CN108564540A - Remove image processing method, device and the terminal device that eyeglass is reflective in image - Google Patents
Remove image processing method, device and the terminal device that eyeglass is reflective in image Download PDFInfo
- Publication number
- CN108564540A CN108564540A CN201810179783.2A CN201810179783A CN108564540A CN 108564540 A CN108564540 A CN 108564540A CN 201810179783 A CN201810179783 A CN 201810179783A CN 108564540 A CN108564540 A CN 108564540A
- Authority
- CN
- China
- Prior art keywords
- image
- human eye
- eye area
- depth image
- retroreflective regions
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 238000012545 processing Methods 0.000 claims abstract description 48
- 238000003702 image correction Methods 0.000 claims abstract description 19
- 238000000034 method Methods 0.000 claims description 13
- 238000003384 imaging method Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 239000000284 extract Substances 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 6
- 239000011521 glass Substances 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 241001300078 Vitrea Species 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005452 bending Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
Classifications
-
- G06T5/77—
-
- G06T5/73—
-
- 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
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- 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
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- 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
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
Abstract
This application discloses eyeglass in a kind of removal image reflective image processing method, device and terminal devices, wherein the reflective image processing method of eyeglass includes in removal image：Generate coloured image and depth image；Based on face recognition algorithms, human face region is extracted from coloured image；The retroreflective regions in human face region are determined according to coloured image and depth image；And image correction processing is carried out to retroreflective regions.Eyeglass reflective image processing method, device and terminal device in the removal image of the embodiment of the present application, by generating coloured image and depth image, and it is based on face recognition algorithms, human face region is extracted from coloured image, and the retroreflective regions in human face region are determined according to coloured image and depth image, and image correction processing is carried out to retroreflective regions, it can accurately identify retroreflective regions, and remove reflective in retroreflective regions, raising image effect.
Description
Technical field
This application involves a kind of reflective image processing methods of eyeglass in technical field of information processing more particularly to removal image
Method, device and terminal device.
Background technology
With being constantly progressive for science and technology, the camera function of mobile phone is more powerful, and the pixel number of camera is also higher and higher, figure
As more and more clear.People can anywhere or anytime be taken pictures using mobile phone.But during portrait takes pictures imaging, glasses
It is reflective caused by eye loss in detail be always insoluble problem.Currently, removing reflective technology may include two class methods,
First, being pre-processed before taking pictures, such as install polarizing film additional or adjust the angle of light source, eyeglass, or even shooting is worn glasses respectively
The photo that do not wear glasses is synthesized；Second is that after imaging of taking pictures, it is reflective by later image processing removal, such as extraction figure
The blue channel of piece eye areas carries out difference processing with other channels, and it is reflective to eliminate blue.First kind method can allow and shoot
Journey complicates, and installation polarizing film can reduce image quality.Second class method is difficult to accurately obtain correct ocular, by
There is complexity in glasses flare, the size of hot spot, color, all it is difficult to predict post-processing efficiency is low, cost for distribution
It is high.
Apply for content
The application provides reflective image processing method, device and the terminal device of eyeglass in a kind of removal image, to solve
In the prior art, shoot portrait when eyeglass lead to the problem of it is reflective caused by eye loss in detail.
The embodiment of the present application provides the reflective image processing method of eyeglass in a kind of removal image, including：Generate cromogram
Picture and depth image；
Based on face recognition algorithms, human face region is extracted from the coloured image；
The retroreflective regions in the human face region are determined according to the coloured image and the depth image；And
Image correction processing is carried out to the retroreflective regions.
Optionally, coloured image and depth image are generated, including：
The coloured image captured by camera is captured by imaging sensor；
The depth image using structure photogenerated is obtained by structured light sensor.
Optionally, the retroreflective regions in the human face region are determined according to the coloured image and the depth image, wrapped
It includes：
The strength information of structure light when generating the depth image is obtained, and lens region is determined according to the strength information
Domain；
According to the depth image human eye area is obtained from the lens area；
The non-human eye area in the lens area is determined according to the lens area and the human eye area；
Highlight detection is carried out to the non-human eye area, determines retroreflective regions.
Optionally, the depth image using structure photogenerated is obtained by structured light sensor, including：
By structured light projector to face projective structure light, and is obtained by the structured light sensor and pass through the people
The structure light image of face；
Processing is decoded to the structure light image, to generate the depth image.
Optionally, processing is decoded to the structure light image, to generate the depth image, including：
Decode the corresponding phase information of deformation position pixel in the structure light image；
Convert the phase information to elevation information；
The depth image is generated according to the elevation information.
Optionally, image correction processing is carried out to the retroreflective regions, including：
Obtain the skin characteristic information of the human face region；
Image correction processing is carried out to the retroreflective regions according to the skin characteristic information of the human face region.
Optionally, highlight detection is carried out to the non-human eye area, determines retroreflective regions, including：
Obtain the luminance information of pixel in the non-human eye area；
When the luminance information of pixel in the non-human eye area is more than predetermined luminance value, determine in the non-human eye area
High luminance pixels；
The set that the high luminance pixels are formed is as the retroreflective regions.
Optionally, after obtaining human eye area in the lens area, increased using edge according to the depth image
Strong algorithms are sharpened processing to the human eye area.
Another embodiment of the application provides the reflective image processing apparatus of eyeglass in a kind of removal image, including：Generate mould
Block, for generating coloured image and depth image；
Extraction module extracts human face region for being based on face recognition algorithms from the coloured image；
Determining module, for determining the reflective areas in the human face region according to the coloured image and the depth image
Domain；And
Processing module carries out image correction processing for correcting to the retroreflective regions.
Optionally, the generation module, is used for：
The coloured image captured by camera is captured by imaging sensor；
The depth image using structure photogenerated is obtained by structured light sensor.
Optionally, the determining module, is used for：
The strength information of structure light when generating the depth image is obtained, and lens region is determined according to the strength information
Domain；
According to the depth image human eye area is obtained from the lens area；
The non-human eye area in the lens area is determined according to the lens area and the human eye area；
Highlight detection is carried out to the non-human eye area, determines retroreflective regions.
Optionally, the generation module, is used for：
By structured light projector to face projective structure light, and is obtained by the structured light sensor and pass through the people
The structure light image of face；
Processing is decoded to the structure light image, to generate the depth image.
Optionally, the generation module, is used for：
Decode the corresponding phase information of deformation position pixel in the structure light image；
Convert the phase information to elevation information；
The depth image is generated according to the elevation information.
Optionally, the processing module, is used for：
Obtain the skin characteristic information of the human face region；
Image correction processing is carried out to the retroreflective regions according to the skin characteristic information of the human face region.
Optionally, the determining module, is used for：
Obtain the luminance information of pixel in the non-human eye area；
When the luminance information of pixel in the non-human eye area is more than predetermined luminance value, determine in the non-human eye area
High luminance pixels；
The set that the high luminance pixels are formed is as the retroreflective regions.
Optionally, the determining module, is additionally operable to：
After obtaining human eye area in the lens area, edge enhancement algorithm pair is being utilized according to the depth image
The human eye area is sharpened processing.
The application a further embodiment provides a kind of non-transitorycomputer readable storage medium, is stored thereon with computer journey
Sequence realizes that eyeglass is anti-in the removal image as described in the application first aspect embodiment when the computer program is executed by processor
The image processing method of light.
The another embodiment of the application provides a kind of terminal device, including memory, processor and is stored in the memory
Computer program that is upper and can running on the processor, eyeglass in the removal image described in the application first aspect embodiment
Reflective image processing method.
Technical solution provided by the embodiments of the present application can include the following benefits：
By generating coloured image and depth image, and face recognition algorithms are based on, are extracted from the coloured image
Human face region, and the retroreflective regions in the human face region are determined according to the coloured image and the depth image, and it is right
The retroreflective regions carry out image correction processing, can accurately identify retroreflective regions, and remove it is reflective in retroreflective regions,
Improve image effect.
The additional aspect of the application and advantage will be set forth in part in the description, and will partly become from the following description
It obtains obviously, or recognized by the practice of the application.
Description of the drawings
The application is above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, wherein：
Fig. 1 is the flow chart of the reflective image processing method of eyeglass in the removal image according to the application one embodiment；
Fig. 2 is the flow chart that corresponding depth image is generated according to the decoding structure light image of the application one embodiment；
Fig. 3 is the schematic diagram of a scenario according to the structural light measurement of the application one embodiment；
Fig. 4 be determined according to coloured image and depth image according to the application one embodiment it is reflective in human face region
The flow chart in region；
Fig. 5 is the schematic diagram of a scenario according to the application one embodiment horizontal glass panel region really；
Fig. 6 is the schematic diagram of a scenario according to the application one embodiment horizontal glass panel region and retroreflective regions really；
Fig. 7 is anti-in human face region according to being determined according to coloured image and depth image for the application another embodiment
The flow chart in light region；
Fig. 8 is the structural frames of the reflective image processing apparatus of eyeglass in the removal image according to the application one embodiment
Figure；
Fig. 9 is the structural schematic diagram according to the terminal device of the application one embodiment.
Specific implementation mode
Embodiments herein is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the application, and should not be understood as the limitation to the application.
Below with reference to the accompanying drawings eyeglass is reflective in the application removal image image processing method, device and terminal is described to set
It is standby.
Fig. 1 is the flow chart of the reflective image processing method of eyeglass in the removal image according to the application one embodiment.
As shown in Figure 1, the reflective image processing method of eyeglass includes in the removal image：
S101 generates coloured image and depth image.
Currently, mobile terminal technology is increasingly powerful, people can anywhere or anytime be taken pictures using smart mobile phone.But
Portrait is taken pictures during imaging, glasses it is reflective caused by eye loss in detail be always insoluble problem.To solve
The above problem, the application propose the reflective image processing method of eyeglass in a kind of removal image.
In the present embodiment, the coloured image captured by camera can be captured by imaging sensor, and pass by structure light
Sensor obtains the depth image using structure photogenerated.
Specifically, can be by structured light projector to face projective structure light, and obtained and passed through by structured light sensor
Then the structure light image of face is decoded processing to structure light image, to generate corresponding depth image.Wherein, it solves
Code structure light image generates the process of corresponding depth image, as shown in Fig. 2, can further comprise：
S201 decodes the corresponding phase information of deformation position pixel in structure light image.
S202 converts phase information to elevation information.
S203 generates depth image according to elevation information.
That is, the relevant information of the threedimensional model of face can be carried out by the face projective structure light to user
Acquisition.Wherein, structure light is infrared light, can be laser stripe, Gray code, sine streak or, the figures such as non-homogeneous speckle
Case.Above-mentioned pattern can get the profile and depth information of face, such as the height of nose, shape of face after face.
Below its concrete principle is illustrated by taking a kind of widely used fringe projection technology as an example.It is thrown using area-structure light
When shadow, as shown in figure 3, generating sine streak by computer programming, extremely by projection by the sine streak
Measured object demodulates the curved stripes and obtains phase using the bending degree modulated by object of camera shooting striped, then by phase
It is converted into height.Certainly wherein crucial point be exactly system registration, including camera and projection device be registrated, no
Then it is more likely to produce error.Specifically, the phase of the phase of curved stripes and reference stripe can be subtracted each other to obtain phase difference, it should
Phase difference then characterizes elevation information of the measured object with respect to the plane of reference, then substitutes into phase and high-degree of conversion formula, to be waited for
Survey the threedimensional model of object.It should be understood that in practical applications, according to the difference of concrete application scene, the application is implemented
Structure light employed in example can also be any other pattern other than above-mentioned striped.
S102 is based on face recognition algorithms, human face region is extracted from coloured image.
Specifically, the position for obtaining face in coloured image, shared size etc. can be identified based on face recognition algorithms.
Human face region is extracted by above- mentioned information.
S103 determines the retroreflective regions in human face region according to coloured image and depth image.
Wherein, the region of reflection is generated when the retroreflective regions in human face region are irradiated by light for glasses.
In one embodiment of the application, as shown in figure 4, being determined in human face region according to coloured image and depth image
Retroreflective regions, can further comprise the steps：
S401, obtains the strength information of structure light when generating depth image, and determines lens area according to strength information.
S402 obtains human eye area according to depth image from lens area.
S403 determines the non-human eye area in lens area according to lens area and human eye area.
S404 carries out highlight detection to non-human eye area, determines retroreflective regions.
Specifically, the luminance information of pixel in non-human eye area can be obtained.When the luminance information of pixel in non-human eye area
When more than predetermined luminance value, so that it may to determine the high luminance pixels in non-human eye area.Then, set high luminance pixels formed
As retroreflective regions.
As shown in figure 5, shooting the coloured image of face using colour imagery shot, while utilizing infrared transmitter (structure light
Projection device) structure light is sent out, when infrared ray (structure light) a1 is irradiated to eyeglass, some light can be anti-by minute surface
It penetrates, some light transmitted through glasses eyeglass is simultaneously irradiated on human eye surface.And without eyeglass, direct irradiation is in face skin
On infrared ray (structure light) a2, due to not by reflection, the infrared ray a2 that infrared sensor (structure optical receiver) receives
Infrared signal it is stronger.The strength information difference of the two is bigger, therefore, as shown in fig. 6, can be connect according to infrared sensor
The strength information of the infrared ray received determines lens area A1.Structure light can also obtain the depth information of face, identification essence simultaneously
Degree reaches a millimeter rank, therefore, can be decoded to infrared light, obtains the depth image and its edge contour letter of human eye part
Breath, so that it may to determine human eye area A2.And in lens area A1, the remaining parts human eye area A2 are removed, are exactly inhuman Vitrea eye
Domain.The luminance information of pixel in the region is detected, luminance information is more than the part of predetermined luminance value, is exactly retroreflective regions.Wherein,
Predetermined luminance value can be arranged according to actual conditions, because it is reflective often more because of the light received, therefore predetermined luminance
Value has to be more than corresponding brightness value when normal exposure.
S104 carries out image correction processing to retroreflective regions.
In one embodiment of the application, the skin characteristic information of human face region can be obtained, then according to human face region
Skin characteristic information to retroreflective regions carry out image correction processing.Such as：The face skin around spectacle-frame can be utilized
The features such as color, brightness are supplemented to the details lost in retroreflective regions.
In addition, in order to further increase modified effect, as shown in fig. 7, can also include the steps of：
S405, according to depth image from lens area obtain human eye area after, using edge enhancement algorithm to people
Vitrea eye domain is sharpened processing.
Due to the angle problem taken pictures, some are reflective also to shelter from human eye area, lead to the loss of human eye details.For
This, processing is sharpened using edge enhancement algorithm to human eye area, and to strengthen the display effect of human eye area, reduction is anti-
The influence of light.
The auth method of the embodiment of the present application by generating coloured image and depth image, and is based on recognition of face
Algorithm extracts human face region from coloured image, and is determined according to coloured image and depth image anti-in human face region
Light region, and image correction processing is carried out to retroreflective regions, it can accurately identify retroreflective regions, and remove in retroreflective regions
It is reflective, improve image effect.
In order to realize above-described embodiment, the application also proposed the image procossing dress that eyeglass is reflective in a kind of removal image
It sets.
Fig. 8 is the structural frames of the reflective image processing apparatus of eyeglass in the removal image according to the application one embodiment
Figure.
As shown in figure 8, the device includes generation module 810, extraction module 820, determining module 830 and processing module 840.
Wherein, generation module 810, for generating coloured image and depth image.
Extraction module 820 extracts human face region for being based on face recognition algorithms from coloured image.
Determining module 830, for determining the retroreflective regions in human face region according to coloured image and depth image.
Processing module 840 carries out image correction processing for correcting to retroreflective regions.
It should be noted that the aforementioned explanation to removing the reflective image processing method of eyeglass in image, is also suitable
The unpub details in the image processing apparatus that eyeglass is reflective in image that removes of the embodiment of the present application, the embodiment of the present application,
Details are not described herein.
The reflective image processing apparatus of eyeglass in the removal image of the embodiment of the present application, by generating coloured image and depth
Image, and face recognition algorithms are based on, human face region is extracted from coloured image, and according to coloured image and depth image
It determines the retroreflective regions in human face region, and image correction processing is carried out to retroreflective regions, can accurately identify reflective areas
Domain, and remove reflective in retroreflective regions, raising image effect.
In order to realize that above-described embodiment, the application also propose a kind of non-transitorycomputer readable storage medium, deposit thereon
Computer program is contained, mirror in the removal image such as previous embodiment can be realized when the computer program is executed by processor
The reflective image processing method of piece.
In order to realize that above-described embodiment, the application also proposed a kind of terminal device.
As shown in figure 9, the terminal device 90 includes：Processor 91, memory 92 and image processing circuit 93.
Wherein, memory 92 is for storing executable program code；Processor 91 is stored by reading in memory 92
Executable program code and image processing circuit 93 handle image, to realize such as the removal image in previous embodiment
The reflective image processing method of middle eyeglass.
S101 ' generates coloured image and depth image.
S102 ' is based on face recognition algorithms, human face region is extracted from coloured image.
S103 ' determines the retroreflective regions in human face region according to coloured image and depth image.
S104 ' carries out image correction processing to retroreflective regions.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is contained at least one embodiment or example of the application.In the present specification, schematic expression of the above terms are not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
It can be combined in any suitable manner in one or more embodiments or example.In addition, without conflicting with each other, the skill of this field
Art personnel can tie the feature of different embodiments or examples described in this specification and different embodiments or examples
It closes and combines.
Although embodiments herein has been shown and described above, it is to be understood that above-described embodiment is example
Property, it should not be understood as the limitation to the application, those skilled in the art within the scope of application can be to above-mentioned
Embodiment is changed, changes, replacing and modification.
Claims (18)
1. the reflective image processing method of eyeglass in a kind of removal image, which is characterized in that including：
Generate coloured image and depth image；
Based on face recognition algorithms, human face region is extracted from the coloured image；
The retroreflective regions in the human face region are determined according to the coloured image and the depth image；And
Image correction processing is carried out to the retroreflective regions.
2. the method as described in claim 1, which is characterized in that coloured image and depth image are generated, including：
The coloured image captured by camera is captured by imaging sensor；
The depth image using structure photogenerated is obtained by structured light sensor.
3. the method as described in claim 1, which is characterized in that according to the coloured image and depth image determination
Retroreflective regions in human face region, including：
The strength information of structure light when generating the depth image is obtained, and lens area is determined according to the strength information；
According to the depth image human eye area is obtained from the lens area；
The non-human eye area in the lens area is determined according to the lens area and the human eye area；
Highlight detection is carried out to the non-human eye area, determines retroreflective regions.
4. method as claimed in claim 2, which is characterized in that obtain the depth using structure photogenerated by structured light sensor
Image is spent, including：
By structured light projector to face projective structure light, and obtained by the face by the structured light sensor
Structure light image；
Processing is decoded to the structure light image, to generate the depth image.
5. method as claimed in claim 4, which is characterized in that processing is decoded to the structure light image, to generate
Depth image is stated, including：
Decode the corresponding phase information of deformation position pixel in the structure light image；
Convert the phase information to elevation information；
The depth image is generated according to the elevation information.
6. the method as described in claim 1, which is characterized in that image correction processing is carried out to the retroreflective regions, including：
Obtain the skin characteristic information of the human face region；
Image correction processing is carried out to the retroreflective regions according to the skin characteristic information of the human face region.
7. method as claimed in claim 3, which is characterized in that carry out highlight detection to the non-human eye area, determine reflective
Region, including：
Obtain the luminance information of pixel in the non-human eye area；
When the luminance information of pixel in the non-human eye area is more than predetermined luminance value, the height in the non-human eye area is determined
Bright pixel；
The set that the high luminance pixels are formed is as the retroreflective regions.
8. method as claimed in claim 3, which is characterized in that further include：
According to the depth image from the lens area obtain human eye area after, using edge enhancement algorithm to described
Human eye area is sharpened processing.
9. the reflective image processing apparatus of eyeglass in a kind of removal image, which is characterized in that including：
Generation module, for generating coloured image and depth image；
Extraction module extracts human face region for being based on face recognition algorithms from the coloured image；
Determining module, for determining the retroreflective regions in the human face region according to the coloured image and the depth image；
And
Processing module carries out image correction processing for correcting to the retroreflective regions.
10. device as claimed in claim 9, which is characterized in that the generation module is used for：
The coloured image captured by camera is captured by imaging sensor；
The depth image using structure photogenerated is obtained by structured light sensor.
11. device as claimed in claim 9, which is characterized in that the determining module is used for：
The strength information of structure light when generating the depth image is obtained, and lens area is determined according to the strength information；
According to the depth image human eye area is obtained from the lens area；
The non-human eye area in the lens area is determined according to the lens area and the human eye area；
Highlight detection is carried out to the non-human eye area, determines retroreflective regions.
12. device as claimed in claim 10, which is characterized in that the generation module is used for：
By structured light projector to face projective structure light, and obtained by the face by the structured light sensor
Structure light image；
Processing is decoded to the structure light image, to generate the depth image.
13. device as claimed in claim 12, which is characterized in that the generation module is used for：
Decode the corresponding phase information of deformation position pixel in the structure light image；
Convert the phase information to elevation information；
The depth image is generated according to the elevation information.
14. device as claimed in claim 9, which is characterized in that the processing module is used for：
Obtain the skin characteristic information of the human face region；
Image correction processing is carried out to the retroreflective regions according to the skin characteristic information of the human face region.
15. device as claimed in claim 11, which is characterized in that the determining module is used for：
Obtain the luminance information of pixel in the non-human eye area；
When the luminance information of pixel in the non-human eye area is more than predetermined luminance value, the height in the non-human eye area is determined
Bright pixel；
The set that the high luminance pixels are formed is as the retroreflective regions.
16. device as claimed in claim 11, which is characterized in that the determining module is additionally operable to：
According to the depth image from the lens area obtain human eye area after, using edge enhancement algorithm to described
Human eye area is sharpened processing.
17. a kind of non-transitorycomputer readable storage medium, is stored thereon with computer program, which is characterized in that the program
As reflective image processing method such as eyeglass in claim 1-8 any one of them removal image is realized when being executed by processor.
18. a kind of terminal device, which is characterized in that including memory and processor, storing computer in the memory can
Reading instruction, when described instruction is executed by the processor so that the processor is executed such as any one of claim 1 to 8 institute
The reflective image processing method of eyeglass in the removal image stated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810179783.2A CN108564540B (en) | 2018-03-05 | 2018-03-05 | Image processing method and device for removing lens reflection in image and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810179783.2A CN108564540B (en) | 2018-03-05 | 2018-03-05 | Image processing method and device for removing lens reflection in image and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108564540A true CN108564540A (en) | 2018-09-21 |
| CN108564540B CN108564540B (en) | 2020-07-17 |
Family
ID=63532316
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810179783.2A Expired - Fee Related CN108564540B (en) | 2018-03-05 | 2018-03-05 | Image processing method and device for removing lens reflection in image and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108564540B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111464745A (en) * | 2020-04-14 | 2020-07-28 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
| CN111582005A (en) * | 2019-02-18 | 2020-08-25 | Oppo广东移动通信有限公司 | Image processing method, image processing device, computer readable medium and electronic equipment |
| CN112001296A (en) * | 2020-08-20 | 2020-11-27 | 广东电网有限责任公司清远供电局 | Three-dimensional safety monitoring method and device for transformer substation, server and storage medium |
| WO2021115550A1 (en) * | 2019-12-09 | 2021-06-17 | Huawei Technologies Co., Ltd. | Separation of first and second image data |
| CN112995529A (en) * | 2019-12-17 | 2021-06-18 | 华为技术有限公司 | Imaging method and device based on optical flow prediction |
| CN113055579A (en) * | 2019-12-26 | 2021-06-29 | 深圳市万普拉斯科技有限公司 | Image processing method and device, electronic equipment and readable storage medium |
| CN113486714A (en) * | 2021-06-03 | 2021-10-08 | 荣耀终端有限公司 | Image processing method and electronic equipment |
| CN113542580A (en) * | 2020-04-22 | 2021-10-22 | 华为技术有限公司 | Method and device for removing light spots of glasses and electronic equipment |
| WO2023160075A1 (en) * | 2022-02-28 | 2023-08-31 | 上海商汤智能科技有限公司 | Image inpainting method and apparatus, and device and medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020579A (en) * | 2011-09-22 | 2013-04-03 | 上海银晨智能识别科技有限公司 | Face recognition method and system, and removing method and device for glasses frame in face image |
| CN103093210A (en) * | 2013-01-24 | 2013-05-08 | 北京天诚盛业科技有限公司 | Method and device for glasses identification in face identification |
| CN105117695A (en) * | 2015-08-18 | 2015-12-02 | 北京旷视科技有限公司 | Living body detecting device and method |
| CN105959543A (en) * | 2016-05-19 | 2016-09-21 | 努比亚技术有限公司 | Shooting device and method of removing reflection |
| EP3073313A1 (en) * | 2015-03-23 | 2016-09-28 | Seiko Epson Corporation | Light guide device, head-mounted display, and method of manufacturing light guide device |
| CN106326828A (en) * | 2015-11-08 | 2017-01-11 | 北京巴塔科技有限公司 | Eye positioning method applied to face recognition |
| CN106503644A (en) * | 2016-10-19 | 2017-03-15 | 西安理工大学 | Glasses attribute detection method based on edge projection and color characteristic |
| EP3217210A1 (en) * | 2016-03-11 | 2017-09-13 | Valeo Vision | Image projector comprising a screen and a light source with electroluminescent rods |
| CN107301392A (en) * | 2017-06-20 | 2017-10-27 | 华天科技（昆山）电子有限公司 | Wafer level image harvester |
| CN107493411A (en) * | 2017-08-09 | 2017-12-19 | 广东欧珀移动通信有限公司 | Image processing system and method |
-
2018
- 2018-03-05 CN CN201810179783.2A patent/CN108564540B/en not_active Expired - Fee Related
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020579A (en) * | 2011-09-22 | 2013-04-03 | 上海银晨智能识别科技有限公司 | Face recognition method and system, and removing method and device for glasses frame in face image |
| CN103093210A (en) * | 2013-01-24 | 2013-05-08 | 北京天诚盛业科技有限公司 | Method and device for glasses identification in face identification |
| EP3073313A1 (en) * | 2015-03-23 | 2016-09-28 | Seiko Epson Corporation | Light guide device, head-mounted display, and method of manufacturing light guide device |
| CN105117695A (en) * | 2015-08-18 | 2015-12-02 | 北京旷视科技有限公司 | Living body detecting device and method |
| CN106326828A (en) * | 2015-11-08 | 2017-01-11 | 北京巴塔科技有限公司 | Eye positioning method applied to face recognition |
| EP3217210A1 (en) * | 2016-03-11 | 2017-09-13 | Valeo Vision | Image projector comprising a screen and a light source with electroluminescent rods |
| CN105959543A (en) * | 2016-05-19 | 2016-09-21 | 努比亚技术有限公司 | Shooting device and method of removing reflection |
| CN106503644A (en) * | 2016-10-19 | 2017-03-15 | 西安理工大学 | Glasses attribute detection method based on edge projection and color characteristic |
| CN107301392A (en) * | 2017-06-20 | 2017-10-27 | 华天科技（昆山）电子有限公司 | Wafer level image harvester |
| CN107493411A (en) * | 2017-08-09 | 2017-12-19 | 广东欧珀移动通信有限公司 | Image processing system and method |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111582005A (en) * | 2019-02-18 | 2020-08-25 | Oppo广东移动通信有限公司 | Image processing method, image processing device, computer readable medium and electronic equipment |
| CN111582005B (en) * | 2019-02-18 | 2023-08-15 | Oppo广东移动通信有限公司 | Image processing method, device, computer readable medium and electronic equipment |
| WO2021115550A1 (en) * | 2019-12-09 | 2021-06-17 | Huawei Technologies Co., Ltd. | Separation of first and second image data |
| CN112995529B (en) * | 2019-12-17 | 2022-07-26 | 华为技术有限公司 | Imaging method and device based on optical flow prediction |
| CN112995529A (en) * | 2019-12-17 | 2021-06-18 | 华为技术有限公司 | Imaging method and device based on optical flow prediction |
| CN113055579A (en) * | 2019-12-26 | 2021-06-29 | 深圳市万普拉斯科技有限公司 | Image processing method and device, electronic equipment and readable storage medium |
| WO2021129806A1 (en) * | 2019-12-26 | 2021-07-01 | 深圳市万普拉斯科技有限公司 | Image processing method, apparatus, electronic device, and readable storage medium |
| CN113055579B (en) * | 2019-12-26 | 2022-02-01 | 深圳市万普拉斯科技有限公司 | Image processing method and device, electronic equipment and readable storage medium |
| CN111464745B (en) * | 2020-04-14 | 2022-08-19 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
| CN111464745A (en) * | 2020-04-14 | 2020-07-28 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
| CN113542580A (en) * | 2020-04-22 | 2021-10-22 | 华为技术有限公司 | Method and device for removing light spots of glasses and electronic equipment |
| CN113542580B (en) * | 2020-04-22 | 2022-10-28 | 华为技术有限公司 | Method and device for removing light spots of glasses and electronic equipment |
| CN112001296A (en) * | 2020-08-20 | 2020-11-27 | 广东电网有限责任公司清远供电局 | Three-dimensional safety monitoring method and device for transformer substation, server and storage medium |
| CN112001296B (en) * | 2020-08-20 | 2024-03-29 | 广东电网有限责任公司清远供电局 | Three-dimensional safety monitoring method and device for transformer substation, server and storage medium |
| CN113486714A (en) * | 2021-06-03 | 2021-10-08 | 荣耀终端有限公司 | Image processing method and electronic equipment |
| WO2023160075A1 (en) * | 2022-02-28 | 2023-08-31 | 上海商汤智能科技有限公司 | Image inpainting method and apparatus, and device and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108564540B (en) | 2020-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564540A (en) | Remove image processing method, device and the terminal device that eyeglass is reflective in image | |
| US10997696B2 (en) | Image processing method, apparatus and device | |
| US11145038B2 (en) | Image processing method and device for adjusting saturation based on depth of field information | |
| CN107563304B (en) | Terminal equipment unlocking method and device and terminal equipment | |
| CN107509031B (en) | Image processing method, image processing device, mobile terminal and computer readable storage medium | |
| KR20200044093A (en) | Image processing methods and devices, electronic devices and computer-readable storage media | |
| CN107564050B (en) | Control method and device based on structured light and terminal equipment | |
| WO2019109805A1 (en) | Method and device for processing image | |
| CN107705278B (en) | Dynamic effect adding method and terminal equipment | |
| CN107392874B (en) | Beauty treatment method and device and mobile equipment | |
| CN107483428A (en) | Auth method, device and terminal device | |
| JP2020526735A (en) | Pupil distance measurement method, wearable eye device and storage medium | |
| CN114697623B (en) | Projection plane selection and projection image correction method, device, projector and medium | |
| CN106296624B (en) | Image fusion method and device | |
| CN109859104B (en) | Method for generating picture by video, computer readable medium and conversion system | |
| JP2013123123A (en) | Stereo image generation device, stereo image generation method and computer program for stereo image generation | |
| CN107613239B (en) | Video communication background display method and device | |
| US11218650B2 (en) | Image processing method, electronic device, and computer-readable storage medium | |
| WO2013024794A1 (en) | Image processing apparatus, projector and image processing method | |
| CN107592491B (en) | Video communication background display method and device | |
| JP2013126135A (en) | Stereo image generation device, stereo image generation method and computer program for stereo image generation | |
| CN107734266B (en) | Image processing method and apparatus, electronic apparatus, and computer-readable storage medium | |
| CN107370952B (en) | Image shooting method and device | |
| CN112770100B (en) | Image acquisition method, photographic device and computer readable storage medium | |
| CN108282650B (en) | Naked eye three-dimensional display method, device and system 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 | ||
| CB02 | Change of applicant information |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Applicant before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200717 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |