CN107346653A - A kind of GAMMA curves adjusting process and device based on deep learning - Google Patents
A kind of GAMMA curves adjusting process and device based on deep learning Download PDFInfo
- Publication number
- CN107346653A CN107346653A CN201710504489.XA CN201710504489A CN107346653A CN 107346653 A CN107346653 A CN 107346653A CN 201710504489 A CN201710504489 A CN 201710504489A CN 107346653 A CN107346653 A CN 107346653A
- Authority
- CN
- China
- Prior art keywords
- value
- initial
- gamma
- target
- values
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000013135 deep learning Methods 0.000 title claims abstract description 16
- 230000008569 process Effects 0.000 title claims abstract description 6
- 238000013499 data model Methods 0.000 claims abstract description 23
- 230000027455 binding Effects 0.000 claims description 92
- 238000009739 binding Methods 0.000 claims description 92
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 8
- 238000004737 colorimetric analysis Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 241000023320 Luma <angiosperm> Species 0.000 abstract 7
- OSWPMRLSEDHDFF-UHFFFAOYSA-N methyl salicylate Chemical compound COC(=O)C1=CC=CC=C1O OSWPMRLSEDHDFF-UHFFFAOYSA-N 0.000 abstract 7
- 239000000243 solution Substances 0.000 description 13
- 238000004519 manufacturing process Methods 0.000 description 6
- 238000012937 correction Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- MCSXGCZMEPXKIW-UHFFFAOYSA-N 3-hydroxy-4-[(4-methyl-2-nitrophenyl)diazenyl]-N-(3-nitrophenyl)naphthalene-2-carboxamide Chemical compound Cc1ccc(N=Nc2c(O)c(cc3ccccc23)C(=O)Nc2cccc(c2)[N+]([O-])=O)c(c1)[N+]([O-])=O MCSXGCZMEPXKIW-UHFFFAOYSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012482 calibration solution Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004020 luminiscence type Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G3/00—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes
- G09G3/20—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters
- G09G3/22—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters using controlled light sources
- G09G3/30—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters using controlled light sources using electroluminescent panels
- G09G3/32—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters using controlled light sources using electroluminescent panels semiconductive, e.g. using light-emitting diodes [LED]
- G09G3/3208—Control arrangements or circuits, of interest only in connection with visual indicators other than cathode-ray tubes for presentation of an assembly of a number of characters, e.g. a page, by composing the assembly by combination of individual elements arranged in a matrix no fixed position being assigned to or needed to be assigned to the individual characters or partial characters using controlled light sources using electroluminescent panels semiconductive, e.g. using light-emitting diodes [LED] organic, e.g. using organic light-emitting diodes [OLED]
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09G—ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION
- G09G2320/00—Control of display operating conditions
- G09G2320/06—Adjustment of display parameters
- G09G2320/0673—Adjustment of display parameters for control of gamma adjustment, e.g. selecting another gamma curve
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Picture Signal Circuits (AREA)
- Processing Of Color Television Signals (AREA)
- Electroluminescent Light Sources (AREA)
Abstract
The invention discloses a kind of GAMMA curve adjusting process based on deep learning, including:The target GAMMA of collection OLED modules ties up the second initial luma values or/and the second initial chroma a little, and by the second initial luma values or/and the second initial chroma compared with each first initial luma values or/and each first initial chroma, obtain first initial luma values or/and first initial chroma minimum with the error of the second initial luma values or/and the second initial chroma;Then RGB register configuration values corresponding to error minimum the first initial luma values or/and the first initial chroma are that target GAMMA ties up RGB register configuration values a little.The present invention is by tying up initial luma values or/and initial chroma and the classification learning of the relation of RGB register configuration values a little to each GAMMA, high-precision data model can be provided for the fast tuning of OLED module GAMMA curves, OLED module producing lines high-quality, efficient requirement can be met.
Description
Technical Field
The invention relates to the field of GAMMA curve adjustment of OLED modules, in particular to a GAMMA curve adjustment method and a GAMMA curve adjustment device based on deep learning.
Background
The OLED has the characteristics of self-luminescence, clearness, brightness, lightness, thinness, high response speed, wide visual angle, low power consumption, large applicable temperature range, low cost, simple manufacturing process and the like, and is regarded as a novel flat panel display technology with the greatest development potential after LCD and PDP. In recent years, with the development of OLED related technologies and the increase of the built-in capacity, the application market of OLED products is also rapidly expanding, including televisions, displays, smart phones, smart wearing, VR, automobile displays, automobile lighting, and the like.
Intuitively, the light and shade representation should be corresponding to the brightness at equal intervals, but actually, the sensitivity of human eyes to the brightness in a dark environment is much higher than that in a bright environment, the human eyes feel approximately proportional to the (1/GAMMA) power of the brightness, and a relation curve between the human eyes feel and the brightness is called as a GAMMA (GAMMA) curve, so that the GAMMA correction needs to be carried out on the module in order to better enable the display effect of the OLED module to better conform to the visual curve of the human eyes. The color temperature is the feeling of human eyes to a luminous body or a white reflecting body, the color characteristic displayed by an OLED product is reflected, a standard black body is heated, the color of the black body starts to change gradually from deep red, light red, orange yellow, white and blue when the temperature is raised to a certain degree, the reference white with the color temperature of 6500K or 9300K is generally selected as a white field of a module, the chromaticity coordinate corresponding to 6500K is 0.312, the chromaticity coordinate y is 0.329, and in order to enable the white field of the OLED module to present a uniform color temperature, chromaticity adjustment is needed to be carried out on each GAMMA binding point bound to the module IC.
At present, GAMMA tuning methods developed by display detection equipment manufacturers at home and abroad mainly aim at LCD modules, but the GAMMA tuning methods aiming at the LCD modules cannot be completely suitable for the OLED modules (the tuning effect is poor, and the product quality of the OLED modules is influenced) because the OLED modules and the LCD modules have different light-emitting mechanisms. In recent years, some manufacturers of display inspection equipment have tried to develop GAMMA adjustment solutions specifically for OLED modules, that is, RGB register values of each GAMMA binding point of an OLED module are adjusted respectively so that the luminance value and the chrominance value of each GAMMA binding point fall within the error range of the target value, and then the luminance value and the chrominance value of each GAMMA binding point are obtained multiple times, and the RGB register values of the GAMMA binding points are adjusted so that the luminance value and the chrominance value of each GAMMA binding point fall within the error range of the target value. However, the GAMMA adjustment solution for the OLED module has the following disadvantages:
1) the GAMMA adjustment and calibration solution for the OLED module consumes a long time, the GAMMA adjustment and calibration are required to be carried out on the OLED modules one by one, the efficiency is low, and the requirement of mass production of an OLED module production line cannot be met;
2) if the GAMMA adjustment efficiency is to be improved, the GAMMA adjustment solution for the OLED module generally only can adopt a simple algorithm and an evaluation method which are less time-consuming, so that the GAMMA adjustment precision is low, and the product quality of the OLED module is further influenced.
Disclosure of Invention
Aiming at the defects of the prior art, the invention discloses a GAMMA curve adjusting method and a GAMMA curve adjusting device based on deep learning, according to the deep learning of the relation between the initial brightness value of GAMMA binding points of a plurality of OLED module samples and the configuration value of an RGB register, or the deep learning of the relation between the initial chromatic value and the configuration value of the RGB register, or the deep learning of the relation between the initial chromatic value, the initial chromatic value and the configuration value of the RGB register, the GAMMA curve adjusting can be rapidly carried out on the OLED module, and the requirements of high quality and high efficiency of the GAMMA adjusting of an OLED module production line are met.
In order to solve the above technical problems, the present invention provides a GAMMA curve adjustment method based on deep learning, which is used for performing GAMMA curve adjustment on an OLED module, and the method includes the following steps:
1) providing a GAMMA data model including a plurality of first initial luminance values, or/and a plurality of first initial chrominance values, of the target GAMMA binding and a plurality of RGB register configuration values corresponding to each of the first initial luminance values, or/and each of the first initial chrominance values;
2) acquiring a second initial brightness value or/and a second initial chromatic value of the target GAMMA binding point of the OLED module, and comparing the second initial brightness value or/and the second initial chromatic value with each first initial brightness value or/and each first initial chromatic value to obtain a first initial brightness value or/and a first initial chromatic value with the minimum error with the second initial brightness value or/and the second initial chromatic value; then the process of the first step is carried out,
the RGB register configuration value corresponding to the first initial luminance value or/and the first initial chrominance value with the minimum error is the RGB register configuration value of the target GAMMA binding point.
Preferably, the training of the GAMMA data model in the above technical solution comprises the following steps:
11) obtaining a data set comprising the first plurality of initial luminance values, or/and the first plurality of initial chrominance values and the RGB register configuration values of the target GAMMA binding;
12) and training the data set by using a convolutional neural network to obtain the GAMMA data model by using the plurality of first initial brightness values or/and the plurality of first initial chromatic values as input values and the plurality of RGB register configuration values as output values.
Preferably, in the above technical solution, the step of acquiring the data set includes:
the luminance value or/and the chrominance value corresponding to all R, G, B register value combinations of the target GAMMA-binding are obtained, the luminance value or/and the chrominance value with the minimum error of the target luminance value or/and the target chrominance value of the target GAMMA-binding are/is taken as the first initial luminance value or/and the first initial chrominance value, and the luminance value or/and the R, G, B register value combination corresponding to the luminance value or/and the chrominance value with the minimum error is taken as the RGB register configuration value.
Preferably, in the above technical solution, the step of acquiring the data set includes:
and obtaining all brightness values or/and chroma values of the target GAMMA binding point by using a CIE standard colorimetry system, taking the brightness value or/and the chroma value with the minimum error with the target brightness value or/and the target chroma value of the target GAMMA binding point as a first initial brightness value or/and a first initial chroma value, and taking R, G, B register value combinations corresponding to the brightness value or/and the chroma value with the minimum error as RGB register configuration values.
Preferably, in the above technical solution, the GAMMA data model includes a network weight of a corresponding relationship between each of the initial luminance values, or/and each of the initial chrominance values and each of the RGB register configuration values.
Preferably, in the above technical solution, the neural network framework is used to train the data set to obtain the network weight of the target GAMMA binding point.
In order to solve the above technical problems, the present invention further provides a GAMMA curve adjusting method based on deep learning, which includes the steps of:
1) providing a GAMMA data model including a plurality of first initial luminance values, or/and a plurality of first initial chrominance values, of the target GAMMA binding and a plurality of RGB register configuration values corresponding to each of the first initial luminance values, or/and each of the first initial chrominance values;
2) collecting a second initial brightness value or/and a second initial chromatic value of the target GAMMA binding point of the OLED module, and comparing the second initial brightness value or/and the second initial chromatic value with each first initial brightness value or/and each first initial chromatic value to obtain a first initial brightness value or/and a first initial chromatic value with minimum error;
if the minimum error is within the target error range, the first initial brightness value of the minimum error or/and the RGB register configuration value corresponding to the first initial chromatic value are the RGB register configuration value of the target GAMMA binding point;
and if the minimum error is out of the target error range, obtaining a target brightness value or/and a target chroma value of the target GAMMA binding point according to the highest gray-scale brightness value, the lowest gray-scale brightness value and a brightness-gray-scale formula, and obtaining a target brightness value or/and an RGB register configuration value corresponding to the target chroma value of the target GAMMA binding point by adjusting R, G, B register values.
Preferably, in the above technical solution, a target error range of the first initial brightness value and the second initial brightness value is ± 2%; the target error range of the first initial chromaticity value and the second initial chromaticity value is ± 0.001.
In order to solve the above technical problem, the present invention further provides a GAMMA curve adjusting apparatus based on deep learning, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor is configured to implement the steps of the method according to the above technical solution when executing the computer program.
To solve the above technical problem, the present invention further provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the method according to the above technical solution.
The invention has the beneficial effects that:
1) in the GAMMA adjustment and correction process of the OLED module production line, the RGB register configuration values of each target GAMMA binding point of the OLED module can be configured directly according to the relation between the initial brightness value of the GAMMA binding point and the RGB register configuration values, or the relation between the initial chromatic value and the RGB register configuration values, so that the GAMMA adjustment and correction efficiency of the OLED module production line can be greatly improved.
2) The GAMMA data model can be trained based on a large number of OLED module samples in the earlier stage, and the accurate corresponding relation between the initial brightness value of each GAMMA binding point and the RGB register configuration value, or the accurate corresponding relation between the initial chromatic value, the initial chromatic value and the RGB register configuration value can be obtained by adopting various complex algorithms and evaluation methods, so that the GAMMA adjustment precision of the OLED module is greatly improved, and the product quality of the OLED module is further improved.
Drawings
Fig. 1 is a flowchart of a GAMMA curve adjustment method according to an embodiment of the present invention;
fig. 2 is a flowchart of a GAMMA curve adjustment method according to a second embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The invention discloses a GAMMA curve adjusting method based on deep learning, which is used for classifying and learning RGB register configuration values of GAMMA bindings of OLED modules in the same batch.
Example one
As shown in fig. 1, the GAMMA curve tuning method includes the following steps:
1) the method comprises the following steps of obtaining an input and output relation data set of the target GAMMA binding point: GAMMA curve adjustment is carried out on a large number of OLED module samples, and the initial brightness value L of the target GAMMA binding point of each OLED module sample is obtained0(or the initial chromaticity value X0Y0Or an initial luminance value L0With an initial colorimetric value X0Y0) And final RGB register configuration values.
2) Training an input and output relation data set of the target GAMMA binding point to obtain a GAMMA data model: these initial luminance values L0And as input values, the RGB register configuration values are used as output values, and a convolutional neural network is used for training to obtain the GAMMA data model of the target GAMMA binding point.
3) Adjusting the GAMMA curve of the OLED module: acquiring initial brightness value L of target GAMMA binding point of OLED module1(it may also be the initial chromaticity value X)1Y1Or may be the initial luminance value L1With an initial colorimetric value X1Y1) And mixing L1With each L in the GAMMA data model0Comparing to obtain a comparison result with L1L with the smallest error0Then take L with the minimum error0The corresponding RGB register configuration values are the RGB register configuration values of the target GAMMA binding.
Or,
acquiring initial brightness value L of target GAMMA binding point of OLED module1(it may also be the initial chromaticity value X)1Y1Or may be the initial luminance value L1With an initial colorimetric value X1Y1) And mixing L1With each L in the GAMMA data model0Comparing to obtain a comparison result with L1L with the smallest error0. If the error range is less than + -2% (if chroma is selected)Value, then X1Y1And X0Y0Is not more than + -0.001), then L with the smallest error is taken0The corresponding RGB register configuration value is the RGB register configuration value of the target GAMMA binding point; if the error range is larger than +/-2%, obtaining a target brightness value or/and a target chroma value of the target GAMMA binding point according to the highest gray-scale brightness value, the lowest gray-scale brightness value and a brightness-gray-scale formula, and obtaining a target brightness value or/and an RGB register configuration value corresponding to the target chroma value of the target GAMMA binding point by adjusting R, G, B register values.
In the above embodiment, a traversal theoretical method may be adopted to obtain a large number of input/output relationship data sets of target GAMMA bindings of the OLED module sample. The method for acquiring the input and output relation data set of the target GAMMA binding point of any OLED module sample by adopting a traversal theory method comprises the following steps of: obtaining all R, G, B register value combinations of the target GAMMA binding and corresponding brightness values L (or colorimetric values XY, or brightness values L and colorimetric values XY), and comparing all brightness values L with the target brightness values of the target GAMMA binding to obtain a brightness value L with the minimum error with the target brightness value of the target GAMMA binding as an initial brightness value L0The R, G, B register value combinations corresponding to the luminance value L with the minimum error are taken as RGB register allocation values. For example, the OLED module has R, G, B three color adjustment options, each color adjustment option has 33 binding points, and the adjustment value of each binding point has 4096 possibilities, and there are 4096 × 3 register value combinations R, G, B for the target GAMMA binding point, and then the luminance values corresponding to the 4096 × 3 register value combinations R, G, B are respectively obtained and compared with the target luminance value of the target GAMMA binding point, respectively, to obtain a luminance value with the minimum error from the target luminance value of the target GAMMA binding point as the initial luminance value, and to obtain the R, G, B register value combination corresponding to the minimum error as the RGB register configuration value.
In the above embodiment, the CIE standard colorimetry system may also be adopted to obtain the input and output relationship data set of the target GAMMA binding point: i.e. using "CIE 193Obtaining all the colorimetric values XY of the target GAMMA binding point by CIE standard colorimetry systems such as 1 XYZ standard colorimetry system, CIE 1931 xyY standard colorimetry system and the like, and comparing all the colorimetric values XY with the target colorimetric values of the target GAMMA binding point to obtain a colorimetric value XY with the minimum error with the target colorimetric values of the target GAMMA binding point as an initial colorimetric value X0Y0The R, G, B register values corresponding to the chromaticity value XY with the minimum error are combined as the RGB register arrangement value.
In the above embodiment, before training according to the input/output relationship data set of the target GAMMA binding point, the network weight obtained by training the target GAMMA binding points of the OLED modules in other batches or in other specifications may be used as an initial value of the GAMMA data model.
In the above embodiment, the GAMMA data model includes the initial brightness value L of the target GAMMA binding points of a plurality of OLED module samples0(or the initial chromaticity value X0Y0Or an initial luminance value L0With an initial colorimetric value X0Y0) And network weights corresponding to the RGB register configuration values.
In the above embodiment, the input-output relationship data set of the target gama binding point is trained by using a neural network framework such as tensorblow, Caffe, CNTK, thano, Torch, MXNet, Chainer, or Keras, so as to obtain the network weight of the target gama binding point.
In the above embodiment, each GAMMA binding point and RGB register address supported by the IC of the OLED module need to be searched according to the IC manual of the OLED module; wherein, the highest gray level W255 and the lowest gray level W0 are fixed GAMMA binding points, and the other gray levels are middle GAMMA binding points.
In the above embodiment, the optical tester is used to collect the initial brightness value and the initial chromatic value of the OLED module, and the image generator is controlled to adjust the R, G, B register value in the IC of the OLED module, so as to perform Gamma calibration on the OLED module according to the existing Gamma calibration technical scheme.
In the above embodiment, the luminance value Lv1 of the highest gray level W255 and the luminance value Lv2 of the lowest gray level W0 are determined by adjusting the white balance of the OLED module, and the target luminance value Lv of the target GAMMA binding point is obtained according to the luminance-gray level formula "Lv ═ (target GAMMA binding gray level value/W255) GAMMA index × (Lv1-Lv2) + Lv 2".
In the above embodiment, the selection principle of the target chromaticity value of the target gama binding point is as follows: when the target binding point is the highest gray level W255, the accuracy requirement on the chromaticity value is high because the W255 gray level is taken as the highest brightness reference, the chromaticity coordinate x ranges between 0.315 and 0.309 (+ -0.003), and the chromaticity coordinate y ranges between 0.332 and 0.326 (+ -0.003); when the target binding point is 11-254 gray scale, the chromatic value is a set value, the color coordinate x is near 0.312 (+ -0.001), and the color coordinate y is near 0.329 (+ -0.001); when the target binding point is in the gray scale of 0 to 10, the chromaticity value is also the set value, and the color coordinate x is near 0.312 (± 0.050), and the color coordinate y is near 0.329 (± 0.050).
Example two
As shown in fig. 2, the GAMMA curve adjusting method includes the following steps:
1) obtaining a target brightness value and a target chroma value of the target GAMMA binding point according to the highest gray scale brightness, the lowest gray scale and a brightness-gray scale formula of the target GAMMA binding point;
2) obtaining an initial brightness value L of the target GAMMA binding point0Initial colorimetric value X0Y0Adjusting R, G, B register value of the target GAMMA binding point to make the brightness value of the target GAMMA binding point fall within the error range of the target brightness value and the chromatic value fall within the error range of the target chromatic value, and obtaining RGB register configuration values corresponding to the brightness value and the chromatic value;
3) the initial brightness value L is measured0Or/and the initial colorimetric value X0Y0As input values, the RGB register configuration values are used as output values, and a convolutional neural network is used to train the GAMMA data model of the target GAMMA binding point.
4) Acquiring initial brightness value L of target GAMMA binding point of OLED module1(it may also be the initial chromaticity value X)1Y1Or may be the initial luminance value L1With an initial colorimetric value X1Y1) And mixing L1With each L in the GAMMA data model0Comparing to obtain a comparison result with L1L with the smallest error0Then take L with the minimum error0The corresponding RGB register configuration values are the RGB register configuration values of the target GAMMA binding.
Or,
acquiring initial brightness value L of target GAMMA binding point of OLED module1(it may also be the initial chromaticity value X)1Y1Or may be the initial luminance value L1With an initial colorimetric value X1Y1) And mixing L1With each L in the GAMMA data model0Comparing to obtain a comparison result with L1L with the smallest error0. If the error range is less than + -2% (if chromatic values are selected, X1Y1And X0Y0Is not more than + -0.001), then L with the smallest error is taken0The corresponding RGB register configuration value is the RGB register configuration value of the target GAMMA binding point; if the error range is larger than +/-2%, obtaining a target brightness value or/and a target chroma value of the target GAMMA binding point according to the highest gray-scale brightness value, the lowest gray-scale brightness value and a brightness-gray-scale formula, and obtaining a target brightness value or/and an RGB register configuration value corresponding to the target chroma value of the target GAMMA binding point by adjusting R, G, B register values.
EXAMPLE III
A GAMMA curve adjusting device based on deep learning comprises: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, all or part of the processes in the method of the embodiment are implemented, for example, the step of obtaining the input/output relationship data set of the target GAMMA binding point, the step of training the input/output relationship data set of the target GAMMA binding point to obtain the GAMMA data model, and the step of adjusting the GAMMA curve of the OLED module.
In the above technical solution, the Processor may be a Central Processing Unit (CPU), or may be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center for the GAMMA curve adjustment mechanism and connects the various parts of the entire GAMMA curve adjustment mechanism using various interfaces, lines or signal logic.
In the above embodiments, the memory may be configured to store the computer program, and the processor may implement various functions of the GAMMA curve adjusting apparatus by running or executing the computer program stored in the memory and calling data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area can store data such as input and output relation data sets containing target GAMMA binding points, GAMMA data models and the like. In addition, the memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
In the above embodiment, the GAMMA curve adjusting apparatus may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, all or part of the flow of the method according to the embodiments of the present invention may also be implemented by a computer program, which may be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the method embodiments may be implemented. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like.
It will be readily understood by those skilled in the art that the details of the present invention which have not been described in detail herein are not to be interpreted as limiting the scope of the invention, but as merely illustrative of the presently preferred embodiments of the invention.
Claims (10)
1. A GAMMA curve adjusting method based on deep learning is used for adjusting GAMMA curves of an OLED module, and is characterized by comprising the following steps:
1) providing a GAMMA data model including a plurality of first initial luminance values, or/and a plurality of first initial chrominance values, of the target GAMMA binding and a plurality of RGB register configuration values corresponding to each of the first initial luminance values, or/and each of the first initial chrominance values;
2) acquiring a second initial brightness value or/and a second initial chromatic value of the target GAMMA binding point of the OLED module, and comparing the second initial brightness value or/and the second initial chromatic value with each first initial brightness value or/and each first initial chromatic value to obtain a first initial brightness value or/and a first initial chromatic value with the minimum error with the second initial brightness value or/and the second initial chromatic value; then the process of the first step is carried out,
the RGB register configuration value corresponding to the first initial luminance value or/and the first initial chrominance value with the minimum error is the RGB register configuration value of the target GAMMA binding point.
2. The GAMMA curve tuning method of claim 1, wherein training the GAMMA data model comprises the steps of:
11) obtaining a data set comprising the first plurality of initial luminance values, or/and the first plurality of initial chrominance values and the RGB register configuration values of the target GAMMA binding;
12) and training the data set by using a convolutional neural network to obtain the GAMMA data model by using the plurality of first initial brightness values or/and the plurality of first initial chromatic values as input values and the plurality of RGB register configuration values as output values.
3. The GAMMA curve alignment method as claimed in claim 2, wherein the step of acquiring the data set comprises:
the luminance value or/and the chrominance value corresponding to all R, G, B register value combinations of the target GAMMA-binding are obtained, the luminance value or/and the chrominance value with the minimum error of the target luminance value or/and the target chrominance value of the target GAMMA-binding are/is taken as the first initial luminance value or/and the first initial chrominance value, and the luminance value or/and the R, G, B register value combination corresponding to the luminance value or/and the chrominance value with the minimum error is taken as the RGB register configuration value.
4. The GAMMA curve alignment method as claimed in claim 2, wherein the step of acquiring the data set comprises:
and obtaining all brightness values or/and chroma values of the target GAMMA binding point by using a CIE standard colorimetry system, taking the brightness value or/and the chroma value with the minimum error with the target brightness value or/and the target chroma value of the target GAMMA binding point as a first initial brightness value or/and a first initial chroma value, and taking R, G, B register value combinations corresponding to the brightness value or/and the chroma value with the minimum error as RGB register configuration values.
5. The GAMMA curve calibration method as claimed in claim 2, wherein the GAMMA data model comprises network weights corresponding to each of the initial luminance values, or/and each of the initial chrominance values and each of the RGB register configuration values.
6. The GAMMA curve tuning method of claim 5, wherein the data set is trained by using neural network framework to obtain the network weights of the target GAMMA binding points.
7. A GAMMA curve adjusting method based on deep learning is used for adjusting GAMMA curves of an OLED module, and is characterized by comprising the following steps:
1) providing a GAMMA data model including a plurality of first initial luminance values, or/and a plurality of first initial chrominance values, of the target GAMMA binding and a plurality of RGB register configuration values corresponding to each of the first initial luminance values, or/and each of the first initial chrominance values;
2) collecting a second initial brightness value or/and a second initial chromatic value of the target GAMMA binding point of the OLED module, and comparing the second initial brightness value or/and the second initial chromatic value with each first initial brightness value or/and each first initial chromatic value to obtain a first initial brightness value or/and a first initial chromatic value with minimum error;
if the minimum error is within the target error range, the first initial brightness value of the minimum error or/and the RGB register configuration value corresponding to the first initial chromatic value are the RGB register configuration value of the target GAMMA binding point;
and if the minimum error is out of the target error range, obtaining a target brightness value or/and a target chroma value of the target GAMMA binding point according to the highest gray-scale brightness value, the lowest gray-scale brightness value and a brightness-gray-scale formula, and obtaining a target brightness value or/and an RGB register configuration value corresponding to the target chroma value of the target GAMMA binding point by adjusting R, G, B register values.
8. The GAMMA curve adjusting method of claim 1, wherein the target error range between the first initial brightness value and the second initial brightness value is ± 2%; the target error range of the first initial chromaticity value and the second initial chromaticity value is ± 0.001.
9. A GAMMA curve tuning apparatus based on deep learning, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor is configured to carry out the steps of the method according to any one of claims 1 to 8 when the computer program is executed.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710504489.XA CN107346653B (en) | 2017-06-28 | 2017-06-28 | GAMMA curve adjusting method and device based on deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710504489.XA CN107346653B (en) | 2017-06-28 | 2017-06-28 | GAMMA curve adjusting method and device based on deep learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107346653A true CN107346653A (en) | 2017-11-14 |
CN107346653B CN107346653B (en) | 2021-05-07 |
Family
ID=60256541
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710504489.XA Active CN107346653B (en) | 2017-06-28 | 2017-06-28 | GAMMA curve adjusting method and device based on deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107346653B (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108154540A (en) * | 2017-12-22 | 2018-06-12 | 武汉华显光电技术有限公司 | Best coloration and brightness determine method, apparatus and computer readable storage medium |
CN109029918A (en) * | 2018-06-06 | 2018-12-18 | 武汉精测电子集团股份有限公司 | A kind of gamma adjusts the method and device tied up a little |
CN109191386A (en) * | 2018-07-18 | 2019-01-11 | 武汉精测电子集团股份有限公司 | A kind of quick Gamma bearing calibration and device based on BPNN |
CN109253862A (en) * | 2018-08-31 | 2019-01-22 | 武汉精测电子集团股份有限公司 | A kind of colour measurement method neural network based |
CN110459170A (en) * | 2019-10-11 | 2019-11-15 | 武汉精立电子技术有限公司 | A kind of mould group Gamma bearing calibration, terminal device and computer-readable medium |
CN110910847A (en) * | 2019-11-25 | 2020-03-24 | 深圳吉迪思电子科技有限公司 | Gamma correction method and device for display module |
CN111540312A (en) * | 2020-07-07 | 2020-08-14 | 武汉精立电子技术有限公司 | Gamma modulation method |
CN111681607A (en) * | 2020-08-17 | 2020-09-18 | 武汉精立电子技术有限公司 | Gamma adjusting method and system based on genetic algorithm |
CN113223453A (en) * | 2020-01-21 | 2021-08-06 | 武汉精立电子技术有限公司 | Module Gamma initial value prediction method |
CN113223452A (en) * | 2020-01-21 | 2021-08-06 | 武汉精立电子技术有限公司 | Characteristic curve-based module Gamma initial value prediction method |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101345033A (en) * | 2008-06-23 | 2009-01-14 | 东莞黄江达裕科技电子厂 | Optical data processing method and system, and LCD device |
US20120274854A1 (en) * | 2007-07-23 | 2012-11-01 | Renesas Electronics Corporation | Video signal processing apparatus performing gamma correction by cubic interpolation computation, and method thereof |
US20160104429A1 (en) * | 2014-10-08 | 2016-04-14 | Samsung Display Co., Ltd. | Data voltage compensation circuit and display device including the same |
CN105590587A (en) * | 2016-03-24 | 2016-05-18 | 京东方科技集团股份有限公司 | Gamma correcting method and device for display modules |
CN106328070A (en) * | 2016-09-28 | 2017-01-11 | 武汉精测电子技术股份有限公司 | OLED module Gamma adjustment and calibration method and device |
CN106384573A (en) * | 2016-11-04 | 2017-02-08 | 武汉精测电子技术股份有限公司 | OLED module Gamma adjustment and calibration method based on linear interpolation calculation |
CN106531065A (en) * | 2016-11-11 | 2017-03-22 | 武汉精测电子技术股份有限公司 | One-to-many Gamma curve parallel adjustment system and method |
CN106847173A (en) * | 2017-01-19 | 2017-06-13 | 武汉精测电子技术股份有限公司 | A kind of OLED modules gamma curve adjusting method and device |
-
2017
- 2017-06-28 CN CN201710504489.XA patent/CN107346653B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120274854A1 (en) * | 2007-07-23 | 2012-11-01 | Renesas Electronics Corporation | Video signal processing apparatus performing gamma correction by cubic interpolation computation, and method thereof |
CN101345033A (en) * | 2008-06-23 | 2009-01-14 | 东莞黄江达裕科技电子厂 | Optical data processing method and system, and LCD device |
US20160104429A1 (en) * | 2014-10-08 | 2016-04-14 | Samsung Display Co., Ltd. | Data voltage compensation circuit and display device including the same |
CN105590587A (en) * | 2016-03-24 | 2016-05-18 | 京东方科技集团股份有限公司 | Gamma correcting method and device for display modules |
CN106328070A (en) * | 2016-09-28 | 2017-01-11 | 武汉精测电子技术股份有限公司 | OLED module Gamma adjustment and calibration method and device |
CN106384573A (en) * | 2016-11-04 | 2017-02-08 | 武汉精测电子技术股份有限公司 | OLED module Gamma adjustment and calibration method based on linear interpolation calculation |
CN106531065A (en) * | 2016-11-11 | 2017-03-22 | 武汉精测电子技术股份有限公司 | One-to-many Gamma curve parallel adjustment system and method |
CN106847173A (en) * | 2017-01-19 | 2017-06-13 | 武汉精测电子技术股份有限公司 | A kind of OLED modules gamma curve adjusting method and device |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108154540A (en) * | 2017-12-22 | 2018-06-12 | 武汉华显光电技术有限公司 | Best coloration and brightness determine method, apparatus and computer readable storage medium |
CN109029918B (en) * | 2018-06-06 | 2020-07-10 | 武汉精测电子集团股份有限公司 | Method and device for adjusting binding point by gamma |
CN109029918A (en) * | 2018-06-06 | 2018-12-18 | 武汉精测电子集团股份有限公司 | A kind of gamma adjusts the method and device tied up a little |
CN109191386B (en) * | 2018-07-18 | 2020-11-06 | 武汉精测电子集团股份有限公司 | BPNN-based rapid Gamma correction method and device |
CN109191386A (en) * | 2018-07-18 | 2019-01-11 | 武汉精测电子集团股份有限公司 | A kind of quick Gamma bearing calibration and device based on BPNN |
CN109253862A (en) * | 2018-08-31 | 2019-01-22 | 武汉精测电子集团股份有限公司 | A kind of colour measurement method neural network based |
CN110459170A (en) * | 2019-10-11 | 2019-11-15 | 武汉精立电子技术有限公司 | A kind of mould group Gamma bearing calibration, terminal device and computer-readable medium |
CN110910847A (en) * | 2019-11-25 | 2020-03-24 | 深圳吉迪思电子科技有限公司 | Gamma correction method and device for display module |
CN110910847B (en) * | 2019-11-25 | 2021-09-21 | 豪威触控与显示科技(深圳)有限公司 | Gamma correction method and device for display module |
CN113223453A (en) * | 2020-01-21 | 2021-08-06 | 武汉精立电子技术有限公司 | Module Gamma initial value prediction method |
CN113223452A (en) * | 2020-01-21 | 2021-08-06 | 武汉精立电子技术有限公司 | Characteristic curve-based module Gamma initial value prediction method |
CN113223452B (en) * | 2020-01-21 | 2022-06-03 | 武汉精立电子技术有限公司 | Characteristic curve-based module Gamma initial value prediction method |
CN111540312A (en) * | 2020-07-07 | 2020-08-14 | 武汉精立电子技术有限公司 | Gamma modulation method |
CN111681607A (en) * | 2020-08-17 | 2020-09-18 | 武汉精立电子技术有限公司 | Gamma adjusting method and system based on genetic algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN107346653B (en) | 2021-05-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107346653B (en) | GAMMA curve adjusting method and device based on deep learning | |
CN106328070B (en) | OLED mould group Gamma adjusting process and device | |
CN106384573B (en) | The OLED module Gamma adjusting process calculated based on linear interpolation | |
CN107682682B (en) | Method for automatically correcting color coordinate and brightness of display screen and related equipment | |
CN103067743B (en) | Quick adjustment system and method for liquid crystal display television | |
CN107358255A (en) | GAMMA based on convolutional neural networks ties up a classification learning method and device | |
CN110024020A (en) | Display device, calibrating installation and its calibration method | |
CN109859689A (en) | Screen luminance adjustment method and Related product | |
CN107872662A (en) | Display device | |
CN103080999A (en) | Adaptive color correction for display with backlight modulation | |
CN110675818B (en) | Curve matching-based module Gamma correction method and system | |
CN107644607B (en) | Color temperature adjusting method of display panel and display device | |
CN109996054B (en) | White balance adjusting method and device | |
CN106373527B (en) | The gamma and colour temperature Automatic adjustment method of a kind of highest and minimum gray scale | |
CN109584792B (en) | Method for quickly adjusting gray scale gamma of O L ED screen | |
CN105336307A (en) | Method and system for correcting gamma curve of display based on color temperature | |
CN107507562B (en) | OLED grayscale gamma method of adjustment based on fast search algorithm | |
CN110310596B (en) | GAMMA (GAMMA-GAMMA) adjustment initial value prediction method and system of OLED module | |
CN109729281A (en) | Image processing method, device, storage medium and terminal | |
CN114203087A (en) | Configuration of compensation lookup table, compensation method, device, equipment and storage medium | |
CN106782347A (en) | Correct the method and device of LED backlight display white point | |
CN112016621B (en) | Training method of classification model, color classification method and electronic equipment | |
CN103426393B (en) | Display device color correcting method | |
CN101668225A (en) | Method for adjusting gamma curve to improve image of flat television | |
WO2023245894A1 (en) | Display panel compensation method and apparatus, device, and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
CB02 | Change of applicant information |
Address after: 430070 Hubei City, Hongshan Province, South Lake Road, No. 53, Hongshan Venture Center, building on the 4 floor, No. Applicant after: Wuhan fine test electronics group Limited by Share Ltd Address before: 430070 Hubei City, Hongshan Province, South Lake Road, No. 53, Hongshan Venture Center, building on the 4 floor, No. Applicant before: Wuhan Jingce Electronic Technology Co., Ltd. |
|
CB02 | Change of applicant information | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |