[go: up one dir, main page]

CN114202484A - Image detail enhancement and its ASIC implementation method and system - Google Patents

Image detail enhancement and its ASIC implementation method and system Download PDF

Info

Publication number
CN114202484A
CN114202484A CN202111542239.8A CN202111542239A CN114202484A CN 114202484 A CN114202484 A CN 114202484A CN 202111542239 A CN202111542239 A CN 202111542239A CN 114202484 A CN114202484 A CN 114202484A
Authority
CN
China
Prior art keywords
image
detail enhancement
difference
gain coefficient
filtering
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.)
Pending
Application number
CN202111542239.8A
Other languages
Chinese (zh)
Inventor
张梦楠
詹志康
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Saifang Technology Co ltd
Original Assignee
Guangdong Saifang Technology Co ltd
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 Guangdong Saifang Technology Co ltd filed Critical Guangdong Saifang Technology Co ltd
Priority to CN202111542239.8A priority Critical patent/CN114202484A/en
Publication of CN114202484A publication Critical patent/CN114202484A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20172—Image enhancement details

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

The invention relates to the technical field of image processing, in particular to an image detail enhancement and ASIC implementation method and system, which comprises the following steps: s1 initialization, inputting the image to be processed, and carrying out parameter-configurable weighted mean filtering on the input image; s2, calculating the difference between the current central pixel point and the average filtering output, and looking up a table to obtain a difference gain coefficient and a gray scale gain coefficient; and S3, combining the weighted average filtering output in S1 and the difference output and the two gain coefficients in S2, and calculating a detail enhancement output result. The method can adjust the detail gain according to the pixel value of the current pixel point, and effectively solves the problems of overshoot and undershoot in the image detail enhancement; different filter coefficients can be selected according to different application scenes, different gain curves are selected according to different application scenes, and detail enhancement is only carried out on a Y channel in a YUV domain, so that the calculation amount is effectively reduced, and ASIC implementation is facilitated.

Description

Image detail enhancement and ASIC implementation method and system thereof
Technical Field
The invention relates to the technical field of image processing, in particular to an image detail enhancement method and an ASIC implementation method and system.
Background
The images are affected by the imaging environment, the imaging equipment and the transmission system in the process of acquisition and transmission, so that the finally received images contain noise, detail information is difficult to identify, and the accuracy of subsequent image processing is greatly hindered. The purpose of image detail enhancement is to improve the image quality, purposefully enhance the recognizable capability of certain target information according to the subsequent image processing requirement, express the interested target characteristic information in the image more finely, and inhibit noise.
The prior art cannot adjust the detail gain according to the current pixel value; the problems of "overshoot" and "low overshoot" cannot be solved; different filter coefficients cannot be selected according to different application scenes; the calculation amount is too large to be beneficial to ASIC realization. Thus, provided herein is an image detail enhancement and ASIC implementation method and system thereof.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses an image detail enhancement method and an ASIC implementation method and system thereof, which are used for solving the problem that the prior art can not adjust the detail gain according to the current pixel value; the problems of "overshoot" and "low overshoot" cannot be solved; different filter coefficients cannot be selected according to different application scenes; the calculated amount is too large, which is not beneficial to the realization of ASIC.
The invention is realized by the following technical scheme:
in a first aspect, the present invention provides an image detail enhancement method and an ASIC implementation method thereof, including the following steps:
s1 initialization, inputting the image to be processed, and carrying out parameter-configurable weighted mean filtering on the input image;
s2, calculating the difference between the current central pixel point and the average filtering output, and looking up a table to obtain a difference gain coefficient and a gray scale gain coefficient;
and S3, combining the weighted average filtering output in S1 and the difference output and the two gain coefficients in S2, and calculating a detail enhancement output result.
Furthermore, in the method, when the average filtering is weighted, the average filtering coefficient obtains different filtering coefficients according to different positions of the pixel points in the filtering window, and meanwhile, the filtering coefficients are adjusted in real time according to different application scenes.
Furthermore, in the method, when the weighted average filtering is performed, the filter coefficients are all integer multiples of 2, and the multiplication is replaced by a shifting mode in the ASIC implementation.
Further, in the method, the calculation procedure of the weighted mean filtering is as follows:
Figure BDA0003414680280000021
M＝WSUM∑PJWJ
WSUM＝1/∑WJ
wherein, XJFor the shift value, W, of each pixel point within the filtering windowJIs the filter coefficient for each pixel within the filter window.
Further, in the method, the flow of calculating the filtering difference value is as follows:
LDIFF＝P-M
wherein, P is the central pixel point in the filtering window.
Furthermore, the method uses unsharp masking, and the enhancement of the high frequency information is achieved by first high-pass filtering and multiplying by a scaling factor, and then adding the result to the original image.
Furthermore, in the method, the difference gain coefficient FD and the gray gain coefficient FI are obtained by looking up a table, and the detail enhancement output is as follows:
Y＝Y+LDIFF*FI*FD。
in a second aspect, the present invention provides an image detail enhancement and ASIC implementation system for implementing the image detail enhancement and ASIC implementation method of the first aspect, comprising an image caching module, a data selector, a gray scale gain coefficient look-up table module, a configurable weighted mean filtering module, a difference gain coefficient look-up table module, and an output calculation module.
Furthermore, the image caching module is configured to cache image data, and generate a 7x7 neighborhood of the current pixel point;
the data selector is used for selecting the central pixel point participating in the detail enhancement and the neighborhood pixel point data thereof;
the gray gain coefficient lookup module is used for looking up a table according to the Y channel value of the current pixel point to obtain a gray gain coefficient;
the configurable weighted mean filtering module is used for calculating to obtain a filtered pixel value and a difference value between an original image and a filtered image;
the difference gain coefficient table look-up module is used for looking up a table to obtain a difference gain coefficient according to the image difference obtained by the configurable weighted mean filter;
and the output calculation is used for calculating to obtain an output image according to the Y channel value of the central pixel, the image difference value, the gray gain coefficient and the difference gain coefficient.
Furthermore, the table entry of the gray scale gain coefficient look-up table module can be configured by a CPU or other main controllers;
the filter coefficient of the configurable weighted mean filtering module can be configured by a CPU or other main controllers;
the table entry of the difference gain coefficient table look-up module can be configured by a CPU or other main controller.
The invention has the beneficial effects that:
the method can adjust the detail gain according to the pixel value of the current pixel point, and effectively solves the problems of overshoot and undershoot in the image detail enhancement; the invention can select different filter coefficients according to different application scenes, select different gain curves according to different application scenes, and only perform detail enhancement on a Y channel in a YUV domain, thereby effectively reducing the calculation amount and being beneficial to the realization of an ASIC.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a diagram of the image detail enhancement and its ASIC implementation of the present invention;
FIG. 2 is a table look-up of the delta gain factor according to an embodiment of the present invention;
FIG. 3 is a table-look-up of gray scale gain factors according to an embodiment of the present invention;
FIG. 4 is a system diagram of image detail enhancement and ASIC implementation thereof, in accordance with an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Referring to fig. 1, the present embodiment provides an image detail enhancement method and an ASIC implementation method thereof, including the following steps:
s1 initialization, inputting the image to be processed, and carrying out parameter-configurable weighted mean filtering on the input image;
s2, calculating the difference between the current central pixel point and the average filtering output, and looking up a table to obtain a difference gain coefficient and a gray scale gain coefficient;
and S3, combining the weighted average filtering output in S1 and the difference output and the two gain coefficients in S2, and calculating a detail enhancement output result.
The embodiment can adjust the detail gain according to the pixel value of the current pixel point; the problems of 'overshoot' and 'undershoot' in the image detail enhancement can be effectively solved.
According to the embodiment, different filter coefficients can be selected according to different application scenes; different gain curves can be selected according to different application scenarios.
The embodiment only performs detail enhancement on the Y channel in the YUV domain, thereby effectively reducing the calculation amount and being beneficial to ASIC realization.
Example 2
In a specific implementation level, this embodiment provides a weighted mean filtering and a filtering difference calculation, in this embodiment, the image detail enhancement usually performs detail enhancement on RGB components in an RGB domain, respectively, and this detail enhancement method can achieve a better effect, but has a large calculation amount and is easy to distort colors.
Therefore, the embodiment performs detail enhancement in the YUV domain and performs enhancement only in the Y channel, which can effectively reduce the amount of calculation without causing color distortion.
W0 W1 W2 W3 W2 W1 W0
W1 W4 W5 W6 W5 W4 W1
W2 W5 W7 W8 W7 W5 W2
W3 W6 W8 W9 W8 W6 W3
W2 W5 W7 W8 W7 W5 W2
W1 W4 W5 W6 W5 W4 W1
W0 W1 W2 W3 W2 W1 W0
In this scheme, as the window size of the above-mentioned mean filtering is 7x7, the coefficient of each pixel point in the window is as shown in the above table, and the calculation flow of the weighted mean filtering is:
Figure BDA0003414680280000051
M＝WSUM∑PJWJ
WSUM＝1/∑WJ
the calculation process of the filtering difference value comprises the following steps:
LDIFF＝P-M
wherein, XJFor the shift value, W, of each pixel point within the filtering windowJThe filter coefficient of each pixel in the filter window is shown, and P is a central pixel point in the filter window.
In this embodiment, the same filter coefficient is used for all the pixels in the filter window in consideration of the conventional mean filtering, and the filter coefficient is fixed, so that different filter coefficients cannot be obtained by optimization according to different application scenarios.
Therefore, the average filter coefficient of the embodiment obtains different filter coefficients according to different positions of the pixel points in the filter window, and the filter coefficients can be different according to the different positions. The filtering coefficient is adjusted in real time by applying the scene, and the aluminum rod performance of the system is improved.
Since the filter coefficients of the present embodiment are all integer multiples of 2, the multiplication can be replaced by a shifting manner in ASIC implementation, thereby further reducing the calculation amount.
Example 3
In a specific implementation level, the embodiment provides a gain coefficient table lookup and detail enhancement output, and a classic algorithm of image enhancement in the embodiment is an UNsharp Masking (UNsharp Masking) technique.
In the embodiment, high-frequency information can be enhanced by high-pass filtering and multiplying by a scaling coefficient, and adding the result to the original image.
Although the present embodiment is simple to implement and can be applied to most application scenarios, the output image will have significant "overshoot" or "low-overshoot" artifacts. In order to eliminate "overshoot" or "low-shoot" artifacts, the "overshoot" or "low-shoot" artifacts must be properly controlled.
In this embodiment, a table is respectively looked up according to the calculated filtering difference and the pixel value of the current pixel point, so as to obtain a filtering gain coefficient and a gray gain coefficient. The strength of detail enhancement is controlled by two gain coefficients, so that the problem of overshoot or low overshoot can be effectively solved.
The difference gain coefficient lookup table of this embodiment is shown in fig. 2, and the gray gain coefficient lookup table is shown in fig. 3, and according to the two curves, the difference gain coefficient FD and the gray gain coefficient FI can be obtained by lookup.
As can be seen from fig. 2 and 3, when the difference value and the gray value are too large or too small, both gain coefficients are constant and small, so that the problem of "overshoot" or "undershoot" can be effectively solved. Meanwhile, in the [0,1] area, along with the increase of the difference value and the gray value, the gain coefficient is increased, the image details can be effectively enhanced, and in the [1,3] area, along with the increase of the difference value and the gray value, the gain coefficient is gradually reduced, so that the overshoot is prevented.
Finally, the output of the detail enhancement is:
Y＝Y+LDIFF*FI*FD。
example 4
Referring to fig. 4, the embodiment provides an image detail enhancement and ASIC implementation system thereof, which includes an image buffer module, a data selector, a gray gain coefficient look-up table module, a configurable weighted average filtering module, a difference gain coefficient look-up table module, and an output calculation module.
The image caching module of the embodiment is used for caching image data and generating a 7x7 neighborhood of a current pixel point;
the data selector is used for selecting a central pixel point participating in detail enhancement and neighborhood pixel point data thereof;
the gray scale gain coefficient lookup module is used for looking up a table according to the Y channel value of the current pixel point to obtain a gray scale gain coefficient;
the configurable weighted mean filtering module is configured to calculate a filtered pixel value and a difference value between an original image and a filtered image;
the difference gain coefficient lookup module is used for looking up a table to obtain a difference gain coefficient according to the image difference obtained by the configurable weighted mean filter;
and the output calculation is used for calculating to obtain an output image according to the Y channel value of the central pixel, the image difference value, the gray gain coefficient and the difference gain coefficient.
The table entry of the gray scale gain coefficient table look-up module of the embodiment can be configured by a CPU or other main controllers;
the filter coefficient of the weighted average filtering module configured in the embodiment can be configured by a CPU or other main controller;
the table entry of the difference gain coefficient table look-up module of this embodiment can be configured by the CPU or other main controller.
In conclusion, the method can adjust the detail gain according to the pixel value of the current pixel point, and effectively solves the problems of overshoot and undershoot in the image detail enhancement; the invention can select different filter coefficients according to different application scenes, select different gain curves according to different application scenes, and only perform detail enhancement on a Y channel in a YUV domain, thereby effectively reducing the calculation amount and being beneficial to the realization of an ASIC.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1.一种图像细节增强及其ASIC实现方法，其特征在于，所述方法包括以下步骤：1. a kind of image detail enhancement and ASIC realization method thereof, is characterized in that, described method comprises the following steps: S1初始化，输入待处理图像，对输入图像进行参数可配的加权均值滤波；S1 initialization, input the image to be processed, and perform weighted mean filtering with configurable parameters on the input image; S2计算当前中心像素点与均值滤波输出之间的差值，并查表得到差值增益系数和灰度增益系数；S2 calculates the difference between the current center pixel and the mean filter output, and looks up the table to obtain the difference gain coefficient and the grayscale gain coefficient; S3结合S1中加权均值滤波输出及S2中差值输出和两个增益系数，计算细节增强输出结果。S3 combines the weighted mean filter output in S1 and the difference output in S2 and two gain coefficients to calculate the output result of detail enhancement. 2.根据权利要求1所述的一种图像细节增强及其ASIC实现方法，其特征在于，所述方法中，加权均值滤波时，均值滤波系数根据像素点在滤波窗口内位置的不同而得到不同的滤波系数，同时滤波系数根据不同的应用场景实时调整滤波系数。