CN111968511A - Display panel, intelligent mirror and method for determining hair style recommendation information - Google Patents

Display panel, intelligent mirror and method for determining hair style recommendation information Download PDF

Info

Publication number
CN111968511A
CN111968511A CN202010872029.4A CN202010872029A CN111968511A CN 111968511 A CN111968511 A CN 111968511A CN 202010872029 A CN202010872029 A CN 202010872029A CN 111968511 A CN111968511 A CN 111968511A
Authority
CN
China
Prior art keywords
display
state
display panel
substrate
face
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
CN202010872029.4A
Other languages
Chinese (zh)
Other versions
CN111968511B (en
Inventor
李文波
张丽杰
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.)
BOE Technology Group Co Ltd
Beijing BOE Technology Development Co Ltd
Original Assignee
BOE Technology Group Co Ltd
Beijing BOE Technology Development 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 BOE Technology Group Co Ltd, Beijing BOE Technology Development Co Ltd filed Critical BOE Technology Group Co Ltd
Priority to CN202010872029.4A priority Critical patent/CN111968511B/en
Publication of CN111968511A publication Critical patent/CN111968511A/en
Application granted granted Critical
Publication of CN111968511B publication Critical patent/CN111968511B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09F—DISPLAYING; ADVERTISING; SIGNS; LABELS OR NAME-PLATES; SEALS
    • G09F9/00—Indicating arrangements for variable information in which the information is built-up on a support by selection or combination of individual elements
    • G09F9/30—Indicating arrangements for variable information in which the information is built-up on a support by selection or combination of individual elements in which the desired character or characters are formed by combining individual elements
    • G—PHYSICS
    • G02—OPTICS
    • G02F—OPTICAL DEVICES OR ARRANGEMENTS FOR THE CONTROL OF LIGHT BY MODIFICATION OF THE OPTICAL PROPERTIES OF THE MEDIA OF THE ELEMENTS INVOLVED THEREIN; NON-LINEAR OPTICS; FREQUENCY-CHANGING OF LIGHT; OPTICAL LOGIC ELEMENTS; OPTICAL ANALOGUE/DIGITAL CONVERTERS
    • G02F1/00—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics
    • G02F1/01—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics for the control of the intensity, phase, polarisation or colour 
    • G—PHYSICS
    • G02—OPTICS
    • G02F—OPTICAL DEVICES OR ARRANGEMENTS FOR THE CONTROL OF LIGHT BY MODIFICATION OF THE OPTICAL PROPERTIES OF THE MEDIA OF THE ELEMENTS INVOLVED THEREIN; NON-LINEAR OPTICS; FREQUENCY-CHANGING OF LIGHT; OPTICAL LOGIC ELEMENTS; OPTICAL ANALOGUE/DIGITAL CONVERTERS
    • G02F1/00—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics
    • G02F1/01—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics for the control of the intensity, phase, polarisation or colour 
    • G02F1/13—Devices or arrangements for the control of the intensity, colour, phase, polarisation or direction of light arriving from an independent light source, e.g. switching, gating or modulating; Non-linear optics for the control of the intensity, phase, polarisation or colour  based on liquid crystals, e.g. single liquid crystal display cells
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
    • Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Nonlinear Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Optics & Photonics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Chemical & Material Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Crystallography & Structural Chemistry (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Devices For Indicating Variable Information By Combining Individual Elements (AREA)
  • Controls And Circuits For Display Device (AREA)

Abstract

The invention provides a display panel, a manufacturing method of the display panel, an intelligent mirror and a method for determining hair style recommendation information, and belongs to the technical field of display. The display area of the display panel provided by the invention comprises at least one two-state display area. The display panel comprises a panel and a dimming device, wherein the dimming device is arranged at the position of the display area corresponding to the two-state display area and is arranged at the display side of the panel; the dimming device can reflect external environment light in a first state and transmit the light emitted from the display area in a second state. According to the display panel provided by the invention, the dimming device is arranged in the two-state display area, so that the dimming device can reflect external environment light in the first state and transmit the light emitted from the display area in the second state, and the area of the display panel corresponding to the two-state display area can be used as a mirror surface in the first state and can normally display in the second state.

Description

Display panel, intelligent mirror and method for determining hair style recommendation information
Technical Field
The invention belongs to the technical field of display, and particularly relates to a display panel, an intelligent mirror and a method for determining hair style recommendation information.
Background
In some application scenarios of the display panel, for example, when the display panel has a camera function, when people take beauty makeup or hair dressing, people usually need to use the camera of the display panel to observe themselves, but the display picture and the mirror picture under real light are always different, so that good user experience cannot be provided.
Disclosure of Invention
The invention aims to at least solve one of the technical problems in the prior art, and provides a display panel which is provided with a dual-state display area, wherein the dual-state display area can reflect light to form a mirror surface and can also transmit the light to display, so that an intelligent display panel is provided, and the user experience is improved.
The technical scheme adopted for solving the technical problem is that the display panel comprises at least one two-state display area; the display panel comprises a panel and a dimming device, wherein the dimming device is arranged at the position of the display area corresponding to the two-state display area and is arranged at the display side of the panel; wherein the content of the first and second substances,
the dimming device can reflect external environment light in a first state and transmit the light emitted from the two-state display area in a second state.
According to the display panel provided by the invention, the dimming device is arranged in the two-state display area, so that the dimming device can reflect external environment light in the first state and transmit the light emitted from the display area in the second state, and the area of the display panel corresponding to the two-state display area can be used as a mirror surface in the first state and can normally display in the second state.
Preferably, the dimming device includes a transflective film, a liquid crystal cell, and a first polarizer sequentially disposed on a display side of the panel.
Preferably, the liquid crystal cell comprises a first substrate and a second substrate which are oppositely arranged, and liquid crystal between the first substrate and the second substrate;
the semi-transparent semi-reflective film is arranged on one side of the second substrate, which is far away from the liquid crystal, and the first polarizer is arranged on one side of the first substrate, which is far away from the liquid crystal;
the first substrate is provided with a first electrode, the second substrate is provided with a second electrode, and the first electrode and the second electrode are used for controlling the liquid crystal to deflect to an angle corresponding to the first state or the second state.
Preferably, if the display area includes at least two of the two-state display areas, the dimming devices corresponding to the two-state display areas are shared.
Preferably, the dimming device comprises a transflective film, a liquid crystal cell and a first polarizer which are sequentially arranged on the display side of the panel; the liquid crystal box comprises a first substrate and a second substrate which are oppositely arranged, and liquid crystal between the first substrate and the second substrate;
the liquid crystal display panel comprises a first substrate, a second substrate and a liquid crystal layer, wherein the first substrate is provided with a first electrode, the second substrate is provided with at least two groups of second electrodes, one group of the second electrodes corresponds to one binary display area, and an electric field is formed between the first electrode and the group of the second electrodes and is used for controlling the liquid crystal in the binary display area corresponding to the group of the second electrodes to deflect to an angle corresponding to a first state or a second state.
Preferably, the display area includes a first display area and a dual-state display area, which are arranged side by side, and in the first state, the first display area displays a picture, and the dual-state display area reflects external ambient light to form a mirror surface.
Preferably, the display panel further includes: and the image acquisition unit is arranged on the display side of the panel and used for acquiring the face information and recommending according to the face information.
Correspondingly, the embodiment of the invention also provides an intelligent mirror which comprises the display panel.
Correspondingly, the embodiment of the invention also provides a method for determining the recommended hair style information, which is applied to the display panel; the method comprises the following steps:
acquiring a face image;
determining a face region and a hair region in the face image;
determining face information corresponding to the face area and determining hair style information corresponding to the hair area;
and determining recommended hair style information according to a preset mapping relation between the face information and at least one hair style and/or a mapping relation between the hair style information and at least one hair style.
Preferably, the determining the face region and the hair region in the face image specifically includes:
dividing the face image into a face area, a hair area and an uncertain area through a pre-trained segmentation network;
and classifying each pixel information in the uncertain region through a pre-trained fine classification network, and determining the region to which each pixel information belongs.
Drawings
Fig. 1 is a schematic structural diagram of an embodiment of a display panel provided in this embodiment;
fig. 2 is a layer structure diagram (a first state) of a display panel corresponding to a dual-state display area provided in this embodiment;
fig. 3 is a layer structure diagram (second state) of the display panel corresponding to the dual-state display area provided in this embodiment;
fig. 4 is a schematic structural diagram of another embodiment of the display panel provided in this embodiment;
fig. 5 is a flowchart of a method for manufacturing a display panel according to the present embodiment;
fig. 6 is a schematic process diagram of a manufacturing method of a display panel according to the present embodiment;
fig. 7 is a decision flow chart of a method for determining recommended hair style information according to the present embodiment;
fig. 8 is a flowchart of a method for determining recommended hair style information according to the present embodiment;
fig. 9 is a second flowchart of a method for determining recommended hair style information according to the present embodiment;
fig. 10 is a flowchart illustrating region segmentation in the method for determining recommended hair style information according to this embodiment;
fig. 11 is a flowchart illustrating a fine classification in the method for determining recommended hair style information according to the present embodiment;
FIG. 12 is a flowchart illustrating a pre-training fine classification network according to the method for determining recommended hair style information provided in this embodiment;
fig. 13 is a third flowchart of a method for determining recommended hair style information according to the present embodiment;
fig. 14 is a flowchart of a decision tree of the method for determining recommended hair style information according to the present embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The shapes and sizes of the various elements in the drawings are not to scale and are merely intended to facilitate an understanding of the contents of the embodiments of the invention.
Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by one of ordinary skill in the art to which this disclosure belongs. The use of "first," "second," and similar terms in this disclosure is not intended to indicate any order, quantity, or importance, but rather is used to distinguish one element from another. Also, the use of the terms "a," "an," or "the" and similar referents do not denote a limitation of quantity, but rather denote the presence of at least one. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.
In a first aspect, as shown in fig. 1, the present embodiment provides a display panel, where the display panel includes a display area a and a non-display area located at a periphery of the display area a, and the display area a of the display panel includes at least one binary display area a 1.
Specifically, as shown in fig. 2 and 3, the display panel includes a panel 1 and a dimming device 2, the dimming device 2 is disposed at a position where a display area a of the display panel corresponds to a two-state display area a1, and the dimming device 2 is disposed at a display side of the panel 1. The dimming device 2 disposed in the binary display area a1 can make the portion of the display area a of the display panel corresponding to the binary display area a1 have two states, and in the first state (as shown in fig. 2), the ambient light irradiated to the display panel by the dimming device 2 is reflected, so that the binary display area a1 forms a mirror surface. In the second state (as shown in fig. 3), the dimming device 2 can transmit the outgoing light of the panel 1 under the dual-state display area a1, and can transmit the external ambient light incident from the outside, so that the dual-state display area a1 can normally display the picture. Because the display panel has the two-state display area a1, functionality of the display panel is increased, in some application scenarios, for example, when the display panel is applied to an intelligent hair-changing mirror, the face image of the user can be displayed in the non-two-state display area of the display area a of the display panel, and hair style recommendation is performed on the displayed face image, and the two-state display area a1 is in the first state, the two-state display area a1 can form a mirror surface, and the two-state display area a1 reflects the face of the user under natural light, so that the user can compare the face of the user in the mirror surface (the two-state display area a1) with the face images displayed in other display areas, thereby achieving more real and comprehensive intelligent hair-changing and further improving user experience. When full-screen display is required, the binary display area a1 can be switched to the second state, so that the display area a can completely display the picture.
It should be noted that the binary display area a1 may be disposed at any position of the display area a, and the display area a of the display panel may be disposed with any plurality of binary display areas a1, a part of the display area a of the display panel may be the binary display area a1, and the rest of the display area a may display normally, or other display areas may be added, such as a transparent display area, and the like, and all the display area a of the display panel may also be the binary display area a1, that is, the entire display area a is disposed with the dimming device 2. If the partial area of the display area a is the binary display area a1, the display area a of the display panel may only be provided with the entire panel 1, and the entire panel 1 is displayed in a partitioned manner, or a plurality of sub-panels may be arranged to be spliced into the panel 1, each sub-panel corresponds to the partial area in the display area a, for example, the binary display area a1, and each sub-panel is separately driven, which is specifically set according to the requirements of practical applications, and is not limited herein.
Alternatively, referring to fig. 2 and 3, the dimming device 2 is disposed at a position of the display area a of the display panel corresponding to the two-state display area a1, and the dimming device 2 may include various structures, for example, the dimming device 2 may include a transflective film 21, a liquid crystal cell 22 and a first polarizer 23 sequentially disposed at the display side of the panel 1. The liquid crystal box 22 is provided with liquid crystal 223, when external environment light enters the two-state display area A1 and is changed into linearly polarized light after passing through the first polarizer 23, the liquid crystal 223 in the liquid crystal box 22 modulates the polarization state of the linearly polarized light through different deflection angles, if the liquid crystal 223 deflects to an angle corresponding to the first state, the polarization direction of the light component after the linearly polarized light passing through the liquid crystal 223 can be parallel to the extension direction of the half-transparent half-reflective film 21, so that the light component is reflected out of the two-state display area A1, and the two-state display area A1 forms a mirror surface; when the liquid crystal 223 is deflected at an angle corresponding to the second state, the polarization direction of the light component after passing through the linearly polarized light of the liquid crystal 223 is not parallel to the extension direction of the transflective film 21, so that the light component is transmitted, and the two-state display area a1 can normally display a screen.
Optionally, referring to fig. 2 and fig. 3, a second polarizer 3 (i.e., an upper polarizer of the panel) may be further disposed on one side of the panel 1 close to the dimming device 2, the second polarizer 3 is used for assisting the panel 1 to perform display, and a third polarizer (i.e., a lower polarizer of the panel) may be further disposed on the opposite side of the panel 1 and the second polarizer 3.
Further, as shown in fig. 2 and 3, the liquid crystal cell 22 includes a first substrate 221 and a second substrate 222 disposed opposite to each other, and a liquid crystal 223 between the first substrate 221 and the second substrate 222, and the first substrate 221 and the second substrate 222 enclose the liquid crystal 223 therebetween. The transflective film 21 is disposed on the second substrate 222 side facing away from the liquid crystal 223, and the first polarizer 23 is disposed on the first substrate 221 side facing away from the liquid crystal 223. The first electrode 224 is disposed on the side of the first substrate 221 close to the liquid crystal 223, the second electrode 225 is disposed on the side of the second substrate 222 close to the liquid crystal 223, an electric field is formed between the first electrode 223 and the second electrode 224, the electric field can drive the liquid crystal 223 to deflect, so that the deflection angle of the liquid crystal 223 can be controlled by changing the direction of the electric field, the liquid crystal 223 is deflected to an angle corresponding to the first state in the first state, and the liquid crystal 223 is deflected to an angle corresponding to the second state in the second state.
The first electrode 224 and/or the second electrode 225 may be any electrode, for example, a planar electrode, a stripe electrode, a slit electrode, or the like, and is not limited thereto.
Alternatively, if the display area a of the display panel includes at least two binary display areas a1, the light modulation devices 2 corresponding to the respective binary display areas a1 can be shared, and then the liquid crystals 223 corresponding to different binary display areas a1 in the liquid crystal cell 22 can be driven individually.
Further, if the light modulation devices 2 of the two-state display regions a1 are shared, the first substrate 221 is provided with the first electrode 224, the second substrate 222 may be provided with at least two sets of second electrodes 225, that is, the second electrodes 225 on the second substrate 222 are partitioned according to the positions of the two-state display regions a1, one set of the second electrodes 225 corresponds to one two-state display region a1, so that an electric field is formed between the first electrode 224 on the first substrate 221 and the one set of the second electrodes 225 on the second substrate 222, and the formed electric field controls the liquid crystal 223 in the two-state display region a1 corresponding to the set of the second electrodes to deflect to an angle corresponding to the first state or the second state. The dimming device is shared by the two-state display areas A1, so that the number of lead wires can be reduced, and the structure is simplified.
Optionally, as shown in fig. 4, the display panel may further include an image obtaining unit 4, where the image obtaining unit 4 is disposed on the display side of the panel 1, and the image obtaining unit 4 is configured to obtain face information of the user and make a recommendation according to the face information of the user, where the face information may include a face shape, facial features, a head shape, a skin color, a hair quality, and the like of the user, for example, if the display panel is applied in an intelligent hair-changing mirror, the face information of the user may be obtained, and a hair style is recommended for the user according to the face shape, the head shape, and the hair quality of the user in the face information.
Alternatively, as shown in fig. 4, the display area a of the display panel provided in this embodiment includes a first display area a2 and a two-state display area a1, which are arranged side by side, in the first state, the first display area a2 displays a picture, the two-state display area a1 reflects ambient light to form a mirror surface, if the display panel is an intelligent hair-changing mirror and has an image obtaining unit 4, the image obtaining unit 4 obtains face information of a user, then inputs the face information into the display panel in real time, displays the face information of the user in the first display area a2 on the left side, analyzes the face information of the user by using an intelligent algorithm, recommends a hairstyle for the user, tries to wear a hairstyle in the first display area a2, and the two-state display area a1 on the right side reflects light to form a mirror surface, can present a real face of the user in natural light as a mirror, and the user can compare the face information of the user displayed in the first display area a2 and the two-state display area a1, a preferred hairstyle is determined. If the mirror surface is not needed and full-screen display is needed, the display panel is switched to the second state, and the transmission light rays are spliced with the first display area A1 to form a finished display area for displaying in the two-state display area A1. Of course, the binary display area a1 in the display panel has many different configurations, which may be specifically configured according to the needs, and is not limited herein.
In a second aspect, as shown in fig. 5, an embodiment of the present invention further provides a method for manufacturing a display panel, including the following steps:
s1, manufacturing the panel 1.
Specifically, the panel 1 may include an organic electroluminescent (OLED) panel, and may also include a Liquid Crystal Display (LCD) panel, and taking the panel 1 as an OLED panel as an example, the manufacturing of the panel 1 specifically includes manufacturing a substrate, manufacturing a driving device on the substrate, manufacturing a light emitting device on the driving device, and the like.
S2, the light control device 2 is fabricated on the display side of the panel 1 at a position where the display area a of the display panel corresponds to the binary display area a 1.
The manufacturing of the light modulation device 2 includes sequentially manufacturing a transflective film 21, a liquid crystal cell 22 and a first polarizer 23 on the panel 1.
Referring to fig. 6, making the liquid crystal cell 22 includes: as shown in fig. 6(a1), a first substrate 221 is produced; as shown in fig. 6(b1), the first electrode 224 is formed on the first substrate 221 by a sputtering process; as shown in fig. 6(a2), a second substrate 222 is fabricated; as shown in fig. 6(b2), the second electrode 225 is fabricated on the second substrate 222 by a sputtering process; if the display area a of the display panel only includes one binary display area a1, or the display area a of the display panel includes a plurality of binary display areas a1, but the plurality of binary display areas a1 do not share the dimming device 2, the next step is performed directly. If the display area a of the display panel includes a plurality of binary display areas a1 and the dimming devices 2 of the plurality of binary display areas a1 are shared, as shown in fig. 6(c2), taking the display area a including the first binary display area a11 and the second binary display area a12 as an example, after a layer of the second electrode 225 is manufactured, the second electrode 225 is divided into two groups by an exposure-etching-development process, and the two groups of the second electrode 225 respectively correspond to the first binary display area a11 and the second binary display area a 12. Then, as shown in fig. 6(d), the first substrate 221 and the second substrate 222 are aligned, and then cut and filled with liquid crystal, followed by encapsulation, thereby completing the liquid crystal cell 22.
In a third aspect, an embodiment of the present invention further provides an intelligent mirror, including the display panel, for example, the display panel shown in fig. 4.
The smart mirror may include a normal mirror surface, a display panel including a binary display area, a processor, a memory, and the like. The processor can be a Central Processing Unit (CPU) or the like, and the image acquisition Unit in the display panel can be used for acquiring the face feature parameters of the user; and the CPU determines whether the imaging of the user in the intelligent mirror needs to be processed or the user needs to be recommended according to the face characteristic parameters, and the like. The Memory may be a RAM (Random Access Memory), a Flash (Flash Memory), or the like, and may be configured to store received data, data required by a processing procedure, data generated in the processing procedure, or the like, such as a face feature parameter of a user.
The smart mirror may also include a transceiver, input components, audio output components, and the like. The transceiver may be used for data transmission with the mobile phone, for example, may obtain a setting parameter sent by the mobile phone to the smart mirror, and the transceiver may include a bluetooth component, a WiFi (Wireless-Fidelity) component, an antenna, a matching circuit, a modem, and the like. The input means may be a touch screen or the like. The audio output component may be a sound box or the like.
The intelligent mirror provided by the embodiment can comprise various types, such as a makeup mirror, a hair-changing mirror, a self-timer mirror and the like. Taking an intelligent mirror as an example of a hair-changing mirror, the intelligent mirror includes the above-mentioned display panel, and the display panel is provided with an image acquisition unit 4, as shown in fig. 7, the image acquisition unit captures an image of a user, performs face recognition, head recognition and hair quality recognition on the image of the user, selects an appropriate recommended hair style from a hair style library according to the results of the face recognition, the hair style recognition and the hair quality recognition, and then performs optimization processing on the recommendation results of the three kinds of recognition to decide a preset number of recommended hair styles. For example, the user is identified as a rectangular face, a flat head type and dry hair quality through the user image, the upper end hair style of the rectangular continuous hair style is preferably curly hair, and then 10 recommended hair styles with curly hair at the upper ends are screened from the hair style library; according to the fact that a user is flat, the fluffy hairstyle is preferably selected, and then 10 fluffy hairstyles are screened from a hairstyle library; and then, according to the fact that the user is dry hair, the curl of the curly hair is not easy to be too large, 10 hairstyles with large curly hair are screened out from a hairstyle library, the screening results of the three are combined, the overlapped hairstyle and the optimal hairstyle are selected out and output to the user as the final result, hairstyle recommendation is carried out, and the simulation hair changing display is carried out in the non-binary display area in the display panel display area A. When the recommended hairstyle is decided, the hairstyle can be recommended by combining with hairstyle preferences preset by the user, and a specific hairstyle recommending algorithm is not limited.
In a fourth aspect, as shown in fig. 8, the present embodiment further provides a method for determining recommended hair style information, which is applied to the display panel, and the method includes the following steps:
and S01, acquiring a face image.
Specifically, for example, the display panel described above includes an image acquisition unit capable of acquiring a face image of a user; or, the display panel has a storage unit, and may also load the user face image stored in the storage unit, which is not limited specifically.
And S02, determining a face area and a hair area in the face image.
Optionally, as shown in fig. 9, S02 may specifically include:
s021, dividing the face image into a face area, a hair area and an uncertain area through a pre-trained segmentation network.
Specifically, as shown in fig. 10, after the face image is input, the face image is subjected to area classification recognition through an area classification network, for example, the area classification network is referred to as Resnet-18, the face image is preprocessed to be divided into a plurality of image blocks (patches) meeting the standard pixels required by the Resnet-18 classification network, then the plurality of patches are input into the Resnet-18 classification network, the Resnet-18 divides the plurality of patches into a face area and a hair area according to the pre-trained classification rules, divides the patches that cannot be determined into an uncertain area, and then expands the grouped patches into heat hairs through hole convolution (scaled convolution) and upsampling processing.
Further, the Resnet-18 judges a mode of a region to which a patch of a face image belongs, specifically, judges a probability that the patch belongs to the face region and a probability that the patch belongs to the hair region, and if the probability that the patch belongs to the face region is greater than or equal to a first preset value, the patch is divided into the face region; if the probability that the patch belongs to the hair area is larger than or equal to a second preset value, the patch is divided into the hair area; if the probability that the patch belongs to the face area is smaller than a first preset value and the probability that the patch belongs to the hair area is smaller than a second preset value, the patch is classified into an uncertain area. The first preset value and the second preset value are both obtained through pre-training deep learning, and specific numerical values are not limited. The plurality of patches of the face image are subjected to probability scoring and then are divided into a face area, a hair area and an uncertain area, the hair thermodynamic diagram is drawn according to the probability of each patch, and the darker the color of the area on the hair thermodynamic diagram, the higher the probability that the patch corresponding to the area is the hair area or the face area is. And then merging (concat) the hair thermodynamic diagram and the originally input face image, inputting a pre-trained segmentation network (such as a Unet segmentation network), segmenting according to a pre-trained segmentation rule through the segmentation network, and outputting a region segmentation result of the face image, namely segmenting a hair region, a face region and a mask (mask) of an uncertain region. The mask of each region (hair region, face region or uncertain region) comprises a plurality of patches belonging to the region, each patch has probability information, and the probability information is the probability value for determining the region to which the patch belongs.
S022, classifying each pixel information in the uncertain region through a pre-trained fine classification network, and determining a region to which each pixel information belongs.
Specifically, as shown in fig. 11, the hair region, the face region, and the uncertain region in the region segmentation result output by the segmentation network in S021 are all part of the original face image, and therefore each region includes a plurality of pixels, the pixel information of each pixel in each region in the region segmentation result output by S021 is input to the fine classification network to perform pixel-level classification, the region to which the pixel belongs is accurately determined, and the final segmentation result is output and includes the hair region, the face region, and the non-hair non-face region.
It should be noted that, referring to fig. 12, in the process of pre-training the fine classification network, a plurality of face images may be used to perform region segmentation through the step S021, then feature extraction is performed on a plurality of region segmentation results, and after model learning is performed through a plurality of feature extraction results, the fine classification network is completed, so that the fine classification network can identify whether each pixel is a face, a hair, or neither a face nor a hair.
And S03, determining face information corresponding to the face area and determining hair style information corresponding to the hair area.
Specifically, a hair style classification network for performing hair style feature extraction by using pre-training is used to perform hair style identification on a hair region in a final segmentation result, and hair style information matched with the features of the hair region is identified, wherein the hair style information includes any one or more of long hair, short hair, curly hair, straight hair and the like. Similarly, the face classification network which is pre-trained to complete face feature extraction is utilized to perform face recognition on the face region in the final segmentation result, and face information matched with the features of the face region is recognized, wherein the face information comprises any one or more of a round face, a square face, an oval face, a long face and the like.
And S04, determining the recommended hair style information according to the mapping relation between the preset face information and at least one hair style and/or the mapping relation between the hair style information and at least one hair style.
Alternatively, a hair style data set is preset, and each hair style has a mapping relationship with at least one of the face information and/or the hair style information, for example, if the hair style 1 is suitable for a round face and a short hair, the hair style 1 has a mapping relationship with the round face and the short hair, if the face information of the face area has the round face in S03, the hair style 1 is selected as the recommended hair style, and if the hair style information of the hair area has the short hair, the hair style 1 is also selected as the recommended hair style. As shown in fig. 7, at least one hair style matching with the face information is selected through the face information, at least one hair style matching with the hair style information is selected through the hair style information, other recognition conditions may be added, for example, at least one hair style matching with the hair quality information is selected through the hair quality information, and finally, the final recommended hair style information is obtained through a preset algorithm.
Alternatively, the preset algorithm may include various manners, for example, a style that is overlapped among the styles screened by the plurality of conditions is used as the style in the recommended style information, or each style screened by the plurality of conditions is weighted according to popularity of different styles, and a style with a high weight is used as the recommended style information, which is not limited herein.
Optionally, referring to fig. 13, the final recommended hair style information may also be determined based on the decision tree in combination with the favorite hair style preset by the user (the hair style pointed by the thin solid line in the figure) and the hair style matched by the above algorithm (the hair style pointed by the thick solid line in the figure). Referring to fig. 14, taking the decision tree of fig. 14 as an example, it is determined through S03 that a face region in a face image input by a user is a round face or a sharp face, if the face region is a round face, it is determined according to a preferred hair style preset by the user that the user prefers straight hair or curly hair, after determining that the user prefers straight hair, it is determined according to face information that the user is suitable for short hair or long hair, and after determining that the user is suitable for short hair, a hair style having a mapping relationship with the round face is selected from a set of short hair and straight hair styles to determine as final recommended hair style information.
In a fifth aspect, an embodiment of the present invention further provides a display device, including the display panel.
The display device may be: any product or component with a display function, such as a mobile phone, a tablet computer, a television, a display, a notebook computer, a digital photo frame, a navigator and the like. Other essential components of the display device are understood by those skilled in the art, and are not described herein or should not be construed as limiting the invention.
It will be understood that the above embodiments are merely exemplary embodiments taken to illustrate the principles of the present invention, which is not limited thereto. It will be apparent to those skilled in the art that various modifications and improvements can be made without departing from the spirit and substance of the invention, and these modifications and improvements are also considered to be within the scope of the invention.

Claims (10)

1. A display panel is characterized in that a display area of the display panel comprises at least one two-state display area; the display panel comprises a panel and a dimming device, wherein the dimming device is arranged at the position of the display area corresponding to the two-state display area and is arranged at the display side of the panel; wherein the content of the first and second substances,
the dimming device can reflect external environment light in a first state and transmit the light emitted from the two-state display area in a second state.
2. The display panel according to claim 1, wherein the dimming device comprises a transflective film, a liquid crystal cell and a first polarizer sequentially disposed on the display side of the panel.
3. The display panel according to claim 2, wherein the liquid crystal cell comprises a first substrate and a second substrate disposed opposite to each other with liquid crystal therebetween;
the semi-transparent semi-reflective film is arranged on one side of the second substrate, which is far away from the liquid crystal, and the first polarizer is arranged on one side of the first substrate, which is far away from the liquid crystal;
the first substrate is provided with a first electrode, the second substrate is provided with a second electrode, and the first electrode and the second electrode are used for controlling the liquid crystal to deflect to an angle corresponding to the first state or the second state.
4. The display panel according to claim 1, wherein if the display area comprises at least two of the two-state display areas, the dimming device corresponding to each of the two-state display areas is shared.
5. The display panel according to claim 4, wherein the dimming device comprises a transflective film, a liquid crystal cell and a first polarizer disposed in this order on the display side of the panel; the liquid crystal box comprises a first substrate and a second substrate which are oppositely arranged, and liquid crystal between the first substrate and the second substrate;
the liquid crystal display panel comprises a first substrate, a second substrate and a liquid crystal layer, wherein the first substrate is provided with a first electrode, the second substrate is provided with at least two groups of second electrodes, one group of the second electrodes corresponds to one binary display area, and an electric field is formed between the first electrode and the group of the second electrodes and is used for controlling the liquid crystal in the binary display area corresponding to the group of the second electrodes to deflect to an angle corresponding to a first state or a second state.
6. The display panel according to claim 1, wherein the display region comprises a first display region and a dual-state display region arranged side by side, and in the first state, the first display region displays a picture, and the dual-state display region reflects ambient light to form a mirror surface.
7. The display panel according to claim 1, characterized in that the display panel further comprises: and the image acquisition unit is arranged on the display side of the panel and used for acquiring the face information and recommending according to the face information.
8. A smart mirror comprising the display panel of any one of claims 1 to 7.
9. A method of determining recommended hair style information, applied to the display panel of any one of claims 1-7; the method is characterized by comprising the following steps:
acquiring a face image;
determining a face region and a hair region in the face image;
determining face information corresponding to the face area and determining hair style information corresponding to the hair area;
and determining recommended hair style information according to a preset mapping relation between the face information and at least one hair style and/or a mapping relation between the hair style information and at least one hair style.
10. The method according to claim 9, wherein the determining the face region and the hair region in the face image specifically comprises:
dividing the face image into a face area, a hair area and an uncertain area through a pre-trained segmentation network;
and classifying each pixel information in the uncertain region through a pre-trained fine classification network, and determining the region to which each pixel information belongs.
CN202010872029.4A 2020-08-26 2020-08-26 Display panel, intelligent mirror and method for determining hair style recommendation information Active CN111968511B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010872029.4A CN111968511B (en) 2020-08-26 2020-08-26 Display panel, intelligent mirror and method for determining hair style recommendation information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010872029.4A CN111968511B (en) 2020-08-26 2020-08-26 Display panel, intelligent mirror and method for determining hair style recommendation information

Publications (2)

Publication Number Publication Date
CN111968511A true CN111968511A (en) 2020-11-20
CN111968511B CN111968511B (en) 2023-04-18

Family

ID=73391334

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010872029.4A Active CN111968511B (en) 2020-08-26 2020-08-26 Display panel, intelligent mirror and method for determining hair style recommendation information

Country Status (1)

Country Link
CN (1) CN111968511B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1670574A (en) * 2004-03-17 2005-09-21 统宝光电股份有限公司 Mirror surface display
CN104111559A (en) * 2014-07-01 2014-10-22 京东方科技集团股份有限公司 Mirror surface display device
CN107450766A (en) * 2016-05-30 2017-12-08 乐金显示有限公司 mirror display and mirror display panel
CN107808136A (en) * 2017-10-31 2018-03-16 广东欧珀移动通信有限公司 Image processing method, device, readable storage medium storing program for executing and computer equipment
CN109791437A (en) * 2016-09-29 2019-05-21 三星电子株式会社 Display device and its control method

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1670574A (en) * 2004-03-17 2005-09-21 统宝光电股份有限公司 Mirror surface display
CN104111559A (en) * 2014-07-01 2014-10-22 京东方科技集团股份有限公司 Mirror surface display device
CN107450766A (en) * 2016-05-30 2017-12-08 乐金显示有限公司 mirror display and mirror display panel
CN109791437A (en) * 2016-09-29 2019-05-21 三星电子株式会社 Display device and its control method
CN107808136A (en) * 2017-10-31 2018-03-16 广东欧珀移动通信有限公司 Image processing method, device, readable storage medium storing program for executing and computer equipment

Also Published As

Publication number Publication date
CN111968511B (en) 2023-04-18

Similar Documents

Publication Publication Date Title
US11875520B2 (en) Method and system for generating a fusion image
TWI754887B (en) Method, device and electronic equipment for living detection and storage medium thereof
US20220157014A1 (en) Method for rendering relighted 3d portrait of person and computing device for the same
WO2022057526A1 (en) Three-dimensional model reconstruction method and apparatus, and three-dimensional reconstruction model training method and apparatus
CN109359499A (en) A kind of method and apparatus for face classifier
EP3772038A1 (en) Augmented reality display method of simulated lip makeup
CN110163832A (en) Face fusion method, apparatus and terminal
KR20200107957A (en) Image processing method and device, electronic device and storage medium
CN109191569A (en) A kind of simulation cosmetic device, simulation cosmetic method and equipment
CN109741289A (en) Image fusion method and VR equipment
CN106942878A (en) Partial enlargement make up system, apparatus and method
CN108874145A (en) A kind of image processing method calculates equipment and storage medium
US20230178044A1 (en) Virtual reality display device and display method
CN108614369A (en) Display device
WO2022227547A1 (en) Method and apparatus for image processing, electronic device, and storage medium
CN117242482A (en) Digital imaging and learning system and method for analyzing pixel data of scalp region of user's scalp to generate one or more user-specific scalp classifications
CN111968511B (en) Display panel, intelligent mirror and method for determining hair style recommendation information
CN110115022A (en) Image processing system, optical sensor and learning device
CN109891459B (en) Image processing apparatus and image processing method
CN113361459A (en) Advertisement display method, device and equipment based on fixation point identification and storage medium
CN114187515A (en) Image segmentation method and image segmentation device
CN113822965A (en) Image rendering processing method, device and equipment and computer storage medium
WO2023272495A1 (en) Badging method and apparatus, badge detection model update method and system, and storage medium
CN110866867B (en) Terminal mirror image display method, terminal and computer readable storage medium
KR102518203B1 (en) Display method and device, and storage medium

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