CN114494096A - Image segmentation method and system for double-layer liquid crystal display - Google Patents
Image segmentation method and system for double-layer liquid crystal display Download PDFInfo
- Publication number
- CN114494096A CN114494096A CN202210129925.0A CN202210129925A CN114494096A CN 114494096 A CN114494096 A CN 114494096A CN 202210129925 A CN202210129925 A CN 202210129925A CN 114494096 A CN114494096 A CN 114494096A
- Authority
- CN
- China
- Prior art keywords
- image
- liquid crystal
- layer
- double
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000004973 liquid crystal related substance Substances 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000003709 image segmentation Methods 0.000 title claims abstract description 41
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 45
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 239000010410 layer Substances 0.000 claims description 85
- 238000012549 training Methods 0.000 claims description 28
- 238000012360 testing method Methods 0.000 claims description 8
- 238000004891 communication Methods 0.000 claims description 7
- 239000002355 dual-layer Substances 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 238000013500 data storage Methods 0.000 claims description 3
- 238000006073 displacement reaction Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 238000005457 optimization Methods 0.000 abstract 1
- 230000000007 visual effect Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000000853 adhesive Substances 0.000 description 1
- 230000001070 adhesive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Control Of Indicators Other Than Cathode Ray Tubes (AREA)
Abstract
The invention discloses an image segmentation method and system for double-layer liquid crystal screen display, wherein the double-layer liquid crystal screen is a front liquid crystal screen close to audiences and a rear liquid crystal screen close to a backlight module respectively, and the image segmentation method comprises the following steps: constructing a convolutional neural network model, wherein the convolutional neural network model is used for processing an input image to obtain a first image and a second image and sending the second image to a rear liquid crystal screen, and the first image is used for being sent to a front liquid crystal screen; the second image is subjected to image reconstruction through the first image, and the image reconstruction is used for improving the problem of artifacts of double-screen liquid crystal display and improving the image display quality; sending the reconstructed second image to a rear liquid crystal screen; the method has a great optimization effect on the artifact phenomenon and the image quality of the double-layer screen, and compared with an image segmentation algorithm based on viewpoint compensation, the calculation speed is also greatly improved.
Description
Technical Field
The invention relates to the technical field of liquid crystal display, in particular to an image segmentation method and an image segmentation system for double-layer liquid crystal screen display.
Background
The high dynamic range allows the viewer to see more accurate and precise details. Conventional liquid crystal displays are not capable of achieving high dynamic range due to the inherent disadvantages of light leakage, which is a great challenge for OLED displays. The double-layer liquid crystal display combines two liquid crystal panels together by using the high-light-transmission optical adhesive, so that light leakage is effectively reduced, and the contrast is improved. Due to the fact that there are two panels, the display image must be split into two sub-images, transmitted to the back plane (close to the backlight unit) and the front panel (close to the viewer), respectively. The image segmentation algorithm in existence at present basically blurs the image sent to the next layer of liquid crystal panel (close to the backlight) to form small partitions with the same brightness. The image segmentation algorithm based on the fuzzy processing is simple, but artifacts exist when the image is obliquely viewed (under a certain visual angle), and the display quality is influenced. And the other image segmentation algorithm based on viewpoint compensation considers the display quality while eliminating parallax error, but the algorithm has huge calculation load and cannot finish quick processing.
Disclosure of Invention
In order to solve the above problems, an object of the present invention is to provide an image segmentation method and system for dual-layer lcd display, which are used to avoid the artifact phenomenon when the existing dual-layer lcd is viewed obliquely and improve the display quality.
In order to achieve the above technical object, the present application provides an image segmentation method for displaying a double-layer liquid crystal display, where the double-layer liquid crystal display is a front liquid crystal display close to a viewer and a rear liquid crystal display close to a backlight module, respectively, and the method includes the following steps:
constructing a convolutional neural network model, wherein the convolutional neural network model is used for processing an input image to obtain a first image and a second image and sending the second image to a rear liquid crystal screen, and the first image is used for being sent to a front liquid crystal screen;
the second image is subjected to image reconstruction through the first image, and the image reconstruction is used for improving the artifact problem of double-screen liquid crystal display and improving the image display quality;
and sending the reconstructed second image to a rear liquid crystal screen.
Preferably, in the process of constructing the convolutional neural network model, a training data set for training the convolutional neural network model is constructed according to the input images, wherein the images of the training data set are all the same-size images with vertical lines.
Preferably, in the process of constructing the training data set, each image of the training data set is divided into 3 channels, each image containing 10 blocks, wherein the images of the training data set are sequentially shuffled 6 times before testing.
Preferably, in the process of constructing the convolutional neural network model, the convolutional neural network model comprises an input layer, a convolutional layer and an output layer, wherein the convolutional neural network model is composed of 8 sequentially stacked two-dimensional convolutions;
the input layer comprises 5 convolution kernels of 3 x 3;
the convolutional layer comprises 64 convolution kernels of 3 x 3, wherein the convolutional layer is a Conv convolutional layer;
the output layer includes 2 64 convolution kernels of 3 x 3.
Preferably, in the process of constructing the convolutional neural network model, full connection is formed between layers of the convolutional neural network model, where the full connection is used to represent a feature map of a layer above the convolutional neural network model as an input of a current layer, and the feature map of the current layer is an input of a next layer.
Preferably, in the process of reconstructing the second image, the pixel values of the first image and the second image are multiplied by shifting after being subjected to gray scale normalization to obtain a reconstructed image, wherein the shifting is multiplied by five times, the first image is not moved, the second image is positioned on the left of the first image from the first time to the fifth time, the third time is opposite to the first image, the fourth time and the fifth time are positioned on the right of the first image, and the distances of each shift are equal.
Preferably, in the process of obtaining the reconstructed image, obtaining a loss function of the reconstructed image and the original image as a loss function of the convolutional neural network model;
the loss function is expressed as:
wherein, IinputRepresenting an input image, IrefRepresenting an image reconstructed by the input image after network processing, wherein n represents the number of pixels of the input image, Loss represents a Loss function, and the input image is a rectangle.
Preferably, during the acquisition of the reconstructed image, the reconstructed image is evaluated by a peak signal-to-noise ratio, wherein the peak signal-to-noise ratio is calculated by the following formula:
wherein n is the bit number of each pixel, and MES is the mean square error;
the MES has the formula:
wherein MES represents mean square error of I (I, j) and K (I, j), I (I, j) and K (I, j) represent gray values of the processed image and the original image at (I, j) pixel points respectively, I and j represent pixel coordinate positions, M is the height of the image, and N is the width of the image.
The invention also discloses an image segmentation system for double-layer liquid crystal screen display, the two layers of liquid crystal screens are respectively a front liquid crystal screen close to audiences and a rear liquid crystal screen close to a backlight module, and the image segmentation system comprises:
the image acquisition module is used for acquiring an input image;
the image processing module is used for processing the input image to obtain a first image and a second image by constructing a convolutional neural network model and sending the first image to the front liquid crystal screen;
and the image reconstruction module is used for reconstructing the second image through the first image and sending the reconstructed second image to the rear liquid crystal screen, wherein the image reconstruction is used for improving the artifact problem of the double-screen liquid crystal display and improving the image display quality.
Preferably, the image segmentation system further comprises:
the data storage module is used for storing the first image and the second image;
the communication module is used for sending the first image and the second image to a control system of the double-layer liquid crystal screen, wherein the control system is used for expressing a system or a program for controlling the double-layer liquid crystal screen to display the images;
the communication module is also used for receiving the first image;
the image segmentation system is also used as a control system of the double-layer liquid crystal screen.
The invention discloses the following technical effects:
the invention can effectively improve the artifact problem of the double-screen liquid crystal display, improve the image display quality and greatly improve the image processing speed. The image segmentation algorithm provided by the invention utilizes the convolutional neural network, simulates real images of a display seen by human eyes under different visual angles through training of a large number of data sets, compares the real images with a test image, updates convolutional neural network parameters through forward transmission, and gives consideration to the display effects of a plurality of visual angles.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a schematic diagram of a convolutional neural network structure according to the present invention;
FIG. 2 is a schematic representation of the process steps of the present invention;
fig. 3 is a schematic diagram of the system structure according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
As shown in fig. 1-3, the present invention provides an image segmentation method for displaying a dual-layer liquid crystal screen, wherein the dual-layer liquid crystal screen is a front liquid crystal screen close to a viewer and a rear liquid crystal screen close to a backlight module, respectively, and the method comprises the following steps:
constructing a convolutional neural network model, wherein the convolutional neural network model is used for processing an input image to obtain a first image and a second image and sending the second image to a rear liquid crystal screen, and the first image is used for being sent to a front liquid crystal screen;
the second image is subjected to image reconstruction through the first image, and the image reconstruction is used for improving the artifact problem of double-screen liquid crystal display and improving the image display quality;
and sending the reconstructed second image to a rear liquid crystal screen.
Further preferably, in the process of constructing the convolutional neural network model, a training data set for training the convolutional neural network model is constructed according to the input images, wherein the images of the training data set are all the same-size images with vertical lines.
It is further preferred that in the process of constructing the training data set, each image of the training data set is divided into 3 channels, each image containing 10 blocks, wherein the images of the training data set are sequentially shuffled 6 times before testing.
Further preferably, in the process of constructing the convolutional neural network model, the convolutional neural network model comprises an input layer, a convolutional layer and an output layer, wherein the convolutional neural network model is composed of 8 sequentially stacked two-dimensional convolutions;
the input layer comprises 5 convolution kernels of 3 x 3;
the convolutional layer comprises 64 convolution kernels of 3 x 3, wherein the convolutional layer is a Conv convolutional layer;
the output layer includes 2 64 convolution kernels of 3 x 3.
Further preferably, in the process of constructing the convolutional neural network model, full connection is formed between the layers of the convolutional neural network model, where the full connection is used to represent a feature map of a layer above the convolutional neural network model as an input of a current layer, and the feature map of the current layer is an input of a next layer.
Further preferably, in the process of reconstructing the second image, the pixel values of the first image and the second image are subjected to dislocation multiplication after gray-scale normalization to obtain a reconstructed image, wherein the dislocation multiplication is performed five times, the first image is not moved, the second image is positioned on the left of the first image in the first time to the fifth time, the third time is opposite to the first image, the fourth time and the fifth time are positioned on the right of the first image, and the distance of each displacement is equal.
Further preferably, in the process of obtaining the reconstructed image, obtaining a loss function of the reconstructed image and the original image as a loss function of the convolutional neural network model;
the loss function is expressed as:
wherein, IinputRepresenting an input image, IrefRepresenting an image reconstructed by the input image after network processing, wherein n represents the number of pixels of the input image, Loss represents a Loss function, and the input image is a rectangle.
Further preferably, in the process of acquiring the reconstructed image, the reconstructed image is evaluated by a peak signal-to-noise ratio, wherein a calculation formula of the peak signal-to-noise ratio is as follows:
wherein n is the bit number of each pixel, and MES is the mean square error;
the MES has the formula:
wherein MES represents mean square error of I (I, j) and K (I, j), I (I, j) and K (I, j) represent gray values of the processed image and the original image at (I, j) pixel points respectively, I and j represent pixel coordinate positions, M is the height of the image, and N is the width of the image.
The invention also discloses an image segmentation system for double-layer liquid crystal screen display, the two layers of liquid crystal screens are respectively a front liquid crystal screen close to audiences and a rear liquid crystal screen close to a backlight module, and the image segmentation system comprises:
the image acquisition module is used for acquiring an input image;
the image processing module is used for processing the input image to obtain a first image and a second image by constructing a convolutional neural network model and sending the first image to the front liquid crystal screen;
and the image reconstruction module is used for reconstructing the second image through the first image and sending the reconstructed second image to the rear liquid crystal screen, wherein the image reconstruction is used for improving the artifact problem of the double-screen liquid crystal display and improving the image display quality.
Further preferably, the image segmentation system further comprises:
the data storage module is used for storing the first image and the second image;
the double-layer liquid crystal display system comprises a communication module, a double-layer liquid crystal display module and a display module, wherein the communication module is used for sending a first image and a second image to a control system of the double-layer liquid crystal display, and the control system is used for representing a system or a program for controlling the double-layer liquid crystal display to display images;
the communication module is also used for receiving the first image;
the image segmentation system is also used as a control system of the double-layer liquid crystal screen.
Example 1: the invention provides an image segmentation algorithm for double-layer liquid crystal screen display based on a convolutional neural network, wherein the two layers of liquid crystal screens are a front liquid crystal screen close to audiences and a rear liquid crystal screen close to a backlight module respectively, and the image segmentation algorithm is characterized by comprising the following steps of:
step (1): constructing a training data set, and carrying out preprocessing operation on the training data set;
step (2): forming a convolutional neural network model by using 8 sequentially stacked two-dimensional convolutions;
and (3): generating two pictures after the test picture passes through the step (1) and the step (2), wherein the first picture represents a front liquid crystal screen close to a viewer, the second picture represents a rear liquid crystal screen close to a backlight module, pixel value gray levels of the two pictures are normalized and then subjected to staggered multiplication to obtain a reconstructed image, the staggered multiplication is performed for 5 times, the first picture is still, the second picture is positioned on the left of the first picture twice from the first time to the fifth time, the third time is opposite to the first picture, the fourth time and the fifth time are positioned on the right of the first picture, and the displacement distance of each time is equal;
and (4): setting a loss function of the network, and optimizing the loss function;
and (5): processing images according to the trained network model, and evaluating and reconstructing images by using a peak signal-to-noise ratio;
in the step (1), the data set preprocessing operation on the training data set comprises the following steps:
1.1: selecting training samples from the training data set as an original training set, wherein images in the training samples are all images with the same size and vertical lines:
1.2: dividing each image in the training data set into 3 channels, wherein each image comprises 10 blocks, and disordering all the images in the data set for 6 times before testing;
the network model comprises an input layer, a convolution layer and an output layer, wherein in the network model, all the layers are fully connected, the feature mapping of the fully connected upper layer is used as the input of the current layer, and the feature mapping of the current layer is used as the input of the next layer;
the input layer comprises 5 convolution kernels of 3 x 3;
the intermediate convolutional layer comprises 64 convolution kernels of 3 x 3;
the output layer comprises 2 64 convolution kernels of 3 x 3;
the convolution layer is a Conv convolution layer;
the loss function of the 5 reconstructed pictures obtained in the step (3) and the original test picture is
Wherein IinputRepresenting an input image, IrefRepresenting an image reconstructed by an input image after network processing, wherein n represents the number of long and wide pixels of the input image (the input image is square), and Loss represents a Loss function;
the peak signal-to-noise ratio is calculated by the formula:
where n is the number of bits per pixel and MES is the mean square error,
the MES has the formula:
wherein MES represents the mean square error of I (I, j) and K (I, j), I (I, j) and K (I, j) represent the gray level of the processed image and the original image at the pixel point (I, j), respectively, wherein I and j represent the pixel coordinate position, M is the height of the image, and N is the width of the image.
The invention can effectively improve the artifact problem of the double-screen liquid crystal display, improve the image display quality and greatly improve the image processing speed. The image segmentation algorithm provided by the invention utilizes the convolutional neural network, simulates real images of a display seen by human eyes under different visual angles through training of a large number of data sets, compares the real images with a test image, updates convolutional neural network parameters through forward transmission, and gives consideration to the display effects of a plurality of visual angles.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures, and moreover, the terms "first," "second," "third," etc. are used merely to distinguish one description from another, and are not to be construed as indicating or implying relative importance.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those skilled in the art that the following descriptions are only illustrative and not restrictive, and that the scope of the present invention is not limited to the above embodiments: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the present invention in its spirit and scope. Are intended to be covered by the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. An image segmentation method for double-layer liquid crystal screen display, the double-layer liquid crystal screen is a front liquid crystal screen close to audience and a back liquid crystal screen close to a backlight module, characterized by comprising the following steps:
constructing a convolutional neural network model, wherein the convolutional neural network model is used for processing an input image to obtain a first image and a second image and sending the second image to the rear liquid crystal display, and the first image is used for being sent to the front liquid crystal display;
carrying out image reconstruction on the second image through the first image, wherein the image reconstruction is used for improving the artifact problem of double-screen liquid crystal display and improving the image display quality;
and sending the reconstructed second image to the rear liquid crystal screen.
2. The image segmentation method for the double-layer liquid crystal display screen according to claim 1, wherein:
in the process of constructing the convolutional neural network model, a training data set used for training the convolutional neural network model is constructed according to the input images, wherein the images of the training data set are all images with the same size and vertical lines.
3. The image segmentation method for the double-layer liquid crystal display screen according to claim 2, wherein the image segmentation method comprises the following steps:
in the process of constructing the training data set, dividing each image of the training data set into 3 channels, each image containing 10 blocks, wherein the images of the training data set are sequentially scrambled 6 times before testing.
4. The image segmentation method for the double-layer liquid crystal display screen according to claim 3, wherein the image segmentation method comprises the following steps:
in the process of constructing the convolutional neural network model, the convolutional neural network model comprises an input layer, a convolutional layer and an output layer, wherein the convolutional neural network model is composed of 8 two-dimensional convolutions which are sequentially stacked;
the input layer comprises 5 convolution kernels of 3 x 3;
the convolutional layer comprises 64 convolution kernels of 3 x 3, wherein the convolutional layer is a Conv convolutional layer;
the output layer comprises 2 64 convolution kernels of 3 x 3.
5. The image segmentation method for the double-layer liquid crystal display screen according to claim 4, wherein the image segmentation method comprises the following steps:
in the process of constructing the convolutional neural network model, all layers of the convolutional neural network model are in full connection, wherein the full connection is used for representing the feature mapping of the previous layer of the convolutional neural network model and is used as the input of the current layer, and the feature mapping of the current layer is the input of the next layer.
6. The image segmentation method for the double-layer liquid crystal display screen according to claim 5, wherein the image segmentation method comprises the following steps:
in the process of reconstructing the second image, performing staggered multiplication after gray-scale normalization of pixel values of the first image and the second image to obtain a reconstructed image, wherein the staggered multiplication is performed five times, the first image is stationary, the second image is located on the left side of the first image in the first time to the fifth time, the third time is opposite to the first image, the fourth time and the fifth time are located on the right side of the first image, and the distances of displacements are equal.
7. The image segmentation method for the double-layer liquid crystal display screen according to claim 6, wherein:
in the process of obtaining a reconstructed image, obtaining a loss function of the reconstructed image and an original image as a loss function of the convolutional neural network model;
the loss function is expressed as:
wherein, IinputRepresenting an input image, IrefRepresenting an image reconstructed by an input image after network processing, wherein n represents the number of pixels with the length and the width of the input image, and Loss represents a Loss function, and the input image is a rectangle.
8. The image segmentation method for the double-layer liquid crystal display screen according to claim 7, wherein:
in the process of obtaining a reconstructed image, evaluating the reconstructed image through a peak signal-to-noise ratio, wherein a calculation formula of the peak signal-to-noise ratio is as follows:
wherein n is the bit number of each pixel, and MES is the mean square error;
the MES has the formula:
wherein MES represents mean square error of I (I, j) and K (I, j), I (I, j) and K (I, j) represent gray values of the processed image and the original image at (I, j) pixel points respectively, I and j represent pixel coordinate positions, M is the height of the image, and N is the width of the image.
9. The utility model provides an image segmentation system for double-deck LCD screen shows, two-layer LCD screen be respectively for being close to spectator's preceding LCD screen and being close to backlight unit's back LCD screen, its characterized in that includes:
the image acquisition module is used for acquiring an input image;
the image processing module is used for processing the input image to obtain a first image and a second image by constructing a convolutional neural network model, and sending the first image to the front liquid crystal display;
and the image reconstruction module is used for reconstructing the second image through the first image and sending the reconstructed second image to the rear liquid crystal screen, wherein the image reconstruction is used for improving the artifact problem of double-screen liquid crystal display and improving the image display quality.
10. The image segmentation system for the dual-layer lcd panel display of claim 9, wherein:
the image segmentation system further comprises:
a data storage module for storing the first image and the second image;
the communication module is used for sending the first image and the second image to a control system of the double-layer liquid crystal screen, wherein the control system is used for representing a system or a program for controlling the double-layer liquid crystal screen to display images;
the communication module is further used for receiving the first image;
the image segmentation system is also used as the control system of the double-layer liquid crystal screen.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210129925.0A CN114494096A (en) | 2022-02-11 | 2022-02-11 | Image segmentation method and system for double-layer liquid crystal display |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210129925.0A CN114494096A (en) | 2022-02-11 | 2022-02-11 | Image segmentation method and system for double-layer liquid crystal display |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114494096A true CN114494096A (en) | 2022-05-13 |
Family
ID=81481247
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210129925.0A Pending CN114494096A (en) | 2022-02-11 | 2022-02-11 | Image segmentation method and system for double-layer liquid crystal display |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114494096A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116563312A (en) * | 2023-07-11 | 2023-08-08 | 山东古天电子科技有限公司 | Method for dividing display image of double-screen machine |
-
2022
- 2022-02-11 CN CN202210129925.0A patent/CN114494096A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116563312A (en) * | 2023-07-11 | 2023-08-08 | 山东古天电子科技有限公司 | Method for dividing display image of double-screen machine |
| CN116563312B (en) * | 2023-07-11 | 2023-09-12 | 山东古天电子科技有限公司 | Method for dividing display image of double-screen machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113240580B (en) | Lightweight image super-resolution reconstruction method based on multi-dimensional knowledge distillation | |
| CN112543317B (en) | Method for converting high-resolution monocular 2D video into binocular 3D video | |
| CN114742719B (en) | End-to-end image defogging method based on multi-feature fusion | |
| CN101529310A (en) | Autostereoscopic system | |
| CN109817170B (en) | Pixel compensation method and device and terminal equipment | |
| CN110516716A (en) | Non-reference picture quality appraisement method based on multiple-limb similarity network | |
| CN105096856B (en) | The driving method and drive device of liquid crystal panel | |
| CN114049464B (en) | Reconstruction method and device of three-dimensional model | |
| CN115205122B (en) | Method, system, apparatus and medium for generating hyper-resolution image maintaining structure and texture | |
| CN110599585A (en) | Single-image human body three-dimensional reconstruction method and device based on deep learning | |
| CN114494096A (en) | Image segmentation method and system for double-layer liquid crystal display | |
| CN116402721A (en) | Underwater image enhancement method based on contrast perception loss | |
| CN115205160A (en) | No-reference low-illumination image enhancement method based on local scene perception | |
| CN117437120A (en) | Image stitching method based on deep learning end to end | |
| CN114881879A (en) | Underwater image enhancement method based on brightness compensation residual error network | |
| CN112866676B (en) | Naked eye three-dimensional display algorithm based on single-pixel multi-view reconstruction | |
| US20060280244A1 (en) | Moving picture converting apparatus and method, and computer program | |
| CN111010605B (en) | Method for displaying video picture-in-picture window | |
| CN114339191B (en) | Naked eye three-dimensional display method based on multi-viewpoint reconstruction | |
| CN114879377A (en) | Parameter determination method, device and equipment of horizontal parallax three-dimensional light field display system | |
| CN115705616A (en) | True image style migration method based on structure consistency statistical mapping framework | |
| Tang et al. | Feature comparison and analysis for new challenging research fields of image quality assessment | |
| CN112991174A (en) | Method and system for improving resolution of single-frame infrared image | |
| CN107767342A (en) | Wavelet transformation super-resolution image reconstruction method based on integration adjustment Models | |
| CN112016456A (en) | Video super-resolution method and system based on adaptive back projection depth learning |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Feng Qibin Inventor after: Su Kai Inventor after: Zhang Xin Inventor after: Lv Guoqiang Inventor after: Wang Zi Inventor before: Feng Qibin Inventor before: Xiao Huili Inventor before: Zhang Le Inventor before: Yang Ling Inventor before: Lv Guoqiang |