the plurality of preset image enhancement algorithms based on the preset strategy, thereby The target image enhancement algorithm performs image enhancement processing on the target image.
  • a plurality of image enhancement algorithms are preset for different image brightness features.
  • the target image obtained after the defogging process is subjected to image enhancement processing, it may be targeted from a plurality of presets according to a preset strategy.
  • An image enhancement algorithm adapted to the brightness characteristics of the target image is selected in the image enhancement algorithm to process the target image. Therefore, it is possible to achieve a better image enhancement effect without setting the upper/lower limit ratio of the image color, and it is not necessary to perform histogram calculation, which reduces the complexity of the image enhancement processing.
  • FIG. 2 is a flowchart of an image enhancement method according to an embodiment of the present disclosure. As shown in FIG. 2, on the basis of the embodiment of FIG. 1, the method includes the following steps.
  • Step 201 Acquire an average brightness of the entire target image.
  • Step 202a If the average brightness of the target image as a whole is less than a first preset threshold, determine that the automatic transform algorithm is a target image enhancement algorithm.
  • the automatic transformation algorithm can be expressed by the following expression:
  • Step 202b If the average brightness of the target image as a whole is greater than the first preset threshold and less than the second preset threshold, determine that the logarithmic transformation algorithm or the gamma transformation algorithm is the target image enhancement algorithm.
  • the second preset threshold is greater than the first preset threshold, and the values of the first preset threshold and the second preset threshold may be set as needed.
  • the overall brightness of the target image is not particularly dark, and the brightness of the target image may be increased as appropriate. Good performance. And since both the gamma transform algorithm and the logarithmic transform algorithm can significantly expand the low gray value in the image and display more low gray value details, the gamma transform algorithm or the logarithmic transform algorithm can be used in this embodiment.
  • the image enhancement processing is performed on the target image whose average brightness is greater than the first preset threshold and less than the second preset threshold, thereby obtaining a better image enhancement effect. Among them, compared with the gamma conversion algorithm, the logarithmic transformation algorithm can achieve better results.
  • Step 203 Perform image enhancement processing on the target image based on the target image enhancement algorithm.
  • the low gray value in the target image can be made.
  • the portion is significantly enhanced to achieve better image enhancement.
  • FIG. 3 is a flowchart of an image enhancement method according to an embodiment of the present disclosure. As shown in FIG. 3, on the basis of the embodiment of FIG. 1, the method includes the following steps.
  • Step 301 Acquire an average brightness of different regions on the target image.
  • Step 302 Determine, for each region on the target image, an image enhancement algorithm that is adapted to the average brightness of the region from the plurality of preset image enhancement algorithms based on the preset policy.
  • Target image enhancement algorithm Determine, for each region on the target image, an image enhancement algorithm that is adapted to the average brightness of the region from the plurality of preset image enhancement algorithms based on the preset policy.
  • Step 303 Perform image enhancement processing on the target image based on a target image enhancement algorithm respectively determined for each region.
  • the target image enhancement algorithm determined in this embodiment may be multiple.
  • the implementation includes the following.
  • an image enhancement process may be performed on the region based on a target image enhancement algorithm that is commensurate with the average brightness of the region for each region on the target image until all regions are processed and stopped.
  • the target image may be subjected to multiple image enhancement processes based on the determined plurality of target image enhancement algorithms. For example, it is assumed that the target image includes a first area and a second area, wherein the average brightness of the first area is less than a third preset threshold, and the average brightness of the second area is greater than a fourth preset threshold, wherein the fourth preset threshold Greater than the third preset threshold.
  • the linear transformation algorithm and the logarithmic transformation algorithm are target image enhancement algorithms.
  • the first image enhancement processing may be performed on the target image based on one of the linear transformation algorithm and the logarithmic transformation algorithm, and then the second image enhancement processing is performed on the target image based on the other of the two. , get the final image.
  • the third preset threshold is used to determine whether the image is too dark
  • the fourth preset threshold is used to determine that the image is too bright.
  • the target image includes an area that is too dark (ie, a first area) and an area that is too bright (ie, a second area).
  • the present embodiment can perform image enhancement processing on the target image by using a linear transformation algorithm.
  • the parameter b in the linear transformation algorithm (1) described above may be set to a different value for the first region and the second region, respectively, and then the first region and the second region are respectively subjected to gradation transformation processing.
  • the enhancement effect is limited, considering the logarithm.
  • the transform can perform the enhancement processing on the region. Therefore, in this embodiment, after the image enhancement processing is performed on the target image by using the linear transform algorithm, the logarithmic transformation algorithm is used to compare the brightness between the first region and the second region. The area between the areas is further enhanced in brightness to achieve an overall improvement in image brightness.
  • the defects of the single image enhancement algorithm can be avoided.
  • the brightness effect of the target image as a whole is enhanced.
  • FIG. 4 is a schematic structural diagram of an image enhancement apparatus according to an embodiment of the present disclosure. As shown in FIG. 4, the apparatus includes the following modules.
  • the defogging module 41 is configured to perform a defogging process on the first image to obtain a target image.
  • the determining module 42 is configured to determine, from the plurality of preset image enhancement algorithms, a target image enhancement algorithm that is adapted to the brightness feature of the target image based on the preset policy.
  • the processing module 43 is configured to perform image enhancement processing on the target image based on the target image enhancement algorithm.
  • the multiple preset image enhancement algorithms include: a linear transformation algorithm, an automatic transformation algorithm, a logarithmic transformation algorithm, and a gamma transformation algorithm.
  • the image enhancement apparatus provided in this embodiment can perform the method of the embodiment of FIG. 1. Other implementation modes and beneficial effects are similar, and details are not described herein again.
  • FIG. 5 is a schematic structural diagram of an image enhancement apparatus according to an embodiment of the present disclosure. As shown in FIG. 5, on the basis of the embodiment of FIG. 4, the brightness characteristic of the target image includes an average brightness of the target image as a whole;
  • the determining module 42 includes:
  • the first determining sub-module 421 is configured to determine, when the average brightness of the target image as a whole is less than a first preset threshold, that the automatic transform algorithm is a target image enhancement algorithm;
  • the second determining sub-module 422 is configured to determine that the logarithmic transform algorithm or the gamma transform algorithm is the target image enhancement algorithm when the average brightness of the target image is greater than the first preset threshold and less than the second preset threshold.
  • the image enhancement apparatus provided in this embodiment can be used to perform the method of the embodiment of FIG. 2, and the execution manner and the beneficial effects are similar, and details are not described herein again.
  • the brightness characteristic of the target image includes respective areas of different areas on the target image.
  • the average brightness; the processing module 43 includes:
  • a first processing sub-module 431, configured to perform image enhancement processing on the region based on a target image enhancement algorithm that is adapted to an average brightness of the region for different regions on the target image;
  • the second processing sub-module 432 is configured to repeatedly perform image enhancement processing on the target image as a whole based on a plurality of target image enhancement algorithms respectively corresponding to different regions on the target image.
  • the image enhancement apparatus provided in this embodiment can be used to perform the method of the embodiment of FIG. 3, and the execution manner and the beneficial effects are similar, and details are not described herein again.
  • FIG. 7 is a schematic structural diagram of a terminal device according to an embodiment of the present disclosure.
  • the terminal device may be, for example, a mobile terminal such as a mobile phone, or may be a traffic camera or the like.
  • a terminal device 700 includes:
  • a memory 702 configured to store computer executable instructions and image data
  • the embodiment of the present disclosure further provides a computer readable non-volatile storage medium, including computer instructions, which can implement the technical solutions of the foregoing method embodiments when the computer instructions are run on a processor.
  • the storage medium may be a magnetic disk, an optical disk, a read only memory (ROM), or a random access memory (RAM).
  • the various functional units in the embodiments of the present disclosure may be integrated into one processing module, or may be physically separated by individual units, or two or more units may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated modules, if implemented in the form of software functional modules and sold or used as separate products, may also be stored in a computer readable storage medium.
  • the storage medium mentioned above may be a read only memory, a magnetic disk or an optical disk or the like.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)
  • Apparatus For Radiation Diagnosis (AREA)

Abstract

一种图像增强方法,该方法包括:对第一图像进行去雾处理,获得目标图像(101);基于预设策略,从多个预设的图像增强算法中,确定与所述目标图像的亮度特征相适应的目标图像增强算法(102);基于所述目标图像增强算法,对所述目标图像进行图像增强处理(103)。

Description

图像增强方法
相关申请的交叉引用
本专利申请要求于2018年4月26日提交的、申请号为201810387527.2、发明名称为“图像增强方法、装置、设备及存储介质”的中国专利申请的优先权,该申请的全文以引用的方式并入本文中。
技术领域
本公开实施例涉及图像处理技术领域,尤其涉及对去雾图像的图像增强处理。
背景技术
通常,在对有雾图像进行去雾处理后,图像的整体亮度偏低,需要进行图像增强处理。目前图像增强处理的方法主要包括例如自动色阶法、自动对比度法等。自动色阶方法首先确定图像颜色的上/下限比率,计算图像的直方图;然后将图像中像素值低于下限比率的像素的像素值设置为0,将像素值高于上限比率的像素的像素值设置为255,并对像素值位于下限比例与上限比例之间的像素的像素值进行线性变换。然而,由于不同的图像像素颜色值分布区间不同,固定的颜色阈值不能自动适应图像。另外,计算直方图需要耗费较长的时间。
发明内容
本公开实施例提供一种图像增强方法、装置、设备及存储介质,用以提高对去雾图像的图像增强效果,降低图像增强处理的复杂度。
本公开实施例第一方面提供一种图像增强方法,包括:
对第一图像进行去雾处理,获得目标图像;
基于预设策略,从多个预设的图像增强算法中,确定与所述目标图像的亮度特征相适应的目标图像增强算法;
基于所述目标图像增强算法,对所述目标图像进行图像增强处理。
可选的,所述多个预设的图像增强算法,包括:线性变换算法、自动变换算法、对数变换算法、伽马变换算法。
可选的,所述目标图像的亮度特征包括所述目标图像整体的平均亮度;
所述基于预设策略,从预设的多个图像增强算法中,确定与所述目标图像的亮度特征相适应的目标图像增强算法,包括:
若所述目标图像整体的平均亮度小于第一预设阈值,则确定所述自动变换算法为目标图像增强算法;
若所述目标图像整体的平均亮度大于第一预设阈值,小于第二预设阈值,则确定对数变换算法或伽马变换算法为目标图像增强算法。
可选的,所述目标图像的亮度特征包括所述目标图像上不同区域各自的平均亮度。
所述基于所述目标图像增强算法,对所述目标图像进行图像增强处理,包括:
针对所述目标图像上的不同区域,基于与所述区域的平均亮度相适应的目标图像增强算法对所述区域进行图像增强处理;
或者
基于分别与所述目标图像上不同区域相对应的多个目标图像增强算法对所述目标图像整体反复进行多次图像增强处理。
本公开实施例第二方面提供一种图像增强装置,包括:
去雾模块,用于对第一图像进行去雾处理,获得目标图像;
确定模块,用于基于预设策略,从多个预设的图像增强算法中,确定与所述目标图像的亮度特征相适应的目标图像增强算法;
处理模块,用于基于所述目标图像增强算法,对所述目标图像进行图像增强处理。
可选的,所述多个预设的图像增强算法,包括:线性变换算法、自动变换算法、对数变换算法、伽马变换算法。
可选的,所述目标图像的亮度特征包括所述目标图像整体的平均亮度;
所述确定模块,包括:
第一确定子模块,用于在所述目标图像整体的平均亮度小于第一预设阈值时,确定所述自动变换算法为目标图像增强算法;
第二确定子模块,用于在所述目标图像整体的平均亮度大于第一预设阈值,小于第二预设阈值时,确定对数变换算法或伽马变换算法为目标图像增强算法。
可选的,所述目标图像的亮度特征包括所述目标图像上不同区域各自的平均亮度;
所述处理模块,包括:
第一处理子模块,用于针对所述目标图像上的不同区域,基于与所述区域的平均亮度相适应的目标图像增强算法对所述区域进行图像增强处理;
或者
第二处理子模块,用于基于分别与所述目标图像上不同区域对应的多个目标图像增强算法对所述目标图像整体反复进行多次图像增强处理。
本公开实施例第三方面提供一种移动终端,包括:
处理器;
存储器,用于存储机器可执行指令以及图像数据;
当所述处理器执行所述机器可执行指令时,实现上述第一方面所述的方法。
本公开实施例第四方面提供一种计算机可读非易失性存储介质,包括指令,当所述指令在处理器上运行时,可以实现上述第一方面所述的方法。
附图说明
为了更清楚地说明本公开实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本公开的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。
图1是本公开实施例提供的一种图像增强方法的流程图。
图2是本公开实施例提供的一种图像增强方法的流程图。
图3是本公开实施例提供的一种图像增强方法的流程图。
图4是本公开实施例提供的一种图像增强装置的结构示意图。
图5是本公开实施例提供的一种图像增强装置的结构示意图。
图6是本公开实施例提供的一种图像增强装置的结构示意图。
图7是本公开实施例提供的一种终端设备的结构示意图。
具体实施方式
在雾、霾之类的恶劣天气下采集的图像会由于大气散射的作用而被严重降质,物体特征难以辨认,视觉效果变差,会影响图像后期的处理。因此,需要图像去雾技术来增强或修复,以改善图像的视觉效果和方便后期处理。通常,图像去雾方法可以有基于图像增强的方法和基于物理模型的方法。基于图像增强的去雾方法有多种,例如有暗通道先验的图像去雾算法。根据通常的基于图像增强的图像去雾算法对图像进行去雾处理后得到的图像的整体亮度偏低,视觉效果不佳。
本公开实施例提供一种图像增强方法。该方法可以由一种图像增强装置来执行,该装置安装在具有图像处理功能的终端上,例如手机、交通摄像头等。参见图1,图1是本公开实施例提供的一种图像增强方法的流程图,如图1所示,该方法包括如下步骤。
步骤101、对第一图像进行去雾处理,获得目标图像。
其中,本实施例中对于“第一图像”的命名仅是用于将待去雾处理的图像与其他图像区分开来,并不具备其他含义。目标图像是指第一图像经过去雾处理后得到的图像。
这里,可以根据预设的图像去雾算法对第一图像进行初步的图像去雾处理,获得去雾处理后的目标图像。在后续步骤中,利用根据本公开实施例的图像增强方法对该目标图像进行图像增强处理,以获得期望图像。在本公开实施例中,并不对所采用的图像去雾算法进行限制,实际上,本公开的图像增强方法可以适用于几乎所有经去雾处理后得到的图像。
步骤102、基于预设策略,从多个预设的图像增强算法中,确定与所述目标图像的亮度特征相适应的目标图像增强算法。
本实施例中涉及的目标图像的亮度特征包括目标图像整体的平均亮度信息,或者目标图像上不同区域的平均亮度信息。本实施例涉及的图像增强算法包括但不局限于包括:线性变换算法、自动变换算法、对数变换算法和伽马变换算法。
本实施例涉及的图像增强算法可以理解为是一种灰度变换算法。灰度变换算法是指根据某种目标条件按照一定变换关系逐像素点改变源图像中每一个像素的灰度值的方法。该灰度变换算法可以分为线性变换算法和非线性变换算法。
其中,线性变换算法可以用如下表达式(1)进行表示:
Figure PCTCN2019072072-appb-000001
其中,x代表目标图像中的任一像素点,I(x)代表该像素点x的灰度值,
Figure PCTCN2019072072-appb-000002
表示经线性变换后的该像素点x的灰度值,a表示如上式(1)的线性变换函数的斜率,b表示纵截距,a,b均为常数。当a=1且b≠0时,经过该线性变换,目标图像整体的灰度值发生了偏移,也就是目标图像整体的亮度变亮或变暗,不会改变目标图像的对比度;当a>1时,可以增加图像的对比度。
其中,非线性变换算法例如有自动变换算法、对数变换算法、伽马变换算法等。
可选的,可用如下表达式(2)表示伽马变换算法:
Figure PCTCN2019072072-appb-000003
其中,I(x)表示目标图像中的像素点x的灰度值,
Figure PCTCN2019072072-appb-000004
表示经伽马变换后的该像素点的灰度值,c、r为正常数。其中,当r<1时,r值越小,对目标图像中低灰度值的像素点的灰度范围扩展越明显,使得像素的动态范围增加,显示的图像更加清晰。
可选的,可用如下表达式(3)表示对数变换算法:
Figure PCTCN2019072072-appb-000005
其中,d是一个常数,对数变换算法能够将目标图像中范围较窄的低灰度值映射到范围较宽的灰度区间,同时将范围较宽的高灰度值区间映射为较窄的灰度区间,从而扩展了暗像素的值,压缩了高灰度的值,能够对图像中低灰度细节进行增强。
可选的,可用如下表达式(4)表示自动变换算法:
Figure PCTCN2019072072-appb-000006
在执行自动变换算法时,需要将目标图像中像素的灰度值归一化到[0,1]之间。在自动变换算法中,目标图像中像素的灰度值增长量关于0.5对称,在[0,0.5]区间内增长量逐渐变大,在[0.5,1]区间内增长量逐渐变小,从而实现图像整体变亮。
本实施例中所称的预设策略是指预先设定的图像增强算法与目标图像亮度特征之间的对应关系。比如,当目标图像的平均亮度小于第一预设阈值时可以采用自动变换算法对目标图像进行图像增强处理。当目标图像的平均亮度大于第一预设阈值,小于第二预设阈值时,可以采用对数变换算法或伽马变换算法对目标图像进行图像增强处理。当目标图像上存在某一区域的平均亮度小于第四阈值,存在另一区域的平均亮度大于第五阈值时,其中,第五阈值大于第四阈值,则可以采用线性变换算法对目标图像进行图像增强处理。当然上述仅为示例说明而不是唯一限定。实际上,图像亮度特征与图像增强算 法之间的对应关系可以根据需要进行设定,比如,在一种设计中,一种图像亮度特征也可以对应多种图像增强算法,从而使用多种图像增强算法实现对目标图像的图像增强处理。
步骤103、基于所述目标图像增强算法,对所述目标图像进行图像增强处理。
本实施例,通过对第一图像进行去雾处理,获得目标图像,基于预设策略从多个预设的图像增强算法中,确定与目标图像的亮度特征相适应的目标图像增强算法,从而基于目标图像增强算法,对目标图像进行图像增强处理。由于本实施例针对不同的图像亮度特征预先设置了多个图像增强算法,在对去雾处理后得到的目标图像进行图像增强处理时,可以根据预设策略有针对性的从多个预设的图像增强算法中选择一个与目标图像亮度特征相适应的图像增强算法对目标图像进行处理。因而,不需要设定图像颜色的上/下限比率就可以实现较好的图像增强效果,并且无需进行直方图计算,降低了图像增强处理的复杂度。
图2是本公开实施例提供的一种图像增强方法的流程图,如图2所示,在图1实施例的基础上,该方法包括以下步骤。
步骤201、获取目标图像整体的平均亮度。
步骤202a、若所述目标图像整体的平均亮度小于第一预设阈值,则确定所述自动变换算法为目标图像增强算法。
本实施例中当目标图像的平均亮度小于第一预设阈值时,则认为目标图像整体亮度较暗,此时采用自动变换算法对目标图像进行图像增强处理,能够大幅提高目标图像整体的亮度,并且由上述实施例可知,自动变换算法可以由如下表达式表示:
Figure PCTCN2019072072-appb-000007
因此,在利用自动变换算法对目标图像进行图像增强处理时,无需另外设置参数,操作方便,能够提高图像增强处理的效率。
步骤202b、若所述目标图像整体的平均亮度大于第一预设阈值,小于第二预设阈值,则确定对数变换算法或伽马变换算法为目标图像增强算法。
其中,第二预设阈值大于第一预设阈值,第一预设阈值和第二预设阈值的值可以根据需要进行设定。
本实施例中,当目标图像整体的平均亮度大于第一预设阈值小于第二预设阈值时, 则认为目标图像的整体亮度不是特别暗,此时只要适当提高目标图像的亮度即可获得较好的表现效果。并且由于伽马变换算法和对数变换算法都能够对图像中低灰度值进行明显的扩展,显示更多低灰度值细节,因此,本实施例可以采用伽马变换算法或对数变换算法对平均亮度大于第一预设阈值小于第二预设阈值的目标图像进行图像增强处理,从而获得较好的图像增强效果。其中,相比伽马变换算法,采用对数变换算法能够取得更好的效果。
步骤203、基于所述目标图像增强算法,对所述目标图像进行图像增强处理。
本实施例,通过在目标图像整体的平均亮度值大于第一阈值小于第二阈值时,采用伽马变换算法或对数变换算法对目标图像进行图像增强处理,能够使得目标图像中低灰度值的部分得到显著的增强,从而获得较好的图像增强效果。
图3是本公开实施例提供的一种图像增强方法的流程图,如图3所示,在图1实施例的基础上,该方法包括如下步骤。
步骤301、获取所述目标图像上不同区域各自的平均亮度。
步骤302、针对所述目标图像上的每个区域,基于预设策略,从多个预设的图像增强算法中,确定出与所述区域的平均亮度相适应的图像增强算法作为针对该区域的目标图像增强算法。
步骤303、基于针对各个区域分别确定的目标图像增强算法,对所述目标图像进行图像增强处理。
由于不同区域的平均亮度可能不同,因此,本实施例中确定出的目标图像增强算法可能是多个。在基于多个目标图像增强算法对目标图像进行图像增强处理时,实现方式包括如下几种。
在第一种实现方式中,可以针对目标图像上的每个区域,基于与该区域的平均亮度相适应的目标图像增强算法对该区域进行图像增强处理,直至全部区域处理完成后停止。
在另一种实现方式中,可以基于确定出的多个目标图像增强算法对目标图像进行多次图像增强处理。举例来说,假设目标图像包括第一区域和第二区域,其中第一区域的平均亮度小于第三预设阈值,第二区域的平均亮度大于第四预设阈值,其中,第四预设阈值大于第三预设阈值。此时确定线性变换算法和对数变换算法为目标图像增强算法。进一步的,可以先基于线性变换算法、对数变换算法二者中的一种对目标图像进行第一 次图像增强处理,再基于二者中的另一种对目标图像进行第二次图像增强处理,得到最终的图像。
具体的,上述第三预设阈值是用于判断图像是否过暗的界限,第四预设阈值是用于判断图像过亮的界限。当图像上某一区域的平均亮度小于第三预设阈值时,表明该区域的亮度过暗;当图像上另一区域的平均亮度大于第四预设阈值时,表明该区域的亮度过亮。基于此,当目标图像上包括上述涉及的第一区域和第二区域时,则说明目标图像上包括过暗的区域(即第一区域)和过亮的区域(即第二区域)。此时如果采用自动变换算法、伽马变换算法或者对数变换算法的话对第一区域和第二区域的亮度改善效果较小,而线性变换算法却能够明显增强图像中亮度过暗或者过强区域的显示效果,并且能够适当提升图像中其他区域的显示效果,因此,本实施例可以采用线性变换算法对目标图像进行图像增强处理。具体地,可以分别针对第一区域和第二区域将上述线性变换算法(1)中的参数b设置为不同的值,然后分别对第一区域和第二区域进行灰度变换处理。
但是若只采用采用线性变换算法对上述目标图像进行图像增强处理的话,虽然能够对亮度介于第一区域和第二区域之间的区域进行一定增强处理,但是其增强效果有限,考虑到对数变换能够较好的对该区域进行增强处理,因此,本实施例还可以在使用线性变换算法对目标图像进行图像增强处理之后再通过对数变换算法对亮度介于第一区域和第二区域之间的区域进行进一步的亮度增强,从而达到整体提升图像亮度的目的。
当然上述举例仅是为了示例说明而不是对本公开的唯一限定。
本实施例,通过基于目标图像上不同区域的平均亮度确定多个目标图像增强算法,再基于多个目标图像增强算法对目标图像进行图像增强处理,能够,避免采用单一图像增强算法所存在的缺陷,使得目标图像整体的亮度效果得到增强。
图4是本公开实施例提供的一种图像增强装置的结构示意图,如图4所示,该装置包括以下模块。
去雾模块41,用于对第一图像进行去雾处理,获得目标图像。
确定模块42,用于基于预设策略,从多个预设的图像增强算法中,确定与所述目标图像的亮度特征相适应的目标图像增强算法。
处理模块43,用于基于所述目标图像增强算法,对所述目标图像进行图像增强处理。
可选的,所述多个预设的图像增强算法,包括:线性变换算法、自动变换算法、对 数变换算法、伽马变换算法。
本实施例提供的图像增强装置,能够执行图1实施例的方法,其他执行方式和有益效果类似,在这里不再赘述。
图5是本公开实施例提供的一种图像增强装置的结构示意图,如图5所示,在图4实施例的基础上,所述目标图像的亮度特征包括所述目标图像整体的平均亮度;所述确定模块42,包括:
第一确定子模块421,用于在所述目标图像整体的平均亮度小于第一预设阈值时,确定所述自动变换算法为目标图像增强算法;
第二确定子模块422,用于在所述目标图像整体的平均亮度大于第一预设阈值,小于第二预设阈值时,确定对数变换算法或伽马变换算法为目标图像增强算法。
本实施例提供的图像增强装置,能够用于执行图2实施例的方法,其执行方式和有益效果类似,在这里不再赘述。
图6是本公开实施例提供的一种图像增强装置的结构示意图,如图6所示,在图4实施例的基础上,所述目标图像的亮度特征包括所述目标图像上不同区域各自的平均亮度;所述处理模块43,包括:
第一处理子模块431,用于针对所述目标图像上的不同区域,基于与所述区域的平均亮度相适应的目标图像增强算法对所述区域进行图像增强处理;
或者
第二处理子模块432,用于基于分别与所述目标图像上不同区域对应的多个目标图像增强算法对所述目标图像整体反复进行多次图像增强处理。
本实施例提供的图像增强装置,能够用于执行图3实施例的方法,其执行方式和有益效果类似,在这里不再赘述。
图7是本公开实施例提供的一种终端设备的结构示意图,该终端设备例如可以是手机等移动终端,也可以是交通摄像头等。如图7所示,一种终端设备700,包括:
处理器701;
存储器702,用于存储计算机可执行指令以及图像数据;
当所述处理器执行所述计算机可执行指令时,可以实现上述方法实施例的技术方 案。
本公开实施例还提供一种计算机可读非易失性存储介质,包括计算机指令,当所述计算机指令在处理器上运行时,可以实现上述方法实施例的技术方案。
最后需要说明的是,本领域普通技术人员可以理解上述实施例方法中的全部或者部分流程,是可以通过计算机程序来指令相关的硬件完成,所述的程序可存储于一计算机可读存储介质中,该程序在执行时,可包括如上述各方法的实施例的流程。其中,所述的存储介质可以为磁盘、光盘、只读存储记忆体(ROM)或随机存储记忆体(RAM)等。
本公开实施例中的各个功能单元可以集成在一个处理模块中,也可以是各个单元单独的物理存在,也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现,也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现,并作为独立的产品销售或使用时,也可以存储在一个计算机可读存储介质中。上述提到的存储介质可以是只读存储器、磁盘或光盘等。
以上各实施例仅用以说明本公开的技术方案,而非对其限制;尽管参照前述各实施例对本公开进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分或者全部技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本公开各实施例技术方案的范围。

Claims (12)

  1. 一种图像增强方法,包括:
    对第一图像进行去雾处理,获得目标图像;
    基于预设策略,从多个预设的图像增强算法中,确定与所述目标图像的亮度特征相适应的目标图像增强算法;
    基于所述目标图像增强算法,对所述目标图像进行图像增强处理。
  2. 根据权利要求1所述的方法,所述多个预设的图像增强算法,包括:线性变换算法、自动变换算法、对数变换算法和伽马变换算法中的多者。
  3. 根据权利要求2所述的方法,所述目标图像的亮度特征包括所述目标图像整体的平均亮度;
    所述基于预设策略,从预设的多个图像增强算法中,确定与所述目标图像的亮度特征相适应的目标图像增强算法,包括:
    若所述目标图像整体的平均亮度小于第一预设阈值,则确定所述自动变换算法为目标图像增强算法;
    若所述目标图像整体的平均亮度大于第一预设阈值,小于第二预设阈值,则确定对数变换算法或伽马变换算法为目标图像增强算法。
  4. 根据权利要求1所述的方法,所述目标图像的亮度特征包括所述目标图像上不同区域各自的平均亮度;
    所述基于所述目标图像增强算法,对所述目标图像进行图像增强处理,包括:
    针对所述目标图像上的不同区域,基于与所述区域的平均亮度相适应的目标图像增强算法对所述区域进行图像增强处理。
  5. 根据权利要求1所述的方法,所述目标图像的亮度特征包括所述目标图像上不同区域各自的平均亮度;
    所述基于所述目标图像增强算法,对所述目标图像进行图像增强处理,包括:
    基于分别与所述目标图像上不同区域相对应的多个目标图像增强算法对所述目标图像整体反复进行多次图像增强处理。
  6. 一种图像增强装置,包括:
    去雾模块,用于对第一图像进行去雾处理,获得目标图像;
    确定模块,用于基于预设策略,从多个预设的图像增强算法中,确定与所述目标图像的亮度特征相适应的目标图像增强算法;
    处理模块,用于基于所述目标图像增强算法,对所述目标图像进行图像增强处理。
  7. 根据权利要求6所述的装置,其特征在于,所述多个预设的图像增强算法,包括:线性变换算法、自动变换算法、对数变换算法、伽马变换算法。
  8. 根据权利要求7所述的装置,其特征在于,所述目标图像的亮度特征包括所述目标图像整体的平均亮度;
    所述确定模块,包括:
    第一确定子模块,用于在所述目标图像整体的平均亮度小于第一预设阈值时,确定所述自动变换算法为目标图像增强算法;
    第二确定子模块,用于在所述目标图像整体的平均亮度大于第一预设阈值,小于第二预设阈值时,确定对数变换算法或伽马变换算法为目标图像增强算法。
  9. 根据权利要求6所述的装置,其特征在于,所述目标图像的亮度特征包括所述目标图像上不同区域各自的平均亮度;
    所述处理模块,包括:
    第一处理子模块,用于针对所述目标图像上的不同区域,基于与所述区域的平均亮度相适应的目标图像增强算法对所述区域进行图像增强处理。
  10. 根据权利要求6所述的装置,其特征在于,所述目标图像的亮度特征包括所述目标图像上不同区域各自的平均亮度;
    所述处理模块,包括:第二处理子模块,用于基于分别与所述目标图像上不同区域对应的多个目标图像增强算法对所述目标图像整体反复进行多次图像增强处理。
  11. 一种终端设备,包括:
    处理器;
    存储器,用于存储计算机可执行指令;
    所述计算机可执行指令被所述处理器执行时,实现上述权利要求1-5中任一项所述的方法。
  12. 一种计算机可读非易失性存储介质,其上存储有计算机指令,所述计算机指令被处理器执行时实现权利要求1到5所述的方法。
PCT/CN2019/072072 2018-04-26 2019-01-17 图像增强方法 WO2019205751A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810387527.2 2018-04-26
CN201810387527.2A CN108665428B (zh) 2018-04-26 2018-04-26 图像增强方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2019205751A1 true WO2019205751A1 (zh) 2019-10-31

Family

ID=63781049

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/072072 WO2019205751A1 (zh) 2018-04-26 2019-01-17 图像增强方法

Country Status (2)

Country Link
CN (1) CN108665428B (zh)
WO (1) WO2019205751A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114298916A (zh) * 2021-11-11 2022-04-08 电子科技大学 一种基于灰度拉伸和局部增强的X-Ray图像增强方法
CN114936981A (zh) * 2022-06-10 2022-08-23 重庆尚优科技有限公司 一种基于云平台的场所扫码登记***

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108665428B (zh) * 2018-04-26 2022-11-11 青岛海信移动通信技术股份有限公司 图像增强方法、装置、设备及存储介质
CN110047052A (zh) * 2019-04-25 2019-07-23 哈尔滨工业大学 一种基于fpga的强光抑制夜视增强方法
CN110689655A (zh) * 2019-09-17 2020-01-14 南昌大学 一种基于人脸识别的宿舍门禁管理一体化***
CN112906712B (zh) * 2021-03-02 2023-05-02 湖南金烽信息科技有限公司 一种基于光强分析的神经网络图像预处理方法
CN112967273B (zh) * 2021-03-25 2021-11-16 北京的卢深视科技有限公司 图像处理方法、电子设备及存储介质
CN113744325B (zh) * 2021-09-06 2024-04-26 中国地质科学院勘探技术研究所 一种基于图像识别技术的液位检测装置及方法

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102663683A (zh) * 2012-03-14 2012-09-12 华平信息技术股份有限公司 图像增强方法及***
CN106412383A (zh) * 2015-07-31 2017-02-15 阿里巴巴集团控股有限公司 视频图像的处理方法和装置
CN107403421A (zh) * 2017-08-10 2017-11-28 杭州联吉技术有限公司 一种图像去雾方法、存储介质及终端设备
CN107644409A (zh) * 2017-09-28 2018-01-30 深圳Tcl新技术有限公司 图像增强方法、显示装置及计算机可读存储介质
CN108665428A (zh) * 2018-04-26 2018-10-16 青岛海信移动通信技术股份有限公司 图像增强方法、装置、设备及存储介质

Family Cites Families (34)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100590529B1 (ko) * 2003-11-04 2006-06-15 삼성전자주식회사 영상의 국부적 휘도 향상 방법 및 장치와 컴퓨터프로그램을 저장하는 컴퓨터로 읽을 수 있는 기록 매체
US7428333B2 (en) * 2004-01-23 2008-09-23 Old Dominion University Visibility improvement in color video stream
JP2009510587A (ja) * 2005-09-30 2009-03-12 コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ 画像ディテール強調
TWI340586B (en) * 2006-11-21 2011-04-11 Wintek Corp Adjusting apparatus for enhancing the contrast of image and method thereof
CN101472113B (zh) * 2007-12-29 2012-05-30 深圳艾科创新微电子有限公司 一种数字图像亮度对比度增强装置
CN101271523B (zh) * 2008-05-21 2010-06-02 北京中星微电子有限公司 用于人脸检测的图像亮度调节控制方法和装置
US8396324B2 (en) * 2008-08-18 2013-03-12 Samsung Techwin Co., Ltd. Image processing method and apparatus for correcting distortion caused by air particles as in fog
CN101350933B (zh) * 2008-09-02 2011-09-14 广东威创视讯科技股份有限公司 一种基于图像感应器拍摄显示屏幕的亮度调整方法
CN101510302B (zh) * 2009-03-25 2014-05-21 北京中星微电子有限公司 一种图像增强方法和装置
CN101770639B (zh) * 2010-01-14 2012-05-23 北京航空航天大学 一种低照度图像增强方法
CN102456223B (zh) * 2010-10-27 2014-05-07 珠海扬智电子有限公司 图像细节增强与缩放装置,以及图像细节增强与缩放方法
CN102158699B (zh) * 2011-03-28 2012-12-12 广州市聚晖电子科技有限公司 一种带有图像增强功能的嵌入式视频压缩编码***
CN102202163B (zh) * 2011-05-13 2013-01-23 成都西图科技有限公司 一种监控视频的自适应增强方法及其装置
CN102611828B (zh) * 2012-01-11 2014-03-26 四川大学 一种雾天连续视频图像实时性增强处理***
CN102957919A (zh) * 2012-11-14 2013-03-06 四川长虹电器股份有限公司 一种数字图像亮度增强方法
CN102968769B (zh) * 2012-11-27 2015-07-22 宁波盈芯信息科技有限公司 一种图像一致性增强装置
CN103854255A (zh) * 2012-11-29 2014-06-11 比亚迪股份有限公司 图像增强方法及装置
CN103002291B (zh) * 2012-12-06 2014-12-03 杭州藏愚科技有限公司 一种摄像机宽动态图像增强方法及装置
CN103024300B (zh) * 2012-12-25 2015-11-25 华为技术有限公司 一种高动态范围图像显示方法及装置
CN103106644B (zh) * 2013-02-02 2016-04-27 南京理工大学 克服彩色图像非均匀光照的自适应画质增强方法
CN104715453A (zh) * 2013-12-12 2015-06-17 苏州长风航空电子有限公司 一种分区域处理的图像增强方法及电路
CN103996168B (zh) * 2014-01-21 2017-02-01 公安部第一研究所 一种基于区域自适应处理的x射线安全检查图像增强方法
CN105335933B (zh) * 2014-05-27 2017-11-17 上海贝卓智能科技有限公司 一种图像对比度增强方法和装置
CN105513015B (zh) * 2014-09-24 2018-04-03 南京理工大学 一种雾天图像的清晰化处理方法
CN104463807B (zh) * 2014-12-24 2017-05-10 深圳市安健科技股份有限公司 X射线图像对比度自适应增强方法与***
CN104517272B (zh) * 2014-12-31 2017-11-03 深圳市天视通电子科技有限公司 一种图像增强方法及装置
US9288458B1 (en) * 2015-01-31 2016-03-15 Hrl Laboratories, Llc Fast digital image de-hazing methods for real-time video processing
JP6365355B2 (ja) * 2015-03-09 2018-08-01 オムロン株式会社 画像生成装置および画像生成方法
CN104867115A (zh) * 2015-04-09 2015-08-26 南京邮电大学 一种去雾后图像色偏检测与图像增强方法
CN105809638A (zh) * 2016-03-01 2016-07-27 深圳Tcl数字技术有限公司 图像处理方法及装置
CN106023100B (zh) * 2016-05-12 2020-03-31 珠海市杰理科技股份有限公司 图像宽动态范围压缩方法及装置
CN106485652A (zh) * 2016-10-12 2017-03-08 青岛海信电器股份有限公司 对比度调整方法及装置
CN107203982A (zh) * 2017-06-26 2017-09-26 郑州云海信息技术有限公司 一种图像处理方法及装置
CN107451979B (zh) * 2017-08-08 2022-11-01 腾讯科技(深圳)有限公司 一种图像处理方法、装置和存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102663683A (zh) * 2012-03-14 2012-09-12 华平信息技术股份有限公司 图像增强方法及***
CN106412383A (zh) * 2015-07-31 2017-02-15 阿里巴巴集团控股有限公司 视频图像的处理方法和装置
CN107403421A (zh) * 2017-08-10 2017-11-28 杭州联吉技术有限公司 一种图像去雾方法、存储介质及终端设备
CN107644409A (zh) * 2017-09-28 2018-01-30 深圳Tcl新技术有限公司 图像增强方法、显示装置及计算机可读存储介质
CN108665428A (zh) * 2018-04-26 2018-10-16 青岛海信移动通信技术股份有限公司 图像增强方法、装置、设备及存储介质

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114298916A (zh) * 2021-11-11 2022-04-08 电子科技大学 一种基于灰度拉伸和局部增强的X-Ray图像增强方法
CN114936981A (zh) * 2022-06-10 2022-08-23 重庆尚优科技有限公司 一种基于云平台的场所扫码登记***
CN114936981B (zh) * 2022-06-10 2023-07-07 重庆尚优科技有限公司 一种基于云平台的场所扫码登记***

Also Published As

Publication number Publication date
CN108665428A (zh) 2018-10-16
CN108665428B (zh) 2022-11-11

Similar Documents

Publication Publication Date Title
WO2019205751A1 (zh) 图像增强方法
CN109801240B (zh) 一种图像增强方法以及图像增强装置
US9710715B2 (en) Image processing system, image processing device, and image processing method
US8165419B2 (en) Histogram stretching apparatus and histogram stretching method for enhancing contrast of image
WO2016206087A1 (zh) 一种低照度图像处理方法和装置
US9842382B2 (en) Method and device for removing haze in single image
WO2020038124A1 (zh) 图像对比度增强方法、装置、设备及存储介质
CN110570360B (zh) 一种基于Retinex的鲁棒和全面的低质量光照图像增强方法
WO2019100675A1 (zh) 一种分区背光控制方法及其装置
US9704227B2 (en) Method and apparatus for image enhancement
US10609303B2 (en) Method and apparatus for rapid improvement of smog/low-light-level image using mapping table
WO2021218603A1 (zh) 图像处理方法及投影***
WO2019101005A1 (zh) 像素补偿方法、装置和终端设备
CN114511479A (zh) 图像增强方法和装置
US10019645B2 (en) Image processing apparatus and method, and electronic equipment
CN111192205A (zh) 一种图像去雾方法、***和计算机可读存储介质
CN111598010B (zh) 动态障碍物检测方法、装置、电子设备及存储介质
CN113449730A (zh) 图像处理方法、***、自动行走设备及可读存储介质
US20200160492A1 (en) Image Adjustment Method and Device, Image Display Method and Device, Non-Transitory Storage Medium
CN114998122A (zh) 一种低照度图像增强方法
Tao et al. Nonlinear image enhancement to improve face detection in complex lighting environment
KR102277005B1 (ko) 비지도 학습을 이용한 저조도 영상 처리 방법 및 장치
CN113808045B (zh) 一种图像亮度调节方法及装置
CN113379631B (zh) 一种图像去雾的方法及装置
US20230162473A1 (en) Image processing method

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: 19793563

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 08.02.2021)

122 Ep: pct application non-entry in european phase

Ref document number: 19793563

Country of ref document: EP

Kind code of ref document: A1