2. a kind of image detail enhancement and ASIC realization method thereof according to claim 1, is characterized in that, in described method, during weighted mean filtering, mean filtering coefficient obtains different according to the difference of pixel position in filtering window At the same time, the filter coefficient is adjusted in real time according to different application scenarios. 3.根据权利要求2所述的一种图像细节增强及其ASIC实现方法，其特征在于，所述方法中，加权均值滤波时，滤波系数均为2的整数倍，在ASIC实现中用移位的方式代替乘法计算。3. a kind of image detail enhancement and ASIC realization method thereof according to claim 2, is characterized in that, in described method, during weighted mean filtering, filter coefficient is the integer multiple of 2, in ASIC realization, use shift instead of multiplication. 4.根据权利要求2所述的一种图像细节增强及其ASIC实现方法，其特征在于，所述方法中，加权均值滤波的计算流程为：4. a kind of image detail enhancement and ASIC realization method thereof according to claim 2, is characterized in that, in described method, the calculation flow of weighted mean filtering is:
Figure FDA0003414680270000011
Figure FDA0003414680270000011
 M＝WSUM∑PJWJ M=W SUM ∑P J W J WSUM＝1/∑WJ W SUM = 1/∑W J 其中，XJ为滤波窗口内每个像素点的移位值，WJ为滤波窗口内每个像素的滤波系数。Among them, X J is the shift value of each pixel in the filtering window, and W J is the filtering coefficient of each pixel in the filtering window. 5.根据权利要求4所述的一种图像细节增强及其ASIC实现方法，其特征在于，所述方法中，滤波差值的计算流程为：5. a kind of image detail enhancement and ASIC realization method thereof according to claim 4, is characterized in that, in described method, the calculation flow of filter difference value is: LDIFF＝P-M LDIFF =PM 其中，P为滤波窗口内的中心像素点。Among them, P is the central pixel in the filtering window. 6.根据权利要求1所述的一种图像细节增强及其ASIC实现方法，其特征在于，所述方法使用非锐化掩码，首先通过高通滤波并与缩放系数相乘，其结果再与原始图像相加，对高频信息进行增强。6. a kind of image detail enhancement according to claim 1 and its ASIC realization method, it is characterized in that, described method uses unsharp mask, at first by high-pass filtering and multiplying with scaling factor, its result and original The images are added to enhance the high frequency information. 7.根据权利要求1所述的一种图像细节增强及其ASIC实现方法，其特征在于，所述方法中，查表得到差值增益系数FD和灰度增益系数FI，细节增强的输出为：7. a kind of image detail enhancement and ASIC realization method thereof according to claim 1, is characterized in that, in described method, look-up table obtains difference gain coefficient FD and gamma gain coefficient FI, and the output of detail enhancement is: Y′＝Y+LDIFF*FI*FD。Y'=Y+ LDIFF *FI*FD. 8.一种图像细节增强及其ASIC实现系统，所述系统用于实现如权利要求1-7任一项所述的图像细节增强及其ASIC实现方法，其特征在于，包括图像缓存模块、数据选择器、灰度增益系数查表模块、可配置加权均值滤波模块、差值增益系数查表模块及输出计算模块。8. a kind of image detail enhancement and ASIC realization system thereof, described system is used to realize the image detail enhancement and ASIC realization method thereof as described in any one of claim 1-7, it is characterized in that, comprise image cache module, data Selector, gray gain coefficient lookup table module, configurable weighted mean filter module, difference gain coefficient lookup table module and output calculation module. 9.根据权利要求8所述的一种图像细节增强及其ASIC实现系统，其特征在于，9. a kind of image detail enhancement and ASIC realization system thereof according to claim 8, is characterized in that, 所述图像缓存模块，用于缓存图像数据，同时产生当前像素点的7x7邻域；The image cache module is used to cache image data and generate a 7×7 neighborhood of the current pixel at the same time; 所述数据选择器，用于选择参与细节增强的中心像素点及其邻域像素点数据；The data selector is used to select the center pixel point and its neighboring pixel point data participating in the detail enhancement; 所述灰度增益系数查表模块，用于根据当前像素点的Y通道值，查表得到灰度增益系数；The gamma gain coefficient look-up table module is used for looking up the table to obtain the gamma gain coefficient according to the Y channel value of the current pixel; 所述可配置加权均值滤波模块，用于计算得到滤波后的像素值，以及原始图像与滤波后图像的差值；The configurable weighted mean filter module is used to calculate the filtered pixel value and the difference between the original image and the filtered image; 所述差值增益系数查表模块，用于根据可配置加权均值滤波器得到的图像差值，查表得到差值增益系数；The difference gain coefficient look-up table module is used to look up the table to obtain the difference gain coefficient according to the image difference obtained by the configurable weighted mean filter; 输出计算，用于根据中心像素Y通道值、图像差值、灰度增益系数、差值增益系数，计算得出输出图像。The output calculation is used to calculate the output image according to the Y channel value of the center pixel, the image difference value, the gray gain coefficient, and the difference gain coefficient. 10.根据权利要求8所述的一种图像细节增强及其ASIC实现系统，其特征在于，所述灰度增益系数查表模块的表项可由CPU或其他主控制器配置得到；10. A kind of image detail enhancement and its ASIC realization system according to claim 8, is characterized in that, the table entry of described gray gain coefficient look-up table module can be obtained by CPU or other main controller configuration; 所述可配置加权均值滤波模块的滤波系数可由CPU或其他主控制器配置得到；The filter coefficient of the configurable weighted mean filter module can be configured by CPU or other main controllers; 所述差值增益系数查表模块的表项可由CPU或其他主控制器配置得到。The table entries of the difference gain coefficient look-up table module can be obtained by configuring the CPU or other main controllers.
CN202111542239.8A 2021-12-16 2021-12-16 Image detail enhancement and its ASIC implementation method and system Pending CN114202484A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111542239.8A CN114202484A (en) 2021-12-16 2021-12-16 Image detail enhancement and its ASIC implementation method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111542239.8A CN114202484A (en) 2021-12-16 2021-12-16 Image detail enhancement and its ASIC implementation method and system

Publications (1)

Publication Number Publication Date
CN114202484A true CN114202484A (en) 2022-03-18

Family

ID=80654499

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111542239.8A Pending CN114202484A (en) 2021-12-16 2021-12-16 Image detail enhancement and its ASIC implementation method and system

Country Status (1)

Country Link
CN (1) CN114202484A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW200731767A (en) * 2006-02-15 2007-08-16 Actvision Technologies Inc Device and method for image edge enhancement
CN102651122A (en) * 2011-02-24 2012-08-29 索尼公司 Image enhancement apparatus and method
CN104157003A (en) * 2014-07-18 2014-11-19 北京理工大学 Heat image detail enhancement method based on normal distribution adjustment
CN110796626A (en) * 2019-11-13 2020-02-14 中国电子科技集团公司信息科学研究院 Image sharpening method and device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW200731767A (en) * 2006-02-15 2007-08-16 Actvision Technologies Inc Device and method for image edge enhancement
CN102651122A (en) * 2011-02-24 2012-08-29 索尼公司 Image enhancement apparatus and method
CN104157003A (en) * 2014-07-18 2014-11-19 北京理工大学 Heat image detail enhancement method based on normal distribution adjustment
CN110796626A (en) * 2019-11-13 2020-02-14 中国电子科技集团公司信息科学研究院 Image sharpening method and device

Similar Documents

Publication Publication Date Title
CN101981911B (en) Image processing method and device
US8842912B2 (en) Method for processing highlights and saturated regions in a digital image
CN109743473A (en) Video image 3 D noise-reduction method, computer installation and computer readable storage medium
US9830690B2 (en) Wide dynamic range imaging method
EP1779653A2 (en) Apparatus and method for adaptive 3d noise reduction
JP2005323365A (en) Digital video signal filtering apparatus and method
US20080085061A1 (en) Method and Apparatus for Adjusting the Contrast of an Input Image
CN105787904A (en) Adaptive global dark channel prior image dehazing method for bright area
CN108133462A (en) A kind of restored method of the single image based on gradient fields region segmentation
CN114663319A (en) FPGA method and system for realizing color image enhancement
Dar et al. An enhanced adaptive histogram equalization based local contrast preserving technique for HDR images
CN105931206B (en) A kind of color image definition enhancing method of color constancy
JP5105286B2 (en) Image restoration apparatus, image restoration method, and image restoration program
JP2008511048A (en) Image processing method and computer software for image processing
Jagatheeswari et al. A novel approach for contrast enhancement based on histogram equalization followed by median filter
US8265419B2 (en) Image processing apparatus and image processing method
CN116245760A (en) A Low-Quality LDR Image Enhancement Method Based on Pseudo-HDR Image Generation
Asari et al. Nonlinear enhancement of extremely high contrast images for visibility improvement
CN114202484A (en) Image detail enhancement and its ASIC implementation method and system
KR101101434B1 (en) Image Clarity Enhancer
US7437020B2 (en) Digital image processing device and method
EP1854278B1 (en) A method for controlling overshoot in a video enhancement system
Terai et al. Color image contrast enhancement by retinex model
CN1620107A (en) Apparatus and method of image sharpness enhancement
TW201933278A (en) Image processing method and image processing device

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination