CN115604448A - Projection method, projection system and projector for improving color gamut - Google Patents

Projection method, projection system and projector for improving color gamut Download PDF

Info

Publication number
CN115604448A
CN115604448A CN202211427616.8A CN202211427616A CN115604448A CN 115604448 A CN115604448 A CN 115604448A CN 202211427616 A CN202211427616 A CN 202211427616A CN 115604448 A CN115604448 A CN 115604448A
Authority
CN
China
Prior art keywords
image
color gamut
projected
frame
character
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
Application number
CN202211427616.8A
Other languages
Chinese (zh)
Other versions
CN115604448B (en
Inventor
何凡
贺正华
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.)
Shenzhen Chiptrip Technology Co ltd
Original Assignee
Shenzhen Chiptrip 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 Shenzhen Chiptrip Technology Co ltd filed Critical Shenzhen Chiptrip Technology Co ltd
Priority to CN202211427616.8A priority Critical patent/CN115604448B/en
Publication of CN115604448A publication Critical patent/CN115604448A/en
Application granted granted Critical
Publication of CN115604448B publication Critical patent/CN115604448B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N9/00—Details of colour television systems
    • H04N9/12—Picture reproducers
    • H04N9/31—Projection devices for colour picture display, e.g. using electronic spatial light modulators [ESLM]
    • H04N9/3179—Video signal processing therefor
    • H04N9/3182—Colour adjustment, e.g. white balance, shading or gamut
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Abstract

The application relates to the technical field of image processing, and provides a projection method, a projection system and a projector for improving color gamut, wherein the method comprises the following steps: analyzing the data to be projected to obtain a character image and an object image of each frame of image to be projected; determining a character color gamut value of a character image in each frame of image to be projected through a character characteristic model; determining an object color gamut value of an object image in each frame of image to be projected through an object characteristic model; determining a character color gamut evaluation index according to the color gamut evaluation index table, and determining an object color gamut evaluation index according to the color gamut evaluation index table; adjusting the character color gamut value based on the character color gamut evaluation index, and adjusting the object color gamut value based on the object color gamut evaluation index; and projecting each frame of image to be projected based on the adjusted text color gamut value and the adjusted object color gamut value of each frame of image to be projected. The projection method for improving the color gamut ensures that the white balance of the picture gray scale is not disordered to the greatest extent.

Description

Projection method, projection system and projector for improving color gamut
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a projection method, a projection system, and a projector for improving a color gamut.
Background
The dynamic range of the picture actually refers to the contrast, and the larger the dynamic range is, the richer the gray scale levels presented by the picture are, and the finer the detailed expression is. The wider the dynamic range can be in a full light-blocking condition, the more chromatic the performance of the projector itself. However, in the case of a typical household, more or less ambient light interference is a problem. The black position expression of the picture can be weakened only by little light interference, so that the dynamic range of the whole projection picture is greatly narrowed, and the depiction of image levels and details is reduced. Meanwhile, the influence also causes the imbalance of the gray scale white balance of the picture.
Disclosure of Invention
The application provides a projection method, a projection system and a projector for improving color gamut, aiming at ensuring the non-imbalance of the white balance of the picture gray scale to the maximum extent.
In a first aspect, the present application provides a projection method for improving color gamut, including:
analyzing data to be projected to obtain a character image and an object image of each frame of image to be projected in the data to be projected;
determining a character color gamut value of a character image in each frame of images to be projected according to the type characteristics and the information characteristics of the digital image in each frame of images to be projected by a character characteristic model;
determining an object color gamut value of an object image in each frame of image to be projected according to the type characteristic and the size characteristic of the object image in each frame of image to be projected through an object characteristic model;
determining a character color gamut evaluation index of the digital image in each frame of image to be projected according to a color gamut evaluation index table, and determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the color gamut evaluation index table;
adjusting the character color gamut value of each frame of image to be projected based on the character color gamut evaluation index of each frame of image to be projected, and adjusting the object color gamut value of each frame of image to be projected based on the object color gamut evaluation index of each frame of image to be projected;
and projecting each frame of image to be projected based on the adjusted text color gamut value and the adjusted object color gamut value of each frame of image to be projected.
In one embodiment, the determining the text color gamut evaluation index of the digital image in each frame to be projected according to the color gamut evaluation index table includes:
determining a character color gamut evaluation index of the digital image in each frame to be projected according to the information intensity of each piece of information reported by any pixel path of the digital image in each frame to be projected within a preset time period, the time for reporting each piece of information, the maximum information intensity in each piece of information and the current time, wherein the preset time period is determined according to the current time and a preset time interval;
the calculation formula of the character color gamut evaluation index of the digital image in each frame of the image to be projected is as follows:
Figure 397015DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 251838DEST_PATH_IMAGE002
、
Figure 828313DEST_PATH_IMAGE003
is a constant number of times, and is,
Figure 879315DEST_PATH_IMAGE004
for the information strength of the ith piece of information in the pixel path,
Figure 365791DEST_PATH_IMAGE005
for the maximum information strength among the respective information,
Figure 719412DEST_PATH_IMAGE006
is the current time of the day, and is,
Figure 910746DEST_PATH_IMAGE007
the time for reporting the ith information in the pixel path is defined, and m is the total number of information reported in the pixel path.
The determining the object color gamut evaluation index of the object image in each frame of the image to be projected according to the color gamut evaluation index table comprises the following steps:
determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the information intensity of each piece of information reported by any pixel path of the object image in each frame of image to be projected within a preset time period, the time for reporting each piece of information, the maximum information intensity in each piece of information and the current time, wherein the preset time period is determined according to the current time and a preset time interval;
the object color gamut evaluation index calculation formula of the object image in each frame of image to be projected is as follows:
Figure 47329DEST_PATH_IMAGE008
wherein the content of the first and second substances,
Figure 903159DEST_PATH_IMAGE009
、
Figure 834206DEST_PATH_IMAGE010
is a constant number of times, and is,
Figure 775486DEST_PATH_IMAGE004
for the information strength of the ith piece of information in the pixel path,
Figure 184602DEST_PATH_IMAGE005
for the maximum information strength among the respective information,
Figure 894937DEST_PATH_IMAGE006
and the current time is the time for reporting the ith information in the pixel path, and n is the total number of the information reported in the pixel path.
The adjusting of the character color gamut value based on the character color gamut evaluation index of each frame of the image to be projected comprises the following steps:
if the character color gamut evaluation index of each frame of image to be projected is that the character color gamut value of each frame of image to be projected is larger than the first character color gamut value, the character color gamut value of each frame of image to be projected is reduced, so that the character color gamut value of each frame of image to be projected after adjustment is larger than the second character color gamut value and smaller than the first character color gamut value;
if the character color gamut evaluation index of each frame of the image to be projected is that the character color gamut value of each frame of the image to be projected is smaller than the second character color gamut value, the character color gamut value of each frame of the image to be projected is increased, so that the character color gamut value of each frame of the image to be projected after adjustment is larger than the second character color gamut value and smaller than the first character color gamut value.
The adjusting of the object color gamut value based on the object color gamut evaluation index of each frame of image to be projected comprises the following steps:
if the object color gamut evaluation index of each frame of the image to be projected is that the object color gamut value of each frame of the image to be projected is greater than the first object color gamut value, the object color gamut value of each frame of the image to be projected is reduced, so that the adjusted object color gamut value of each frame of the image to be projected is greater than the second object color gamut value and smaller than the first object color gamut value;
if the object color gamut evaluation index of each frame of the image to be projected is that the object color gamut value of each frame of the image to be projected is smaller than the second object color gamut value, the object color gamut value of each frame of the image to be projected is increased, so that the adjusted object color gamut value of each frame of the image to be projected is larger than the second object color gamut value and smaller than the first object color gamut value.
Before analyzing the data to be projected to obtain the text image and the object image of each frame of the image to be projected in the data to be projected, the method further comprises the following steps:
carrying out normalization processing on the type characteristics of the digital image in each image to be trained, and carrying out unique hot coding after normalization processing to generate a character type vector of each image to be trained;
carrying out one-hot coding on the information characteristics of the digital image in each image to be trained to generate a character information vector of each image to be trained;
connecting the character type vector and the character information vector of each image to be trained to obtain a character training vector of each image to be trained;
and training the deep neural network of the character features based on the character training vector of each image to be trained to obtain the character feature model.
Before analyzing the data to be projected to obtain the text image and the object image of each frame of the image to be projected in the data to be projected, the method further comprises the following steps:
carrying out normalization processing on the type characteristics of the object image in each image to be trained, and carrying out unique hot coding after normalization processing to generate an object type vector of each image to be trained;
carrying out independent thermal coding on the size characteristics of the object image in each image to be trained to generate an object size vector of each image to be trained;
connecting the object type vector and the object size vector of each image to be trained to obtain an object training vector of each image to be trained;
and training the deep neural network of the object characteristics based on the object training vector of each image to be trained to obtain the object characteristic model.
In a second aspect, the present application provides a color gamut enhanced projection system comprising:
the analysis module is used for analyzing the data to be projected to obtain a character image and an object image of each frame of image to be projected in the data to be projected;
the first determining module is used for determining the character color gamut value of the character image in each frame of the image to be projected according to the type characteristics and the information characteristics of the character image in each frame of the image to be projected through the character characteristic model;
the second determination module is used for determining the object color gamut value of the object image in each frame of image to be projected according to the type feature and the size feature of the object image in each frame of image to be projected through the object feature model;
the third determining module is used for determining a character color gamut evaluation index of the digital image in each frame of image to be projected according to a color gamut evaluation index table and determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the color gamut evaluation index table;
the adjusting module is used for adjusting the character color gamut value of each frame of image to be projected based on the character color gamut evaluation index of each frame of image to be projected and adjusting the object color gamut value of each frame of image to be projected based on the object color gamut evaluation index of each frame of image to be projected;
and the projection module is used for projecting each frame of image to be projected based on the adjusted character color gamut value and the adjusted object color gamut value of each frame of image to be projected.
In a third aspect, the present application further provides a projector, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the program, the projector implements the color gamut enhancing projection method of the first aspect.
In a fourth aspect, the present application further provides a non-transitory computer-readable storage medium comprising a computer program which, when executed by the processor, implements the color gamut enhancing projection method of the first aspect.
In a fifth aspect, the present application further provides a computer program product comprising a computer program which, when executed by the processor, implements the color gamut enhancing projection method of the first aspect.
According to the projection method, the projection system and the projector for improving the color gamut, data to be projected are analyzed to obtain a character image and an object image of each frame of image to be projected; determining a character color gamut value of a character image in each frame of image to be projected through a character characteristic model; determining an object color gamut value of an object image in each frame of image to be projected through an object characteristic model; determining a character color gamut evaluation index according to a color gamut evaluation index table, and determining an object color gamut evaluation index according to the color gamut evaluation index table; adjusting the character color gamut value based on the character color gamut evaluation index, and adjusting the object color gamut value based on the object color gamut evaluation index; and projecting each frame of image to be projected based on the adjusted character color gamut value and the adjusted object color gamut value of each frame of image to be projected.
In the process of improving the color gamut projection, the final character color gamut value and the final character color gamut value of each frame of image to be projected are improved through the character color gamut value and the character color gamut evaluation index of the character image in each frame of image to be projected, and the object color gamut value and the object color gamut evaluation index of the object image in each frame of image to be projected, so that the non-imbalance of the white balance of the picture gray scale is ensured to the greatest extent.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a flow chart of a color gamut enhancing projection method provided herein;
FIG. 2 is a schematic diagram of a pixel path provided herein;
FIG. 3 is a block diagram of an enhanced color gamut projection system provided herein;
fig. 4 is a structural diagram of a projector provided in the present application.
Detailed Description
To make the purpose, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be clearly and completely described below with reference to the drawings in the present application, and it is obvious that the described embodiments are some, but not all embodiments of the present application. 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 application.
Further, the projection method, the projection system and the projector for improving the color gamut provided by the present application are described below with reference to fig. 1 to 4. FIG. 1 is a flow chart of a color gamut enhancing projection method provided herein; FIG. 2 is a schematic diagram of a pixel path provided herein; FIG. 3 is a block diagram of an enhanced color gamut projection system provided herein; fig. 4 is a structural diagram of a projector provided in the present application.
While the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order than that shown or described.
The embodiment of the present application uses the projection system as an execution subject, and is not limited.
Referring to fig. 1, fig. 1 is a flowchart of a color gamut enhancing projection method provided in the present application. The projection method for improving the color gamut provided by the embodiment of the application comprises the following steps:
step 101, analyzing data to be projected to obtain a character image and an object image of each frame of image to be projected in the data to be projected;
102, determining a character color gamut value of a character image in each frame of images to be projected according to the type characteristics and the information characteristics of the character image in each frame of images to be projected through a character characteristic model;
and 103, determining the object color gamut value of the object image in each frame of image to be projected according to the type characteristic and the size characteristic of the object image in each frame of image to be projected through the object characteristic model.
It should be noted that the projection system in the embodiment of the present invention is provided with an external interface or an internal disk, and the projection system may read data of an inserted memory device (such as a usb disk) through the external interface, and at the same time, the projection system may also read data in the optical disk through the memory disk. The embodiment of the invention takes an external interface as an example.
Therefore, the projection system reads the data in the memory device and determines the read data as the data to be projected, it should be noted that the data to be projected may be video data or image data, and the embodiment of the present invention exemplifies the video data.
Further, the projection system analyzes the read data to be projected, and analyzes to obtain each frame of image to be projected in the data to be projected. Further, the projection system analyzes each frame of image to be projected, analyzes an image containing a text part in each frame of image to be projected into a text image of each frame of image to be projected, and analyzes an image containing an object part in each frame of image to be projected into an object image of each frame of image to be projected, wherein the part containing the object can be understood as containing a person or other animals or still objects.
Further, the projection system determines a text color gamut value of the text image in each frame of the image to be projected according to the type characteristic and the information characteristic of the digital image in each frame of the image to be projected through a text characteristic model, wherein the type characteristic belongs to one of the sparse characteristics, and the information characteristic belongs to one of the dense characteristics. Therefore, the type feature of the text image can be understood as a sparse feature of the text image, and the information feature of the text image can be understood as a dense feature of the text image.
Further, the projection system determines an object color gamut value of the object image in each frame of the image to be projected according to the type feature and the size feature of the object image in each frame of the image to be projected through the object feature model. Wherein the type feature belongs to one of the sparse features and the size feature belongs to one of the dense features. Therefore, the type feature of the object image can be understood as a sparse feature of the object image, and the information feature of the object image can be understood as a dense feature of the object image.
104, determining a character color gamut evaluation index of the digital image in each frame of image to be projected according to a color gamut evaluation index table, and determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the color gamut evaluation index table;
105, adjusting the character color gamut value of each frame of image to be projected based on the character color gamut evaluation index of each frame of image to be projected, and adjusting the object color gamut value of each frame of image to be projected based on the object color gamut evaluation index of each frame of image to be projected;
and 106, projecting each frame of image to be projected based on the adjusted character color gamut value and the adjusted object color gamut value of each frame of image to be projected.
Further, the projection system determines a color gamut evaluation index table, and determines the character color gamut evaluation index of the digital image in each frame to be projected according to the color gamut evaluation index table. At the same time. And the projection system determines the object color gamut evaluation index of the object image in each frame of image to be projected according to the color gamut evaluation index table.
Further, the projection system determines whether the character color gamut value of each frame of the image to be projected is high or low according to the character color gamut evaluation index of each frame of the image to be projected, so that the character color gamut value of each frame of the image to be projected is adjusted according to the character color gamut evaluation index of each frame of the image to be projected. In a similar way, the projection system determines whether the object color gamut value of each frame of the image to be projected is high or low according to the object color gamut evaluation index of each frame of the image to be projected, so that the object color gamut value of each frame of the image to be projected is adjusted through the object color gamut evaluation index of each frame of the image to be projected.
According to the projection method for improving the color gamut, the data to be projected is analyzed to obtain the character image and the object image of each frame of image to be projected; determining a character color gamut value of a character image in each frame of image to be projected through a character characteristic model; determining an object color gamut value of an object image in each frame of image to be projected through an object characteristic model; determining a character color gamut evaluation index according to the color gamut evaluation index table, and determining an object color gamut evaluation index according to the color gamut evaluation index table; adjusting the character color gamut value based on the character color gamut evaluation index, and adjusting the object color gamut value based on the object color gamut evaluation index; and projecting each frame of image to be projected based on the adjusted text color gamut value and the adjusted object color gamut value of each frame of image to be projected.
In the process of improving the color gamut projection, the final character color gamut value and the final character color gamut value of each frame of image to be projected are improved through the character color gamut value and the character color gamut evaluation index of the character image in each frame of image to be projected, and the object color gamut value and the object color gamut evaluation index of the object image in each frame of image to be projected, so that the non-imbalance of the white balance of the picture gray scale is ensured to the greatest extent.
Further, the step 104 of determining the character color gamut evaluation index of the digital image in each frame of the image to be projected according to the color gamut evaluation index table includes:
determining a character color gamut evaluation index of the digital image to be projected in each frame according to the information intensity of each information reported by any pixel path of the digital image to be projected in each frame in a preset time period, the time for reporting each information, the maximum information intensity in each information and the current time, wherein the preset time period is determined according to the current time and a preset time interval;
the calculation formula of the character color gamut evaluation index of the digital image in each frame of the image to be projected is as follows:
Figure 121519DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 35249DEST_PATH_IMAGE002
、
Figure 234674DEST_PATH_IMAGE003
is a constant number of times, and is,
Figure 550248DEST_PATH_IMAGE004
for the information strength of the ith piece of information in the pixel path,
Figure 72365DEST_PATH_IMAGE005
for the maximum information strength among the respective information,
Figure 598025DEST_PATH_IMAGE006
is the current time of the day, and is,
Figure 614522DEST_PATH_IMAGE007
the time for reporting the ith information in the pixel path is defined, and m is the total number of information reported in the pixel path.
Specifically, a color gamut evaluation index table is preset in the projection system, and a text image in each frame of an image to be projected includes M rows of pixels and N columns of pixels, so that the color gamut evaluation index table includes M rows and N columns of pixels, as shown in fig. 2, fig. 2 is a pixel path schematic diagram provided by the present application, an element in the table of fig. 2 is a text color gamut evaluation index of a pixel path formed by a corresponding row pixel i and a column pixel j, and fig. 2 exemplifies 4 rows of pixels i and 4 columns of pixels j.
Further, the character color gamut evaluation index is evaluated based on two dimensions of information intensity and time, the average information intensity condition in a certain period of time is represented, and the time isThe closer the weight is. Illustratively, for each frame of a digital image to be projected, a pixel path consisting of a row pixel numbered i and a column pixel numbered j
Figure 299450DEST_PATH_IMAGE011
(Pixel Path)
Figure 8780DEST_PATH_IMAGE012
I.e. in fig. 2
Figure 880790DEST_PATH_IMAGE013
) According to the current time and the preset time interval, determining the historical time of which the time interval with the current time is the preset time interval, and taking the time interval formed according to the historical time and the current time as the preset time interval. Then, the path of the pixel in the preset time period is determined
Figure 435400DEST_PATH_IMAGE011
Reporting m pieces of information to the projection system, and acquiring the information intensity of any one piece of information i
Figure 700466DEST_PATH_IMAGE014
Reporting the time required for any information i to the projection system respectively
Figure 439752DEST_PATH_IMAGE015
Maximum information intensity of character image in each frame of image to be projected
Figure 549790DEST_PATH_IMAGE016
And the current time
Figure 891779DEST_PATH_IMAGE017
. Finally, based on the intensity of each information
Figure 302031DEST_PATH_IMAGE018
Time of day
Figure 602432DEST_PATH_IMAGE019
Most preferablyBig information intensity
Figure 730925DEST_PATH_IMAGE020
And the current time
Figure 142183DEST_PATH_IMAGE021
Determining a pixel path
Figure 875784DEST_PATH_IMAGE011
The character color gamut evaluation index at the current moment is as follows:
Figure 350015DEST_PATH_IMAGE001
Figure 434646DEST_PATH_IMAGE002
、
Figure 259382DEST_PATH_IMAGE022
is a constant number of times, and is,
Figure 362337DEST_PATH_IMAGE023
for the information strength of the ith piece of information in the pixel path,
Figure 489693DEST_PATH_IMAGE024
for the maximum information strength among the respective information,
Figure 576466DEST_PATH_IMAGE006
is the current time of the day, and is,
Figure 814681DEST_PATH_IMAGE007
the time for reporting the ith information in the pixel path is defined, and m is the total number of information reported in the pixel path.
The embodiment of the invention accurately determines the character color gamut evaluation index of the digital image in each frame of the image to be projected, and ensures that the white balance of the picture gray scale is not disordered to the greatest extent.
Further, the determining, according to the color gamut evaluation index table, the object color gamut evaluation index of the object image in each frame of the image to be projected according to step 104 includes:
determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the information intensity of each piece of information reported by any pixel path of the object image in each frame of image to be projected within a preset time period, the time for reporting each piece of information, the maximum information intensity in each piece of information and the current time, wherein the preset time period is determined according to the current time and a preset time interval;
the object color gamut evaluation index calculation formula of the object image in each frame of image to be projected is as follows:
Figure 37720DEST_PATH_IMAGE008
wherein,
Figure 195032DEST_PATH_IMAGE009
、
Figure 988676DEST_PATH_IMAGE010
is a constant number of times, and is,
Figure 282779DEST_PATH_IMAGE023
for the information strength of the ith piece of information in the pixel path,
Figure 970112DEST_PATH_IMAGE024
for the maximum information strength among the respective information,
Figure 439270DEST_PATH_IMAGE006
as the current time, the time of day,
Figure 969478DEST_PATH_IMAGE007
the time for reporting the ith information in the pixel path is defined, and n is the total number of information reported in the pixel path.
Specifically, a color gamut evaluation index table is preset in the projection system, and if an object image in each frame of an image to be projected includes M rows of pixels and N columns of pixels, the color gamut evaluation index table includes M rows and N columns of pixels, as shown in fig. 2, fig. 2 is a pixel path schematic diagram provided in the present application, an element in the table of fig. 2 is an object color gamut evaluation index of a pixel path formed by a corresponding row pixel i and a column pixel j, and fig. 2 exemplifies 4 rows of pixels i and 4 columns of pixels j.
Further, the object color gamut evaluation index is evaluated based on two dimensions of information intensity and time, the average information intensity condition in a certain period of time is represented, and the closer the time is, the larger the weight occupied by the time is. Illustratively, for each frame of the object image to be projected, the pixel path is composed of row pixels with the number i and column pixels with the number j
Figure 815074DEST_PATH_IMAGE025
(Pixel Path)
Figure 622493DEST_PATH_IMAGE026
I.e. in fig. 2
Figure 511820DEST_PATH_IMAGE027
) According to the current time and the preset time interval, determining historical time with the time interval of the current time as the preset time interval, and taking a time interval formed according to the historical time and the current time as a preset time interval. Then, determining the path of the pixel in the preset time period
Figure 14477DEST_PATH_IMAGE028
Reporting n pieces of information to the projection system, and acquiring the information intensity of any one piece of information i
Figure 522819DEST_PATH_IMAGE023
Reporting the time required for any information i to the projection system respectively
Figure 100002_309378DEST_PATH_IMAGE007
Maximum information intensity of object image in each frame of image to be projected
Figure 120339DEST_PATH_IMAGE024
And the current time. Finally, based on the intensity of each information
Figure 893648DEST_PATH_IMAGE023
Time of day
Figure 815467DEST_PATH_IMAGE007
Maximum information intensity
Figure 331899DEST_PATH_IMAGE024
And the current time
Figure 563029DEST_PATH_IMAGE006
Determining a pixel path
Figure 305857DEST_PATH_IMAGE029
The object gamut evaluation index at the present time is:
Figure 156002DEST_PATH_IMAGE030
Figure 917153DEST_PATH_IMAGE009
、
Figure 69917DEST_PATH_IMAGE010
is a constant number of times, and is,
Figure 283730DEST_PATH_IMAGE023
for the information strength of the ith piece of information in the pixel path,
Figure 937565DEST_PATH_IMAGE024
for the maximum information strength among the respective information,
Figure 303955DEST_PATH_IMAGE006
is the current time of the day, and is,
Figure 891536DEST_PATH_IMAGE007
the time for reporting the ith information in the pixel path is defined, and n is the total number of information reported in the pixel path.
The embodiment of the invention accurately determines the object color gamut evaluation index of the object image in each frame of image to be projected, and ensures that the white balance of the picture gray scale is not disordered to the greatest extent.
Further, the adjusting of the character color gamut value based on the character color gamut evaluation index of each frame of the image to be projected, which is recorded in step 105, includes:
if the character color gamut evaluation index of each frame of the image to be projected is that the character color gamut value of each frame of the image to be projected is larger than the first character color gamut value, the character color gamut value of each frame of the image to be projected is reduced, so that the character color gamut value of each frame of the image to be projected after adjustment is larger than the second character color gamut value and smaller than the first character color gamut value;
if the character color gamut evaluation index of each frame of the image to be projected is that the character color gamut value of each frame of the image to be projected is smaller than the second character color gamut value, the character color gamut value of each frame of the image to be projected is increased, so that the character color gamut value of each frame of the image to be projected after adjustment is larger than the second character color gamut value and smaller than the first character color gamut value.
Specifically, if the character color gamut evaluation index of each frame of the image to be projected is determined as follows: the character color gamut value of each frame of the image to be projected is larger than the first character color gamut value, namely the character color gamut value of each frame of the image to be projected is too high, the projection system reduces the character color gamut value of each frame of the image to be projected so that the character color gamut value of each frame of the image to be projected after adjustment is larger than the second character color gamut value and smaller than the first character color gamut value, wherein the first character color gamut value and the second character color gamut value are set by technical personnel.
If the character color gamut evaluation index of each frame of the image to be projected is determined as follows: and the character color gamut value of each frame of the image to be projected is smaller than the second character color gamut value, namely the character color gamut value of each frame of the image to be projected is too low, and the projection system increases the character color gamut value of each frame of the image to be projected so that the adjusted character color gamut value of each frame of the image to be projected is larger than the second character color gamut value and smaller than the first character color gamut value.
If the character color gamut evaluation index of each frame of the image to be projected is determined as follows: the character color gamut value of each frame of the image to be projected is larger than the second character color gamut value and smaller than the first character color gamut value, namely the character color gamut value of each frame of the image to be projected belongs to a normal range, and the projection system keeps the character color gamut value of each frame of the image to be projected.
The embodiment of the invention accurately adjusts the character color gamut value of each frame of image to be projected through the character color gamut evaluation index of each frame of image to be projected, and ensures that the white balance of the picture gray scale is not disordered to the maximum extent
Further, the adjusting the object color gamut value based on the object color gamut evaluation index of each frame to be projected, which is described in step 105, includes:
if the object color gamut evaluation index of each frame of image to be projected is that the object color gamut value of each frame of image to be projected is greater than the first object color gamut value, the object color gamut value of each frame of image to be projected is reduced, so that the adjusted object color gamut value of each frame of image to be projected is greater than the second object color gamut value and smaller than the first object color gamut value;
if the object color gamut evaluation index of each frame of image to be projected is that the object color gamut value of each frame of image to be projected is smaller than the second object color gamut value, the object color gamut value of each frame of image to be projected is increased, so that the adjusted object color gamut value of each frame of image to be projected is larger than the second object color gamut value and smaller than the first object color gamut value.
Specifically, if it is determined that the object gamut evaluation index of each frame of the image to be projected is: and the object color gamut value of each frame of the image to be projected is greater than the first object color gamut value, namely the object color gamut value of each frame of the image to be projected is too high, the projection system reduces the object color gamut value of each frame of the image to be projected so that the adjusted object color gamut value of each frame of the image to be projected is greater than the second object color gamut value and smaller than the first object color gamut value, wherein the first object color gamut value and the second object color gamut value are set by technical personnel.
If the object color gamut evaluation index of each frame of the image to be projected is determined as follows: and the object color gamut value of each frame of the image to be projected is smaller than the second object color gamut value, namely the object color gamut value of each frame of the image to be projected is too low, and the projection system increases the object color gamut value of each frame of the image to be projected so that the adjusted object color gamut value of each frame of the image to be projected is larger than the second object color gamut value and smaller than the first object color gamut value.
If each frame of image to be projected is determined the object gamut evaluation index of (a) is: and the object color gamut value of each frame of image to be projected is greater than the second object color gamut value and smaller than the first object color gamut value, namely the object color gamut value of each frame of image to be projected belongs to a normal range, and the projection system maintains the object color gamut value of each frame of image to be projected.
According to the method and the device, the object color gamut evaluation index of each frame of image to be projected is used for accurately adjusting the object color gamut value of each frame of image to be projected, so that the white balance of the picture gray scale is ensured to be not maladjusted to the maximum extent.
Further, before analyzing the data to be projected and obtaining the text image and the object image of each frame of the image to be projected in the data to be projected, the method described in step 101 further includes:
carrying out normalization processing on the type characteristics of the digital image in each image to be trained, and carrying out unique hot coding after normalization processing to generate a character type vector of each image to be trained;
carrying out one-hot coding on the information characteristics of the digital image in each image to be trained to generate a character information vector of each image to be trained;
connecting the character type vector and the character information vector of each image to be trained to obtain a character training vector of each image to be trained;
and training the deep neural network of the character features based on the character training vector of each image to be trained to obtain the character feature model.
It should be noted that the Deep Neural Network DNN (Deep Neural Network) with literal features in the embodiment of the present invention is composed of a fully-connected layer with an input dimension of 256, a fully-connected layer with an input dimension of 128, and a fully-connected layer with an output dimension of 32.
In particular, the projection system determinesAnd determining each image to be trained in the image set to be trained. Further, the projection system normalizes the type characteristics of the digital image in each image to be trained to obtain a character image after normalization of each image to be trained, wherein the normalization formula is
Figure 874536DEST_PATH_IMAGE031
Wherein, X is a sample value,
Figure 722275DEST_PATH_IMAGE032
is the average value of the samples and is,
Figure 943172DEST_PATH_IMAGE033
is the sample standard deviation. Further, the projection system performs one-hot encoding on the text image subjected to normalization processing on each image to be trained to generate a text type vector of each image to be trained.
Further, the projection system directly performs unique hot coding on the information characteristics of the digital image in each image to be trained to generate a text information vector of each image to be trained, the text information vector of each image to be trained obtained after one-hot unique coding, and the text information vector is in a shape of [0,1,0,0,0], wherein the marked value is 1, and other values are 0.
Furthermore, the projection system connects the character type vector and the character information vector of each image to be trained, and obtaining the character training vector of each image to be trained.
In one embodiment, the text training vector for each image to be trained can be used
Figure 952585DEST_PATH_IMAGE034
The word type vector of each image to be trained can be expressed by
Figure 16356DEST_PATH_IMAGE035
The word information vector of each image to be trained can be expressed
Figure 887360DEST_PATH_IMAGE036
Representing, therefore, the literal training vector of each image to be trained
Figure 212031DEST_PATH_IMAGE034
=
Figure 143078DEST_PATH_IMAGE037
。
And finally, the projection system trains the deep neural network of the character features through the character training vector of each image to be trained to obtain a character feature model.
It should be noted that when the color gamut value of the text image in each frame of the image to be projected needs to be determined, the text feature model only needs to input the type feature and the information feature of the text image in each frame of the image to be projected into the text feature model, and the text feature model can extract the color gamut value of the text image in each frame of the image to be projected according to the type feature and the information feature of the text image in each frame of the image to be projected.
The embodiment of the invention directly extracts the character color gamut value of the character image in each frame of the image to be projected through the character characteristic model, thereby ensuring the white balance of the picture gray scale to be not disordered to the maximum extent.
Further, before analyzing the data to be projected and obtaining the text image and the object image of each frame of the image to be projected in the data to be projected, the method described in step 101 further includes:
carrying out normalization processing on the type characteristics of the object image in each image to be trained, and carrying out unique hot coding after normalization processing to generate an object type vector of each image to be trained;
carrying out independent thermal coding on the size characteristics of the object image in each image to be trained to generate an object size vector of each image to be trained;
connecting the object type vector and the object size vector of each image to be trained to obtain an object training vector of each image to be trained;
and training the deep neural network of the object characteristics based on the object training vector of each image to be trained to obtain the object characteristic model.
It should be noted that the deep neural network DNN of the object feature model in the embodiment of the present invention is composed of a fully-connected layer with an input dimension of 128, a fully-connected layer with an input dimension of 64, and a fully-connected layer with an output dimension of 32.
Specifically, the projection system determines a set of images to be trained for model training and determines each image to be trained in the set of images to be trained. Further, the projection system normalizes the type characteristics of the object image in each image to be trained to obtain the normalized object image of each image to be trained, wherein the normalization formula is
Figure 694145DEST_PATH_IMAGE031
Wherein X is a sample value,
Figure 355458DEST_PATH_IMAGE032
is the average value of the samples and is,
Figure 550947DEST_PATH_IMAGE033
is the sample standard deviation. Further, the projection system performs one-hot encoding on each object image subjected to normalization processing on each image to be trained, and generates an object type vector of each image to be trained.
Further, the projection system directly performs unique hot coding on the size features of the object image in each image to be trained to generate an object size vector of each image to be trained, and the object size vector of each image to be trained is obtained after one-hot unique coding.
Further, the projection system connects the object type vector and the object size vector of each image to be trained to obtain an object training vector of each image to be trained.
In one embodiment, the object training vector for each image to be trained may be used
Figure 167742DEST_PATH_IMAGE038
Representing that the object type vector of each image to be trained can be used
Figure 815892DEST_PATH_IMAGE039
Representing that the object size vector of each image to be trained can be used
Figure 887753DEST_PATH_IMAGE040
Representing, therefore, object training vectors for each image to be trained
Figure 452596DEST_PATH_IMAGE038
=
Figure 725445DEST_PATH_IMAGE041
。
And finally, the projection system trains the deep neural network of the object characteristics through the object training vector of each image to be trained to obtain an object characteristic model.
When the object color gamut value of the object image in each frame of the image to be projected is determined, only the type feature and the size feature of the object image in each frame of the image to be projected are input into the object feature model, and the object feature model can extract the object color gamut value of the object image in each frame of the image to be projected according to the type feature and the size feature of the object image in each frame of the image to be projected.
According to the embodiment of the invention, the object color gamut value of the object image in each frame of the image to be projected is directly extracted through the object characteristic model, so that the white balance of the picture gray scale is ensured to be not disordered to the greatest extent.
Further, the projection system for improving the color gamut provided by the application and the projection method for improving the color gamut provided by the application are referred to correspondingly.
Fig. 3 is a block diagram of a color gamut enhanced projection system provided in the present application, where the color gamut enhanced projection system includes:
the analysis module 301 is configured to analyze data to be projected to obtain a text image and an object image of each frame of image to be projected in the data to be projected;
the first determining module 302 is configured to determine, through the text feature model, a text color gamut value of a text image in each frame of the image to be projected according to the type feature and the information feature of the digital image in each frame of the image to be projected;
the second determining module 303 is configured to determine, through the object feature model, an object color gamut value of the object image in each frame of the image to be projected according to the type feature and the size feature of the object image in each frame of the image to be projected;
a third determining module 304, configured to determine, according to a color gamut evaluation index table, a character color gamut evaluation index of the digital image in each frame of the image to be projected, and determine, according to the color gamut evaluation index table, an object color gamut evaluation index of the object image in each frame of the image to be projected;
the adjusting module 305 is configured to adjust a text gamut value of each frame of image to be projected based on the text gamut evaluation index of each frame of image to be projected, and adjust an object gamut value of each frame of image to be projected based on the object gamut evaluation index of each frame of image to be projected;
and the projection module 306 is configured to project each frame of image to be projected based on the adjusted text color gamut value and the adjusted object color gamut value of each frame of image to be projected.
Further, the third determining module 304 is further configured to:
determining a character color gamut evaluation index of the digital image to be projected in each frame according to the information intensity of each information reported by any pixel path of the digital image to be projected in each frame in a preset time period, the time for reporting each information, the maximum information intensity in each information and the current time, wherein the preset time period is determined according to the current time and a preset time interval;
the calculation formula of the character color gamut evaluation index of the digital image in each frame of the image to be projected is as follows:
Figure 985525DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 985711DEST_PATH_IMAGE002
、
Figure 155793DEST_PATH_IMAGE022
is a constant number of times, and is,
Figure 851741DEST_PATH_IMAGE023
for the information strength of the ith piece of information in the pixel path,
Figure 740062DEST_PATH_IMAGE024
for the maximum information strength among the respective information,
Figure 153726DEST_PATH_IMAGE006
as the current time, the time of day,
Figure 427581DEST_PATH_IMAGE007
and m is the total number of the information reported in the pixel path.
Further, the third determining module 304 is further configured to:
determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the information intensity of each piece of information reported by any pixel path of the object image in each frame of image to be projected within a preset time period, the time for reporting each piece of information, the maximum information intensity in each piece of information and the current time, wherein the preset time period is determined according to the current time and a preset time interval;
the object color gamut evaluation index calculation formula of the object image in each frame of image to be projected is as follows:
Figure 307813DEST_PATH_IMAGE030
wherein the content of the first and second substances,
Figure 667119DEST_PATH_IMAGE009
、
Figure 290998DEST_PATH_IMAGE010
is a constant number of times, and is,
Figure 481677DEST_PATH_IMAGE023
for the information strength of the ith piece of information in the pixel path,
Figure 660373DEST_PATH_IMAGE024
for the maximum information strength among the respective information,
Figure 788866DEST_PATH_IMAGE006
as the current time, the time of day,
Figure 934546DEST_PATH_IMAGE007
and reporting the time of the ith information in the pixel path, wherein n is the total number of the information reported in the pixel path.
Further, the adjusting module 305 is further configured to:
if the character color gamut evaluation index of each frame of the image to be projected is that the character color gamut value of each frame of the image to be projected is larger than the first character color gamut value, the character color gamut value of each frame of the image to be projected is reduced, so that the character color gamut value of each frame of the image to be projected after adjustment is larger than the second character color gamut value and smaller than the first character color gamut value;
if the character color gamut evaluation index of each frame of the image to be projected is that the character color gamut value of each frame of the image to be projected is smaller than the second character color gamut value, the character color gamut value of each frame of the image to be projected is increased, so that the character color gamut value of each frame of the image to be projected after adjustment is larger than the second character color gamut value and smaller than the first character color gamut value.
Further, the adjusting module 305 is further configured to:
if the object color gamut evaluation index of each frame of image to be projected is that the object color gamut value of each frame of image to be projected is greater than the first object color gamut value, the object color gamut value of each frame of image to be projected is reduced, so that the adjusted object color gamut value of each frame of image to be projected is greater than the second object color gamut value and smaller than the first object color gamut value;
if the object color gamut evaluation index of each frame of the image to be projected is that the object color gamut value of each frame of the image to be projected is smaller than the second object color gamut value, the object color gamut value of each frame of the image to be projected is increased, so that the adjusted object color gamut value of each frame of the image to be projected is larger than the second object color gamut value and smaller than the first object color gamut value.
Further, the color gamut enhanced projection system further comprises a training module for:
carrying out normalization processing on the type characteristics of the digital image in each image to be trained, and carrying out unique hot coding after normalization processing to generate a character type vector of each image to be trained;
carrying out one-hot coding on the information characteristics of the digital image in each image to be trained to generate a character information vector of each image to be trained;
connecting the character type vector and the character information vector of each image to be trained to obtain a character training vector of each image to be trained;
and training the deep neural network of the character features based on the character training vector of each image to be trained to obtain the character feature model.
Further, the training module is further configured to:
normalizing the type characteristics of the object image in each image to be trained, and performing unique thermal coding after normalization to generate an object type vector of each image to be trained;
carrying out independent thermal coding on the size characteristics of the object image in each image to be trained to generate an object size vector of each image to be trained;
connecting the object type vector and the object size vector of each image to be trained to obtain an object training vector of each image to be trained;
and training the deep neural network of the object characteristics based on the object training vector of each image to be trained to obtain the object characteristic model.
The specific embodiment of the projection system for improving the color gamut provided by the present application is substantially the same as the embodiments of the projection method for improving the color gamut, and details are not described herein.
Fig. 4 illustrates a physical structure diagram of a projector, and as shown in fig. 4, the projector may include: a processor (processor) 410, a communication interface (communication interface) 420, a memory (memory) 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 are communicated with each other via the communication bus 440. The processor 410 may invoke logic instructions in the memory 430 to perform a gamut enhancing projection method comprising:
analyzing data to be projected to obtain a character image and an object image of each frame of image to be projected in the data to be projected;
determining a character color gamut value of a character image in each frame of images to be projected according to the type characteristics and the information characteristics of the digital image in each frame of images to be projected by a character characteristic model;
determining an object color gamut value of an object image in each frame of image to be projected according to the type characteristic and the size characteristic of the object image in each frame of image to be projected through an object characteristic model;
determining a character color gamut evaluation index of the digital image in each frame of image to be projected according to a color gamut evaluation index table, and determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the color gamut evaluation index table;
adjusting the character color gamut value of each frame of image to be projected based on the character color gamut evaluation index of each frame of image to be projected, and adjusting the object color gamut value of each frame of image to be projected based on the object color gamut evaluation index of each frame of image to be projected;
and projecting each frame of image to be projected based on the adjusted text color gamut value and the adjusted object color gamut value of each frame of image to be projected.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, an optical disk, or other various media capable of storing program codes.
In another aspect, the present application also provides a computer program product, which includes a computer program stored on a non-transitory computer readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer being capable of executing the color gamut enhancing projection method provided by the above methods, the method including:
analyzing data to be projected to obtain a character image and an object image of each frame of image to be projected in the data to be projected;
determining a character color gamut value of a character image in each frame of images to be projected according to the type characteristics and the information characteristics of the digital image in each frame of images to be projected by a character characteristic model;
determining an object color gamut value of an object image in each frame of image to be projected according to the type characteristic and the size characteristic of the object image in each frame of image to be projected through an object characteristic model;
determining a character color gamut evaluation index of the digital image in each frame of image to be projected according to a color gamut evaluation index table, and determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the color gamut evaluation index table;
adjusting the character color gamut value of each frame of image to be projected based on the character color gamut evaluation index of each frame of image to be projected, and adjusting the object color gamut value of each frame of image to be projected based on the object color gamut evaluation index of each frame of image to be projected;
and projecting each frame of image to be projected based on the adjusted text color gamut value and the adjusted object color gamut value of each frame of image to be projected.
In yet another aspect, the present application further provides a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program being implemented by a processor to perform the above-provided color gamut enhancing projection method, the method comprising:
analyzing the data to be projected to obtain a character image and an object image of each frame of image to be projected in the data to be projected;
determining a character color gamut value of a character image in each frame of images to be projected according to the type characteristics and the information characteristics of the digital image in each frame of images to be projected by a character characteristic model;
determining an object color gamut value of an object image in each frame of image to be projected according to the type characteristic and the size characteristic of the object image in each frame of image to be projected through an object characteristic model;
determining a character color gamut evaluation index of the digital image in each frame of image to be projected according to a color gamut evaluation index table, and determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the color gamut evaluation index table;
adjusting the character color gamut value of each frame of image to be projected based on the character color gamut evaluation index of each frame of image to be projected, and adjusting the object color gamut value of each frame of image to be projected based on the object color gamut evaluation index of each frame of image to be projected;
and projecting each frame of image to be projected based on the adjusted text color gamut value and the adjusted object color gamut value of each frame of image to be projected.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. Based on the understanding, the above technical solutions substantially or otherwise contributing to the prior art may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should 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 in the embodiments of the present application.

Claims (10)

1. A color gamut enhanced projection method, comprising:
analyzing data to be projected to obtain a character image and an object image of each frame of image to be projected in the data to be projected;
determining a character color gamut value of a character image in each frame of images to be projected according to the type characteristics and the information characteristics of the digital image in each frame of images to be projected by a character characteristic model;
determining an object color gamut value of an object image in each frame of image to be projected according to the type characteristic and the size characteristic of the object image in each frame of image to be projected through an object characteristic model;
determining a character color gamut evaluation index of the digital image in each frame of image to be projected according to a color gamut evaluation index table, and determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the color gamut evaluation index table;
adjusting the character color gamut value of each frame of image to be projected based on the character color gamut evaluation index of each frame of image to be projected, and adjusting the object color gamut value of each frame of image to be projected based on the object color gamut evaluation index of each frame of image to be projected;
and projecting each frame of image to be projected based on the adjusted text color gamut value and the adjusted object color gamut value of each frame of image to be projected.
2. The color gamut improving projection method according to claim 1, wherein the determining the text color gamut evaluation index of the digital image to be projected in each frame according to the color gamut evaluation index table comprises:
determining a character color gamut evaluation index of the digital image to be projected in each frame according to the information intensity of each information reported by any pixel path of the digital image to be projected in each frame in a preset time period, the time for reporting each information, the maximum information intensity in each information and the current time, wherein the preset time period is determined according to the current time and a preset time interval;
the calculation formula of the character color gamut evaluation index of the digital image in each frame of the image to be projected is as follows:
Figure 415951DEST_PATH_IMAGE002
wherein the content of the first and second substances,
Figure DEST_PATH_IMAGE003
、
Figure 129829DEST_PATH_IMAGE004
is a constant number of times, and is,
Figure DEST_PATH_IMAGE005
for the information strength of the ith piece of information in the pixel path,
Figure 34200DEST_PATH_IMAGE006
for the maximum information strength among the respective information,
Figure DEST_PATH_IMAGE007
is the current time of the day, and is,
Figure 786999DEST_PATH_IMAGE008
the time for reporting the ith information in the pixel path is defined, and m is the total number of information reported in the pixel path.
3. The color gamut improving projection method according to claim 1, wherein the determining an object color gamut evaluation index of an object image in each frame of an image to be projected according to the color gamut evaluation index table comprises:
determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the information intensity of each piece of information reported by any pixel path of the object image in each frame of image to be projected within a preset time period, the time for reporting each piece of information, the maximum information intensity in each piece of information and the current time, wherein the preset time period is determined according to the current time and a preset time interval;
the object color gamut evaluation index calculation formula of the object image in each frame of image to be projected is as follows:
Figure 132530DEST_PATH_IMAGE010
wherein, the first and the second end of the pipe are connected with each other,
Figure DEST_PATH_IMAGE011
、
Figure 751730DEST_PATH_IMAGE012
is a constant number of times, and is,
Figure 81080DEST_PATH_IMAGE005
for the information strength of the ith piece of information in the pixel path,
Figure 811139DEST_PATH_IMAGE006
for the most in each informationThe intensity of the large information is high,
Figure 309378DEST_PATH_IMAGE007
is the current time of the day, and is,
Figure 833901DEST_PATH_IMAGE008
the time for reporting the ith information in the pixel path is defined, and n is the total number of information reported in the pixel path.
4. The color gamut enhancing projection method according to claim 1, wherein the adjusting the text color gamut value based on the text color gamut evaluation index of each frame to be projected comprises:
if the character color gamut evaluation index of each frame of the image to be projected is that the character color gamut value of each frame of the image to be projected is larger than the first character color gamut value, the character color gamut value of each frame of the image to be projected is reduced, so that the character color gamut value of each frame of the image to be projected after adjustment is larger than the second character color gamut value and smaller than the first character color gamut value;
if the character color gamut evaluation index of each frame of the image to be projected is that the character color gamut value of each frame of the image to be projected is smaller than the second character color gamut value, the character color gamut value of each frame of the image to be projected is increased, so that the character color gamut value of each frame of the image to be projected after adjustment is larger than the second character color gamut value and smaller than the first character color gamut value.
5. The color gamut improving projection method according to claim 1, wherein the adjusting the object color gamut value based on the object color gamut evaluation index of each frame of the image to be projected comprises:
if the object color gamut evaluation index of each frame of the image to be projected is that the object color gamut value of each frame of the image to be projected is greater than the first object color gamut value, the object color gamut value of each frame of the image to be projected is reduced, so that the adjusted object color gamut value of each frame of the image to be projected is greater than the second object color gamut value and smaller than the first object color gamut value;
if the object color gamut evaluation index of each frame of the image to be projected is that the object color gamut value of each frame of the image to be projected is smaller than the second object color gamut value, the object color gamut value of each frame of the image to be projected is increased, so that the adjusted object color gamut value of each frame of the image to be projected is larger than the second object color gamut value and smaller than the first object color gamut value.
6. The color gamut enhancing projection method according to any one of claims 1 to 5, wherein before analyzing the data to be projected to obtain the text image and the object image of each frame of the data to be projected, the method further comprises:
carrying out normalization processing on the type characteristics of the digital image in each image to be trained, and carrying out unique hot coding after normalization processing to generate a character type vector of each image to be trained;
carrying out one-hot coding on the information characteristics of the digital image in each image to be trained to generate a character information vector of each image to be trained;
connecting the character type vector and the character information vector of each image to be trained to obtain a character training vector of each image to be trained;
and training the deep neural network of the character features based on the character training vector of each image to be trained to obtain the character feature model.
7. The color gamut enhancing projection method according to any one of claims 1 to 5, wherein before analyzing the data to be projected to obtain the text image and the object image of each frame of the data to be projected, the method further comprises:
normalizing the type characteristics of the object image in each image to be trained, and performing unique thermal coding after normalization to generate an object type vector of each image to be trained;
carrying out unique thermal coding on the size characteristics of the object image in each image to be trained to generate an object size vector of each image to be trained;
connecting the object type vector and the object size vector of each image to be trained to obtain an object training vector of each image to be trained;
and training the deep neural network of the object characteristics based on the object training vector of each image to be trained to obtain the object characteristic model.
8. An improved color gamut projection system, comprising:
the analysis module is used for analyzing the data to be projected to obtain a character image and an object image of each frame of image to be projected in the data to be projected;
the first determining module is used for determining the character color gamut value of the character image in each frame of the image to be projected according to the type characteristics and the information characteristics of the character image in each frame of the image to be projected through the character characteristic model;
the second determination module is used for determining the object color gamut value of the object image in each frame of image to be projected according to the type feature and the size feature of the object image in each frame of image to be projected through the object feature model;
the third determining module is used for determining a character color gamut evaluation index of the digital image in each frame of image to be projected according to a color gamut evaluation index table and determining an object color gamut evaluation index of an object image in each frame of image to be projected according to the color gamut evaluation index table;
the adjusting module is used for adjusting the character color gamut value of each frame of image to be projected based on the character color gamut evaluation index of each frame of image to be projected and adjusting the object color gamut value of each frame of image to be projected based on the object color gamut evaluation index of each frame of image to be projected;
and the projection module is used for projecting each frame of image to be projected based on the adjusted character color gamut value and the adjusted object color gamut value of each frame of image to be projected.
9. A projector comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the color gamut enhanced projection method according to any one of claims 1 to 7 when executing the computer program.
10. A non-transitory computer readable storage medium comprising a computer program, wherein the computer program when executed by a processor implements the color gamut enhanced projection method of any one of claims 1 to 7.
CN202211427616.8A 2022-11-15 2022-11-15 Projection method, projection system and projector for improving color gamut Active CN115604448B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211427616.8A CN115604448B (en) 2022-11-15 2022-11-15 Projection method, projection system and projector for improving color gamut

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211427616.8A CN115604448B (en) 2022-11-15 2022-11-15 Projection method, projection system and projector for improving color gamut

Publications (2)

Publication Number Publication Date
CN115604448A true CN115604448A (en) 2023-01-13
CN115604448B CN115604448B (en) 2023-04-07

Family

ID=84853524

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211427616.8A Active CN115604448B (en) 2022-11-15 2022-11-15 Projection method, projection system and projector for improving color gamut

Country Status (1)

Country Link
CN (1) CN115604448B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8749478B1 (en) * 2009-08-21 2014-06-10 Amazon Technologies, Inc. Light sensor to adjust contrast or size of objects rendered by a display
US9495915B1 (en) * 2010-12-20 2016-11-15 Amazon Technologies, Inc. Display adjustments using a light sensor
CN111312141A (en) * 2020-02-18 2020-06-19 京东方科技集团股份有限公司 Color gamut adjusting method and device
CN112399089A (en) * 2019-08-19 2021-02-23 比亚迪股份有限公司 Method for improving visual effect of high dynamic range image and related equipment thereof
CN114363597A (en) * 2022-01-21 2022-04-15 深圳市普渡科技有限公司 Character projection method, device, robot and storage medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8749478B1 (en) * 2009-08-21 2014-06-10 Amazon Technologies, Inc. Light sensor to adjust contrast or size of objects rendered by a display
US9495915B1 (en) * 2010-12-20 2016-11-15 Amazon Technologies, Inc. Display adjustments using a light sensor
CN112399089A (en) * 2019-08-19 2021-02-23 比亚迪股份有限公司 Method for improving visual effect of high dynamic range image and related equipment thereof
CN111312141A (en) * 2020-02-18 2020-06-19 京东方科技集团股份有限公司 Color gamut adjusting method and device
CN114363597A (en) * 2022-01-21 2022-04-15 深圳市普渡科技有限公司 Character projection method, device, robot and storage medium

Also Published As

Publication number Publication date
CN115604448B (en) 2023-04-07

Similar Documents

Publication Publication Date Title
Gu et al. Blind quality assessment of tone-mapped images via analysis of information, naturalness, and structure
Kanan et al. Color-to-grayscale: does the method matter in image recognition?
US11790198B2 (en) Method and apparatus for processing encoded pattern, storage medium, and electronic apparatus
CN111241291B (en) Method and device for generating countermeasure sample by utilizing countermeasure generation network
CN112818737A (en) Video identification method and device, storage medium and terminal
WO2022227547A1 (en) Method and apparatus for image processing, electronic device, and storage medium
CN111415304A (en) Underwater vision enhancement method and device based on cascade deep network
CN113553954A (en) Method and apparatus for training behavior recognition model, device, medium, and program product
US20170048533A1 (en) Video transcoding method and device
CN111028222A (en) Video detection method and device, computer storage medium and related equipment
Pishori et al. Detecting deepfake videos: An analysis of three techniques
CN113392791A (en) Skin prediction processing method, device, equipment and storage medium
CN105893927B (en) Animation video identification and coding method and device
CN115604448B (en) Projection method, projection system and projector for improving color gamut
CN112818774A (en) Living body detection method and device
WO2021000407A1 (en) Character verification method and apparatus, and computer device and storage medium
CN108665455B (en) Method and device for evaluating image significance prediction result
CN115457015A (en) Image no-reference quality evaluation method and device based on visual interactive perception double-flow network
CN114896594A (en) Malicious code detection device and method based on image feature multi-attention learning
CN110766153A (en) Neural network model training method and device and terminal equipment
US20220164934A1 (en) Image processing method and apparatus, device, video processing method and storage medium
US20220398504A1 (en) Learning system, learning method and program
CN115484447B (en) Projection method, projection system and projector based on high color gamut adjustment
CN110163761B (en) Suspicious item member identification method and device based on image processing
Tapia et al. An efficient super-resolution single image network using sharpness loss metrics for iris

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
GR01 Patent grant
GR01 Patent grant