CN115147326A - Color cast detection method and device, and storage medium - Google Patents
Color cast detection method and device, and storage medium Download PDFInfo
- Publication number
- CN115147326A CN115147326A CN202110331992.6A CN202110331992A CN115147326A CN 115147326 A CN115147326 A CN 115147326A CN 202110331992 A CN202110331992 A CN 202110331992A CN 115147326 A CN115147326 A CN 115147326A
- Authority
- CN
- China
- Prior art keywords
- color cast
- display screen
- cast detection
- model
- image acquisition
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 132
- 238000003860 storage Methods 0.000 title claims abstract description 11
- 230000000712 assembly Effects 0.000 claims abstract description 43
- 238000000429 assembly Methods 0.000 claims abstract description 43
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims description 39
- 238000013135 deep learning Methods 0.000 claims description 32
- 238000012360 testing method Methods 0.000 claims description 27
- 238000000605 extraction Methods 0.000 claims description 15
- 230000015654 memory Effects 0.000 claims description 13
- 238000011176 pooling Methods 0.000 claims description 8
- 238000009826 distribution Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 230000001953 sensory effect Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 4
- 230000005291 magnetic effect Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 2
- 208000003464 asthenopia Diseases 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30121—CRT, LCD or plasma display
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The disclosure relates to a color cast detection method and device and a storage medium. The method comprises the following steps: acquiring images of a display screen when the display screen displays a picture through a plurality of image acquisition assemblies; the image acquisition assemblies are distributed at different angles; and inputting the images acquired from multiple angles into a preset color cast detection model to obtain a color cast detection result of the display screen. By the method, the detection efficiency can be improved, the problem of inconsistent judgment standards caused by sensory differences among different personnel is reduced, the problem of missed detection or over detection is reduced, and the accuracy of color cast detection is improved.
Description
Technical Field
The present disclosure relates to the field of electronic devices, and in particular, to a color shift detection method and apparatus, and a storage medium.
Background
The viewing angle color shift of an organic light-Emitting Diode (OLED) display panel seriously affects the quality of the screen. Need manage and control and detect this type of phenomenon in process of production, present detection scheme is the screen of lightening under the volume production environment, rotates the screen angle under specific picture, observes the detection through artificial mode to the screen.
The manual detection mode has extremely low efficiency, and the production line can cause eye fatigue due to long-time manual operation, so that batch omission or over-detection is very easy to occur.
Disclosure of Invention
In order to overcome the above technical problems, an object of the present disclosure is to provide a color shift detection method and apparatus, and a storage medium, so as to improve detection efficiency and accuracy of color shift detection.
In order to achieve the purpose, the technical scheme adopted by the disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, there is provided a color cast detection method, including:
acquiring images of a display screen when the display screen displays a picture through a plurality of image acquisition assemblies; the image acquisition assemblies are distributed at different angles;
and inputting the images acquired from multiple angles into a preset color cast detection model to obtain a color cast detection result of the display screen.
In some embodiments, the color cast detection model is constructed by deep learning; the sample image adopted by the color cast detection model is acquired by a plurality of image acquisition assemblies distributed at different angles to a plurality of display screens.
In some embodiments, the method for constructing the color cast detection model includes:
dividing a sample image of the plurality of display screens into a first portion and a second portion; wherein sample images of the same display screen are in the same portion;
and taking the sample image of the first part as a training set and the sample image of the second part as a test set, and training by utilizing a deep learning network to obtain the color cast detection model.
In some embodiments, the obtaining the color cast detection model by using deep learning network training with the sample images of the first part as a training set and the sample images of the second part as a test set includes:
inputting the sample image of the first part as a training set into the deep learning network, and combining a preset label of the sample image of the first part to obtain an initial model;
inputting the sample image of the second part as the test set into the initial model to obtain a model output result;
and adjusting and optimizing the network of the initial model according to the model output result and the preset label of the sample image of the second part to obtain the color cast detection model.
In some embodiments, the deep learning network comprises a plurality of feature extraction sub-modules, one said feature extraction sub-module comprising: convolutional layers, active layers, and pooling layers.
In some embodiments, said plurality of said image acquisition assemblies comprises 5 of said image acquisition assemblies; one of the image acquisition assemblies is perpendicular to the display screen, and the remaining 4 image acquisition assemblies are respectively distributed at an angle of 30 degrees with the image acquisition assemblies perpendicular to the display screen.
According to a second aspect of the embodiments of the present disclosure, there is provided an information control apparatus including:
the acquisition module is configured to acquire images of the display screen of the detected equipment when the display screen displays a picture through a plurality of image acquisition components; the image acquisition assemblies are distributed at different angles;
and the detection module is configured to input images acquired from multiple angles into a preset color cast detection model to obtain a color cast detection result of the display screen.
In some embodiments, the apparatus further comprises:
a model construction module configured to construct the color cast detection model by deep learning; the sample image adopted for constructing the color cast detection model is obtained by carrying out image acquisition on a plurality of display screens by a plurality of image acquisition assemblies distributed at different angles.
In some embodiments, the model building module comprises:
a dividing module configured to divide sample images of the plurality of display screens into a first portion and a second portion; wherein sample images of the same display screen are in the same portion;
and the training module is configured to train the sample images of the first part as a training set and the sample images of the second part as a test set by using a deep learning network to obtain the color cast detection model.
In some embodiments, the training module is further configured to input the sample images of the first part as a training set into the deep learning network, and obtain an initial model in combination with preset labels of the sample images of the first part; inputting the sample image of the second part as the test set into the initial model to obtain a model output result; and adjusting and optimizing the network of the initial model according to the model output result and the preset label of the sample image of the second part to obtain the color cast detection model.
In some embodiments, the deep learning network comprises a plurality of feature extraction sub-modules, one said feature extraction sub-module comprising: convolutional layers, active layers, and pooling layers.
In some embodiments, said plurality of said image acquisition assemblies comprises 5 of said image acquisition assemblies; one of the image acquisition assemblies is perpendicular to the display screen, and the remaining 4 image acquisition assemblies are respectively distributed at an angle of 30 degrees with the image acquisition assemblies perpendicular to the display screen.
According to a third aspect of the embodiments of the present disclosure, there is provided a color shift detection apparatus including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the color shift detection method as described in the first aspect above.
According to a fourth aspect of an embodiment of the present disclosure, there is provided a storage medium including:
the instructions in said storage medium, when executed by a processor of a colour shift detection apparatus, enable the colour shift detection apparatus to perform a colour shift detection method as described in the first aspect above.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects:
in the embodiment of the disclosure, images acquired from a plurality of angles when a display screen displays a picture are obtained, and the images of the plurality of angles are input into a preset color cast detection model to obtain a color cast detection result, so that on one hand, the detection efficiency can be greatly improved in an automatic detection mode; on the other hand, the problem of inconsistent judgment standards caused by sensory differences among different people can be reduced, in addition, the possibility of missed detection or over detection can be reduced, and the accuracy of color cast detection is improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is a flowchart illustrating a color cast detection method according to an embodiment of the disclosure.
Fig. 2 is a diagram illustrating a distribution of an exemplary image capture assembly in an embodiment of the present disclosure.
Fig. 3 is an exemplary diagram of an exemplary detection module in an embodiment of the disclosure.
Fig. 4 is a diagram illustrating a color shift detection device according to an exemplary embodiment.
Fig. 5 is a block diagram illustrating a color shift detection apparatus according to an exemplary embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the disclosure, as detailed in the appended claims.
Fig. 1 is a flowchart of a color cast detection method according to an embodiment of the disclosure, and as shown in fig. 1, the color cast detection method includes the following steps:
s11, acquiring images of a display screen when the display screen displays a picture through a plurality of image acquisition assemblies; the image acquisition assemblies are distributed at different angles;
and S12, inputting the images acquired from multiple angles into a preset color cast detection model to obtain a color cast detection result of the display screen.
In the embodiment of the present disclosure, the color cast detection method may be applied to a detection device on a production line, where the detection device may be a terminal device such as a computer. The detection device may include a plurality of image capturing components, or may be externally connected to the plurality of image capturing components, for example, the image capturing component is a camera based on charge-coupled device (CCD) sensor imaging, or a camera based on Complementary Metal-Oxide-Semiconductor (CMOS) sensor imaging.
In step S11, the detection apparatus may acquire an image of the display screen of the device under test when displaying the screen through a plurality of image capturing assemblies distributed at different angles. The detected device can be a mobile phone, a tablet computer or other intelligent devices with a display screen.
It should be noted that the display screen on the display screen of the device under test may be a screen of a predetermined color, such as a screen of full white or full black, or a grayscale screen between full white and full black. The image acquisition assemblies distributed at different angles can acquire images of the display screen when the display screen displays the images.
In step S12, the detection device inputs images acquired from a plurality of angles into a predetermined color shift detection model to obtain a color shift detection result of the display screen.
In the embodiment of the present disclosure, the predetermined color shift detection model may be a model obtained in a training manner, or may be a non-training manner, and color-related features are extracted from images obtained from multiple angles and analyzed to obtain a detection result of whether color shift exists.
It should be noted that, when a single image capturing assembly captures an image, the angle at which light is incident on the image capturing assembly may affect the color of the image, so that it is not accurate enough to determine whether the color shift problem exists in the display screen based on the image. Therefore, the display screen can acquire images through multiple angles, influence of ambient light on imaging colors can be reduced as much as possible, and accuracy of color cast problem detection is improved.
In addition, in the embodiment of the present disclosure, after the detecting device detects the color shift of the display screen of the device under test, if it is determined that the display screen of the device under test does not have the color shift, it indicates that the display screen of the device under test is a qualified screen. And if the display screen is determined to have color cast after the color cast detection model is used for detection, the display screen can be rechecked again in a manual detection mode.
In the related color cast detection method, the angle of the display screen is rotated under a specific picture, and the display screen is observed and detected in a manual mode. The defects that the manual detection efficiency is extremely low, the judgment standard is possibly inconsistent due to sensory differences among personnel, the long-time manual operation of a production line can cause eye fatigue, and the problems of batch missed detection or over-detection and the like are very easy to occur.
In contrast, the method and the device have the advantages that the images of the display screen collected from multiple angles are obtained when the display screen displays the picture, and the images of the multiple angles are input into the preset color cast detection model so as to obtain the color cast detection result, so that on one hand, the detection efficiency can be greatly improved in an automatic detection mode; on the other hand, the problem of inconsistent judgment standards caused by sensory differences among different people can be reduced, in addition, the possibility of missed detection or over detection can be reduced, and the accuracy of color cast detection is improved.
In some embodiments, the plurality of image acquisition assemblies comprises 5 of the image acquisition assemblies; one the image acquisition assembly with the display screen is perpendicular, and the remaining 4 the image acquisition assembly is respectively with perpendicular to the image acquisition assembly of display screen is 30 angle distributions.
Fig. 2 is a diagram illustrating a distribution of an exemplary image capture assembly in an embodiment of the present disclosure. As shown in fig. 2, the camera a is perpendicular to the display screen (display panel) O and is located right above the display screen O. And the other 4 cameras B, C, D, E surround the camera a and are respectively distributed at 30-degree included angles with the camera a. As shown in fig. 2, taking a camera a and a camera B as an example, a projection point of the camera a on the display screen O is M, and an included angle Q between a connection line of the camera a and the projection point M and a connection line of the camera B and the projection point M is 30 degrees. Through this distribution mode for the camera can cover different shooting angles, thereby reduces the influence of ambient light incident angle to the formation of image color.
In some embodiments, the color cast detection model is constructed by deep learning; the sample image adopted for constructing the color cast detection model is obtained by carrying out image acquisition on a plurality of display screens by a plurality of image acquisition assemblies distributed at different angles.
In this embodiment, the color cast detection model is constructed by performing deep learning on sample images from multiple display screens, where the sample image of the same display screen includes multiple images from different angles.
For example, sample images of 10000 display screens may be acquired, and the sample image of the same display screen includes 5 images at different angles.
It should be noted that, in the embodiment of the present disclosure, in the sample data acquisition stage, the number of sample images may be determined according to the calculation capability of the detection apparatus and/or the model accuracy requirement, and generally, the higher the calculation capability is, or the higher the model accuracy requirement is, the more samples may be acquired.
In addition, for the collected sample images, corresponding labels can be preset so as to facilitate the training of the model. For example, for a plurality of sample images of the same display screen, a result of whether color shift exists on the display screen can be manually given based on each sample image, for example, the corresponding label "OK" when color shift does not exist, and the corresponding label "NG" when color shift exists. In the embodiment of the disclosure, as many display screens exist, as many corresponding labels exist, and the labels are stored after being in one-to-one correspondence with the images of the display screens.
For example, if each display screen has 5 images at different angles, the 5 images of each display screen are superimposed to form an image set. If each image is of size [576,224,3], then the set of images after each display screen overlay is [576,224,15]. For 10000 displays, the sample image set is [576,224,15,10000], and the number of label sets is 10000 × 1.
In some embodiments, the deep learning network comprises a plurality of feature extraction sub-modules, one said feature extraction sub-module comprising: convolutional layers, active layers, and pooling layers.
In an embodiment of the present disclosure, the deep learning network adopts a multi-layer network structure, and includes a plurality of feature extraction sub-modules. A feature extraction submodule includes a convolutional layer, an active layer, and a pooling layer. Wherein, the convolution layer obtains a plurality of local characteristics through local perception and weight sharing; the active layer carries out nonlinear mapping on the result of the convolutional layer so as to improve the adaptability of the model; and the pooling layer performs data dimension reduction on the result of the active layer, and reduces redundant information.
Fig. 3 is an exemplary diagram of an exemplary detection module in an embodiment of the disclosure. As shown in fig. 3, after the images (image sets) acquired from multiple angles are input into the feature extraction module of the multi-layer structure through the input module, the output result of the model can be obtained based on the multiple fully-connected layers of the decision layer module.
The deep learning network disclosed by the present disclosure may be a residual error network RESNET, or may also be a Long Short-Term Memory network (LSTM), etc., and the embodiments of the present disclosure are not limited thereto.
In some embodiments, when the color cast detection model is constructed,
dividing a sample image of a plurality of display screens into a first portion and a second portion; wherein sample images of the same display screen are in the same portion;
and taking the sample image of the first part as a training set and the sample image of the second part as a test set, and training by utilizing a deep learning network to obtain the color cast detection model.
In the embodiment of the disclosure, the sample images of different display screens are divided into two parts, namely a first part and a second part, and the sample images of the same display screen are in the same part. The color cast detection model can be obtained by combining deep learning network training based on the sample image of the first part as a training set and the sample image of the second part as a testing set.
It should be noted that the number of sample images that are the first part of the training set may be greater than the number of sample images that are the second part of the test set. In addition, in the embodiment of the disclosure, in order to improve the accuracy of the model, a certain number of "OK" samples and "NG" samples are required to be included in both the training set and the test set.
For example, for sample images of 10000 display screens, 70% of the sample images may be used as a training set, the size of which is [576,224,15,7000]. Meanwhile, 7000 sets contain the training set of 5 images, which also correspond to 7000 preset labels. The remaining 30% of the sample images were used as test sets, the size of the test set was [576,224,15,3000],3000 groups of test sets containing 5 images, corresponding to 3000 preset labels.
In some embodiments, the obtaining the color cast detection model by using deep learning network training with the sample images of the first part as a training set and the sample images of the second part as a test set includes:
inputting the sample image of the first part as a training set into the deep learning network, and combining a preset label of the sample image of the first part to obtain an initial model;
inputting the sample image of the second part as the test set into the initial model to obtain a model output result;
and adjusting and optimizing the network of the initial model according to the model output result and the preset label of the sample image of the second part to obtain the color cast detection model.
In this embodiment, the initial model is trained using sample images as a first part of a training set. After the sample images of the first part are input into the deep learning network to obtain training values, the difference between the training values and the preset labels of the samples is measured by using a loss function in combination with the preset labels of the sample images of the first part, and therefore parameters in the network are updated through back propagation to obtain an initial model.
In order to improve the generalization capability of the model, the sample image of the second part of the test set is input into the initial model to obtain the output result of the model, and then the output result of the model is compared with the preset label of the sample image of the second part to calculate the accuracy of the initial model. If the accuracy of the initial model is not too high, the network of the initial model may be optimized, including optimizing network parameters in the model, or optimizing the structure of the network, and the like, which is not limited in this embodiment of the disclosure.
Fig. 4 is a diagram illustrating a color shift detection device according to an exemplary embodiment. Referring to fig. 4, in an alternative embodiment, the apparatus comprises:
the acquisition module 101 is configured to acquire images of a display screen when the display screen displays a screen through a plurality of image acquisition components; the image acquisition assemblies are distributed at different angles;
the detection module 102 is configured to input images acquired from multiple angles into a predetermined color cast detection model, so as to obtain a color cast detection result of the display screen.
In some embodiments, the apparatus further comprises:
a model construction module 103 configured to construct the color cast detection model by deep learning; the sample image adopted for constructing the color cast detection model is obtained by carrying out image acquisition on a plurality of display screens by a plurality of image acquisition assemblies distributed at different angles.
In some embodiments, the model building module 103 comprises:
a dividing module 104 configured to divide the sample image of the different display screen into a first portion and a second portion; wherein sample images of the same display screen are in the same portion;
and the training module 105 is configured to train the sample images of the first part as a training set and the sample images of the second part as a test set by using a deep learning network to obtain the color cast detection model.
In some embodiments, the training module 105 is further configured to input the sample images of the first part as a training set into the deep learning network, and obtain an initial model in combination with preset labels of the sample images of the first part; inputting the sample image of the second part as the test set into the initial model to obtain a model output result; and adjusting and optimizing the network of the initial model according to the model output result and the preset label of the sample image of the second part to obtain the color cast detection model.
In some embodiments, the deep learning network comprises a plurality of feature extraction sub-modules, one said feature extraction sub-module comprising: convolutional layers, active layers, and pooling layers.
In some embodiments, the plurality of image acquisition assemblies comprises 5 of the image acquisition assemblies; one of the image acquisition assemblies is perpendicular to the display screen, and the remaining 4 image acquisition assemblies are respectively distributed at an angle of 30 degrees with the image acquisition assemblies perpendicular to the display screen.
With regard to the apparatus in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be described in detail here.
Fig. 5 is a block diagram illustrating a color shift detection apparatus 800 according to an exemplary embodiment. For example, the device 800 may be a computer or the like.
Referring to fig. 5, the apparatus 800 may include one or more of the following components: processing component 802, memory 804, power component 806, multimedia component 808, audio component 810, input/output (I/O) interface 812, sensor component 814, and communication component 816.
The processing component 802 generally controls overall operation of the device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 802 may include one or more processors 820 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 802 can include one or more modules that facilitate interaction between the processing component 802 and other components. For example, the processing component 802 can include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
The memory 804 is configured to store various types of data to support operation at the device 800. Examples of such data include instructions for any application or method operating on device 800, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 804 may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The multimedia component 808 includes a screen that provides an output interface between the device 800 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 800 is in an operational mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 810 is configured to output and/or input audio signals. For example, the audio component 810 includes a Microphone (MIC) configured to receive external audio signals when the apparatus 800 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 804 or transmitted via the communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.
The I/O interface 812 provides an interface between the processing component 802 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor assembly 814 includes one or more sensors for providing various aspects of state assessment for the device 800. For example, the sensor assembly 814 may detect the open/closed state of the device 800, the relative positioning of the components, such as a display and keypad of the apparatus 800, the sensor assembly 814 may also detect a change in position of the apparatus 800 or a component of the apparatus 800, the presence or absence of user contact with the apparatus 800, orientation or acceleration/deceleration of the apparatus 800, and a change in temperature of the apparatus 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of a nearby object in the absence of any physical contact. The sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 816 is configured to facilitate communications between the apparatus 800 and other devices in a wired or wireless manner. The device 800 may access a wireless network based on a communication standard, such as Wi-Fi,2G, or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described methods.
In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 804 comprising instructions, executable by the processor 820 of the device 800 to perform the above-described method is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
A non-transitory computer readable storage medium having instructions therein, which when executed by a processor of a color cast detection apparatus, enable the color cast detection apparatus to perform a control method, the method comprising:
acquiring images of a display screen when the display screen displays a picture through a plurality of image acquisition assemblies; the image acquisition assemblies are distributed at different angles;
and inputting the images acquired from multiple angles into a preset color cast detection model to obtain a color cast detection result of the display screen.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (14)
1. A color cast detection method, the method comprising:
acquiring images of a display screen when the display screen displays a picture through a plurality of image acquisition assemblies; the image acquisition assemblies are distributed at different angles;
and inputting images acquired from multiple angles into a preset color cast detection model to obtain a color cast detection result of the display screen.
2. The color cast detection method according to claim 1, wherein the color cast detection model is constructed by deep learning; the sample image adopted for constructing the color cast detection model is obtained by carrying out image acquisition on a plurality of display screens by a plurality of image acquisition assemblies distributed at different angles.
3. The color cast detection method according to claim 2, wherein the color cast detection model is constructed by a method comprising:
dividing a sample image of the plurality of display screens into a first portion and a second portion; wherein sample images of the same display screen are in the same portion;
and taking the sample images of the first part as a training set and the sample images of the second part as a test set, and training by utilizing a deep learning network to obtain the color cast detection model.
4. The method according to claim 3, wherein the obtaining the color cast detection model by using deep learning network training with the sample images of the first part as a training set and the sample images of the second part as a testing set comprises:
inputting the sample image of the first part as a training set into the deep learning network, and combining a preset label of the sample image of the first part to obtain an initial model;
inputting the sample image of the second part as the test set into the initial model to obtain a model output result;
and adjusting and optimizing the network of the initial model according to the model output result and the preset label of the sample image of the second part to obtain the color cast detection model.
5. The color cast detection method according to claim 2, wherein the deep learning network comprises a plurality of feature extraction sub-modules, and one of the feature extraction sub-modules comprises: convolutional layers, active layers, and pooling layers.
6. The color cast detection method according to claim 1, wherein the plurality of image capturing components comprises 5 image capturing components; one of the image acquisition assemblies is perpendicular to the display screen, and the remaining 4 image acquisition assemblies are respectively distributed at an angle of 30 degrees with the image acquisition assemblies perpendicular to the display screen.
7. A color shift detection device, the device comprising:
the acquisition module is configured to acquire images of the display screen when the display screen displays the images through the plurality of image acquisition components; the image acquisition assemblies are distributed at different angles;
and the detection module is configured to input images acquired from multiple angles into a preset color cast detection model to obtain a color cast detection result of the display screen.
8. The color shift detection device according to claim 7, wherein the device further comprises:
a model construction module configured to construct the color cast detection model through deep learning; the sample image adopted for constructing the color cast detection model is obtained by carrying out image acquisition on a plurality of display screens by a plurality of image acquisition assemblies distributed at different angles.
9. The color cast detection device of claim 8, wherein the device model construction module comprises:
a dividing module configured to divide sample images of the plurality of display screens into a first portion and a second portion; wherein sample images of the same display screen are in the same portion;
and the training module is configured to use the sample images of the first part as a training set and the sample images of the second part as a test set, and train by using a deep learning network to obtain the color cast detection model.
10. The color shift detection device according to claim 9,
the training module is further configured to input the sample images of the first part serving as a training set into the deep learning network, and obtain an initial model by combining preset labels of the sample images of the first part; inputting the sample image of the second part as the test set into the initial model to obtain a model output result; and adjusting and optimizing the network of the initial model according to the model output result and the preset label of the sample image of the second part to obtain the color cast detection model.
11. The color cast detection device of claim 8, wherein the deep learning network comprises a plurality of feature extraction sub-modules, one of the feature extraction sub-modules comprising: convolutional layers, active layers, and pooling layers.
12. The color cast detection device of claim 7, wherein the plurality of image capture assemblies comprises 5 of the image capture assemblies; one the image acquisition assembly with the display screen is perpendicular, and the remaining 4 the image acquisition assembly is respectively with perpendicular to the image acquisition assembly of display screen is 30 angle distributions.
13. A color cast detection device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to perform the color shift detection method of any one of claims 1 to 6.
14. A non-transitory computer readable storage medium having instructions therein which, when executed by a processor of a color cast detection apparatus, enable the color cast detection apparatus to perform the color cast detection method of any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110331992.6A CN115147326A (en) | 2021-03-29 | 2021-03-29 | Color cast detection method and device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110331992.6A CN115147326A (en) | 2021-03-29 | 2021-03-29 | Color cast detection method and device, and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115147326A true CN115147326A (en) | 2022-10-04 |
Family
ID=83404339
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110331992.6A Pending CN115147326A (en) | 2021-03-29 | 2021-03-29 | Color cast detection method and device, and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115147326A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20100094373A (en) * | 2009-02-17 | 2010-08-26 | 가부시끼가이샤 니혼 마이크로닉스 | Method and apparatus for testing liquid crystal display |
CN106231295A (en) * | 2016-08-04 | 2016-12-14 | 惠州市德赛西威汽车电子股份有限公司 | A kind of display screen image quality automatic checkout system, detection method and application thereof |
CN106526910A (en) * | 2016-10-12 | 2017-03-22 | 昆山龙腾光电有限公司 | Image quality inspection device, transmission system, and display graded transmission method |
CN206479733U (en) * | 2017-02-14 | 2017-09-08 | 昆山龙腾光电有限公司 | LCDs detecting system |
CN108846841A (en) * | 2018-07-02 | 2018-11-20 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
CN108961238A (en) * | 2018-07-02 | 2018-12-07 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
CN109064446A (en) * | 2018-07-02 | 2018-12-21 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
-
2021
- 2021-03-29 CN CN202110331992.6A patent/CN115147326A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20100094373A (en) * | 2009-02-17 | 2010-08-26 | 가부시끼가이샤 니혼 마이크로닉스 | Method and apparatus for testing liquid crystal display |
CN106231295A (en) * | 2016-08-04 | 2016-12-14 | 惠州市德赛西威汽车电子股份有限公司 | A kind of display screen image quality automatic checkout system, detection method and application thereof |
CN106526910A (en) * | 2016-10-12 | 2017-03-22 | 昆山龙腾光电有限公司 | Image quality inspection device, transmission system, and display graded transmission method |
CN206479733U (en) * | 2017-02-14 | 2017-09-08 | 昆山龙腾光电有限公司 | LCDs detecting system |
CN108846841A (en) * | 2018-07-02 | 2018-11-20 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
CN108961238A (en) * | 2018-07-02 | 2018-12-07 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
CN109064446A (en) * | 2018-07-02 | 2018-12-21 | 北京百度网讯科技有限公司 | Display screen quality determining method, device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
RU2630167C1 (en) | Method and device for switching colour range mode | |
EP3379805B1 (en) | Method, apparatus for controlling a smart device and computer storage medium | |
CN105678296B (en) | Method and device for determining character inclination angle | |
CN105357449A (en) | Shooting method and device, and image processing method and apparatus | |
CN112033527B (en) | Ambient brightness detection method, device, equipment and storage medium | |
CN107657608B (en) | Image quality determination method and device and electronic equipment | |
CN106557294A (en) | Color adjustment method and device | |
CN104536713B (en) | Method and device for displaying characters in image | |
CN107609513B (en) | Video type determination method and device | |
CN113705389A (en) | Face recognition module testing method and device, storage medium and electronic equipment | |
CN112750081A (en) | Image processing method, device and storage medium | |
CN112905135A (en) | Screen brightness processing method, electronic device and storage medium | |
CN112261453A (en) | Method, device and storage medium for transmitting subtitle splicing map | |
CN111131596B (en) | Screen brightness adjusting method and device | |
CN108650412B (en) | Display method, display device and computer readable storage medium | |
CN115706750B (en) | Color temperature calibration method, color temperature calibration device and storage medium | |
CN112188111B (en) | Photographing method and device, terminal and storage medium | |
CN115147326A (en) | Color cast detection method and device, and storage medium | |
CN108182658B (en) | Image beautifying method and device | |
CN111835977B (en) | Image sensor, image generation method and device, electronic device, and storage medium | |
CN111263190A (en) | Video processing method and device, server and storage medium | |
CN111753753A (en) | Image recognition method and device, electronic equipment and storage medium | |
CN113709275A (en) | Ambient light determination method and device, terminal equipment and storage medium | |
CN110213524B (en) | Video networking conference exception handling method and device | |
CN112822465B (en) | Terminal equipment and image processing method |
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 |