CN109543523A - Image processing method, device, system and storage medium - Google Patents
Image processing method, device, system and storage medium Download PDFInfo
- Publication number
- CN109543523A CN109543523A CN201811215311.4A CN201811215311A CN109543523A CN 109543523 A CN109543523 A CN 109543523A CN 201811215311 A CN201811215311 A CN 201811215311A CN 109543523 A CN109543523 A CN 109543523A
- Authority
- CN
- China
- Prior art keywords
- image
- human face
- face region
- processed
- brightness
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/141—Control of illumination
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of image processing method, device, system and storage mediums, this method comprises: obtaining image to be processed;Face datection is carried out to the image to be processed, with determination human face region therein;Increase the light metering weight of the human face region, and adjust the brightness of the image to be processed according to the light metering weight, to obtain treated image.Image processing method, device, system and storage medium according to an embodiment of the present invention solve the problems, such as that human face region picture is excessively dark or overexposure, the effect promoting identified to night vision scene human face are obvious according to the human face region dynamic regulation light metering weight detected.
Description
Technical field
The present invention relates to technical field of face recognition, relates more specifically to a kind of image processing method, device, system and deposit
Storage media.
Background technique
Recognition of face is a kind of biological identification technology for carrying out identification based on facial feature information of people, uses
Video camera or camera acquire image or video flowing containing face, and automatic detection and tracking face in the picture, and then right
The face detected carries out face recognition.This technology is because that it has the characteristics that non-contact, non-imposed and concurrency is wide
It is general to be applied to the multiple fields such as face verification, safety, monitoring and human-computer interaction.
With the extensive use of face recognition technology, has Face datection/identification function monitoring camera also therefore meet the tendency of
And it gives birth to.Under conditions of light is uniform, bright, traditional monitoring camera is preferable to the recognition effect of face;However, in night ring
In the biggish scene of the light and shades contrast such as border, face region was easy to produce dark or overexposure phenomenon, to seriously affect prison
Control the recognition of face effect of camera.
Summary of the invention
The invention proposes a kind of schemes about image procossing, survey light according to the human face region dynamic regulation detected
Weight solves the problems, such as that human face region picture is excessively dark or overexposure, the effect promoting identified to night vision scene human face are obvious.Under
Face brief description is proposed by the present invention about face recognition scheme, and more details will be in subsequent combination attached drawing in specific embodiment
In described.
According to an aspect of the present invention, a kind of image processing method is provided, which comprises obtain image to be processed;
Face datection is carried out to the image to be processed, with determination human face region therein;Increase the light metering weight of the human face region,
And the brightness of the image to be processed is adjusted according to the light metering weight, to obtain treated image.
In one embodiment, the method also includes: treated that image carries out recognition of face based on described.
In one embodiment, the method carries out survey light using matrix Exposure Metering, and the matrix Exposure Metering includes:
The image to be processed is divided into several areas Ce Guang and independently surveys light, and distributes respective light metering weight for each area Ce Guang.
In one embodiment, the light metering weight for increasing the human face region includes: the survey for making the human face region
Light weight is higher than the light metering weight in other areas Ce Guang.
In one embodiment, the brightness for adjusting the image to be processed according to the light metering weight includes: to work as institute
State human face region brightness it is relatively low when, increase exposure parameter, to improve the brightness of the human face region;When the human face region
Brightness it is higher when, reduce exposure parameter, to reduce the brightness of the human face region.
In one embodiment, described to be processed to increase or decrease by adjusting image gain and/or infrared lamp brightness
The brightness of image.
In one embodiment, the human face region includes face region and its neighboring area.
In one embodiment, the method also includes: determine light emitting source position in the image to be processed;It reduces
The light metering weight of the light emitting source position.
According to a further aspect of the invention, a kind of image processing apparatus is provided, described device includes: acquisition module, is used for
Obtain image to be processed;Face detection module, it is described to be processed with determination for carrying out Face datection to the image to be processed
Human face region in image;And adjustment module, it is weighed for increasing the light metering weight of the human face region, and according to the survey light
The brightness of image to be processed described in recanalization, with the image that obtains that treated.
In one embodiment, described device further include: face recognition module, for being carried out to treated the image
Recognition of face.
Another aspect according to the present invention provides a kind of image processing system, and the system comprises storage devices and processing
Device is stored with the computer program run by the processor on the storage device, and the computer program is by the place
Image processing method described in any of the above embodiments is executed when reason device operation.
According to a further aspect of the present invention, a kind of storage medium is provided, is stored with computer program on the storage medium,
The computer program executes image processing method described in any of the above embodiments at runtime.
Image processing method, device, system and storage medium according to an embodiment of the present invention are according to the face area detected
Domain dynamic regulation light metering weight solves the problems, such as that human face region picture is excessively dark or overexposure, to the identification of night vision scene human face
Effect promoting is obvious.
Detailed description of the invention
The embodiment of the present invention is described in more detail in conjunction with the accompanying drawings, the above and other purposes of the present invention,
Feature and advantage will be apparent.Attached drawing is used to provide to further understand the embodiment of the present invention, and constitutes explanation
A part of book, is used to explain the present invention together with the embodiment of the present invention, is not construed as limiting the invention.In the accompanying drawings,
Identical reference label typically represents same parts or step.
Fig. 1 shows the schematic flow chart of image processing method according to an embodiment of the present invention;
Fig. 2 shows the schematic block diagrams of image processing apparatus according to an embodiment of the present invention;And
Fig. 3 shows the schematic block diagram of image processing system according to an embodiment of the present invention.
Specific embodiment
In order to enable the object, technical solutions and advantages of the present invention become apparent, root is described in detail below with reference to accompanying drawings
According to example embodiments of the present invention.Obviously, described embodiment is only a part of the embodiments of the present invention, rather than this hair
Bright whole embodiments, it should be appreciated that the present invention is not limited by example embodiment described herein.Based on described in the present invention
The embodiment of the present invention, those skilled in the art's obtained all other embodiment in the case where not making the creative labor
It should all fall under the scope of the present invention.
Firstly, describing image processing method 100 according to an embodiment of the present invention referring to Fig.1.As shown in Figure 1, at image
Reason method 100 may include steps of:
In step S110, image to be processed is obtained.
Wherein, the image to be processed is the image for needing to carry out it recognition of face.In one embodiment, it is described to
Handling image is the image under night vision scene.In one example, image to be processed can be the image acquired in real time.Another
In a example, image to be processed can be the image from any source.
The image to be processed is collected by image collecting device.Illustratively, image collecting device can be
Imaging sensor;Illustratively, image collector is set to security protection camera.
In step S120, Face datection is carried out to the image to be processed, with determination human face region therein.
It illustratively, can be by running human-face detector, to detect the human face region in facial image.For example,
Human-face detector can be preparatory trained convolutional neural networks (Convolutional Neural Network, CNN) people
Face detector.For example, the Face datections such as Ha Er (Haar) algorithm, Adaboost algorithm, convolutional neural networks can be advanced with
Human-face detector is trained on the basis of a large amount of pictures with recognizer.Or the opencv Face datection using standard
Model locating human face region in the image to be processed.
In one embodiment, the human face region includes face region and its neighboring area.
In step S130, increase the light metering weight of the human face region, and described wait locate according to light metering weight adjustment
The brightness of image is managed, to obtain treated image.
In this step, due to increasing the light metering weight of the human face region, when calculating exposure parameter, resulting exposure
Optical parameter preferentially guarantees the brightness of human face region, so that the brightness of human face region is met the requirement of recognition of face, avoids human face region
It is too dark or too bright.
In one embodiment, this method carries out survey light using matrix Exposure Metering.Specifically, image to be processed is being obtained
Afterwards, the image to be processed is divided into several areas Ce Guang, and distributes respective light metering weight, each area Ce Guang for each area Ce Guang
After independent survey light, then integration weighted calculation goes out whole exposure parameter.After identifying human face region, it is determined that face
Coordinate of the region in the entire picture of image to be processed, and increase the light metering weight of the human face region, make the survey of human face region
Light weight is higher than the light metering weight in other areas Ce Guang.
Then, according to the light metering weight in each area Ce Guang and the survey resulting brightness of image of light, the exposure parameter of image is adjusted.
Illustratively, required exposure parameter, and root can be calculated according to the light metering weight and brightness of image in each area Ce Guang
Current exposure parameter is adjusted according to required exposure parameter.Since the weight of human face region is higher than other areas Ce Guang, because
This calculates the exposure demand that resulting exposure parameter preferentially meets human face region.
After exposure parameter is adjusted, image is shot with the exposure parameter through adjusting, so that in captured image
The exposure status of human face region can satisfy the requirement of subsequent recognition of face.Based on this, it is possible to prevente effectively from because with full figure
On the basis of calculate exposure parameter the phenomenon that influence face normal exposure, it is larger and cause to solve light and shade gap under night vision scene
Human face region exposure effect larger problem affected by environment, to improve the efficiency of recognition of face and improve recognition of face
Accuracy.
It is understood that this method preferentially meets the brightness demand of human face region, i.e., other regions may be excessively dark at this time
Or it is excessively bright, but this has no effect on subsequent recognition of face.For example, in backlight scene, since scene parts zonal ray is too strong,
To make entire scene not overexposure, human face region may be imaged it is black, so that effective recognition of face can not be carried out to human face region.
Therefore, after increasing the light metering weight of human face region, when human face region brightness is relatively low, since it is weighed in overall picture
Again bigger than other regions, image collecting device can preferentially guarantee the brightness of human face region, by increasing exposure parameter so that people
Face regional exposure is to the value needed or ideal value, to meet the needs of recognition of face.At this point, the region other than human face region can
Energy overexposure, but since recognition of face is based only on the image of human face region part, may not necessarily consider the non-of other overexposures
Region Of Interest.Similarly, when human face region brightness is higher, due to increasing the light metering weight of human face region, exposure parameter at this time
The overexposure to reduce or avoid face split screen can be reduced.That is, human face region is exposure feelings in image to be processed
Condition need to meet the region of predetermined demand, and the region except region corresponding with preferred coordinates region can be unsatisfactory for for exposure status
The region of pre-provisioning request.
In one embodiment, the human face region is dynamically adjusted by adjusting image gain and/or infrared lamp brightness
Brightness.Specifically, when the brightness of the human face region is relatively low, image gain and/or infrared lamp brightness is turned up, to improve
State the brightness of human face region;When the brightness of the human face region is relatively low, gain and/or infrared lamp brightness are turned down, to reduce
State the brightness of human face region.Illustratively, the infrared lamp is the near-infrared light compensating lamp of 850 nano wave lengths.In one embodiment
In, it is possible to use the light compensating lamp of more than one wavelength, such as the near infrared light light filling of 850 nano wave lengths had not only been used, but also use 940
The near infrared light light filling of nano wave length.
In another embodiment, the method also includes: determine light emitting source position in the image to be processed;And
Reduce the light metering weight of the light emitting source position.By reducing the light metering weight of light emitting source position, hair can be reduced
Influence of the excessive brightness of light source to overall exposing parameter, to avoid the presence due to light emitting source and make overall exposing parameter mistake
It is low, cause human face region excessively dark.
Illustratively, mobile phone terminal configuration interface can be provided a user, is dropped by the position of user configuration light emitting source, and accordingly
The light metering weight of low light emitting source region.Illustratively, the light emitting source includes in image collecting device installation site picture
Street lamp, garden lamp etc..
It in one embodiment, further include that treated that image carries out people to described after obtaining treated image
Face identification.
In this step, recognition of face can be carried out by trained deep learning neural network.Neural network is first
Feature vector is extracted to facial image to be identified.Such as LBP (local binary patterns), HoG (direction gradient histogram can be used
Figure), the various face feature extraction methods appropriate such as PCA (Principal Component Analysis) or neural network extract people to be identified
Face characteristic in face image simultaneously generates face feature vector, to be used for recognition of face.Neural network then and calculates resulting
Similarity in facial image to be identified and bottom library between the feature vector of facial image, if similarity is greater than similarity threshold
Value, then it is assumed that belong to the same person, otherwise then think to be not belonging to the same person.The feature vector of bottom library face can be deposits in advance
Storage.For example, when constructing bottom library, the feature of storage bottom library face in storage medium (storage device 104 as shown in Figure 1)
Vector.
Based on the human face region determined by step S120, and in the step S130 light metering weight adjusting carried out and accordingly
The exposure status of the brightness regulation of progress, the human face region in the image that can make that treated meets the needs of recognition of face.
Based on above description, image processing method according to an embodiment of the present invention solves human face region picture only
Exposure/under-exposure problem is obvious to the effect promoting of night vision scene human face identification.
Image processing method according to an embodiment of the present invention is described above exemplarily.Illustratively, according to the present invention
The image processing method of embodiment can with memory and processor unit or system in realize.
In addition, image processing method according to an embodiment of the present invention be deployed to can be convenient smart phone, tablet computer,
In the mobile devices such as personal computer.Alternatively, image processing method according to an embodiment of the present invention can also be deployed in service
Device end (or cloud).Alternatively, image processing method according to an embodiment of the present invention can also be deployed in server end with being distributed
At (or cloud) and personal terminal.
The image processing apparatus of another aspect of the present invention offer is described below with reference to Fig. 2.Fig. 2 shows real according to the present invention
Apply the schematic block diagram of the image processing apparatus 200 of example.
As shown in Fig. 2, image processing apparatus 200 according to an embodiment of the present invention includes obtaining module 210, Face datection mould
Block 220 and adjustment module 230.The modules can be executed respectively above in conjunction with each of Fig. 1 image processing method described
A step/function.Only the major function of each module of image processing apparatus 200 is described below, and more than omitting
The detail content described.
Module 210 is obtained for obtaining image to be processed.Face detection module 220 is used to carry out the image to be processed
Face datection, with the human face region in the determination image to be processed.Adjustment module 230 is used to increase the survey of the human face region
Light weight, and adjust according to the light metering weight brightness of the image to be processed, with the image that obtains that treated.Obtain module
210, face detection module 220 and adjustment module 230 can be by storing in the processor Running storage device in electronic equipment
Program instruction realize.
Module 210 is obtained for obtaining image to be processed.
Wherein, obtaining the image to be processed that module 210 obtains is the image for needing to carry out it recognition of face.One
In a embodiment, obtaining the image to be processed that module 210 obtains is the image under night vision scene.In one example, to
Processing image can be the image acquired in real time.In another example, image to be processed can be the image from any source.
It obtains module 210 and the image to be processed is acquired by image collecting device.Illustratively, image collecting device
It can be imaging sensor;Illustratively, image collector is set to security protection camera.
Face detection module 220 is used to carry out Face datection to the image to be processed, with determination human face region therein.
Illustratively, face detection module 220 can be by running human-face detector, to detect in facial image
Human face region.For example, human-face detector can be preparatory trained convolutional neural networks (Convolutional Neural
Network, CNN) human-face detector.For example, Ha Er (Haar) algorithm, Adaboost algorithm, convolutional Neural can be advanced with
The Face datections such as network and recognizer train human-face detector on the basis of a large amount of pictures.Or utilize standard
Opencv Face datection model locating human face region in the image to be processed.
In one embodiment, the human face region for obtaining the determination that module 210 obtains include face region with
And its neighboring area.
Adjustment module 230 is used to increase the light metering weight of the human face region, and according to light metering weight adjustment
The brightness of image to be processed, to obtain treated image.
Since adjustment module 230 increases the light metering weight of the human face region, when calculating exposure parameter, resulting exposure
Optical parameter preferentially guarantees the brightness of human face region, so that the brightness of human face region is met the requirement of recognition of face, avoids human face region
It is too dark or too bright.
In one embodiment, described device 200 further includes surveying optical module, and the survey optical module is used to survey light using matrix
Mode carries out survey light.Specifically, after obtaining image to be processed, optical module is surveyed by the image to be processed and is divided into several survey light
Area, and respective light metering weight is distributed for each area Ce Guang, after each area Ce Guang independently surveys light, then integration weighted calculation goes out
Whole exposure parameter.After face detection module 220 identifies human face region, determine that human face region is whole in image to be processed
Coordinate in a picture, and increase by adjustment module 230 light metering weight of the human face region, make the light metering weight of human face region
Higher than the light metering weight in other areas Ce Guang.
Adjustment module 230 is also used to the light metering weight according to each area Ce Guang and surveys the resulting brightness of image of light, adjustment figure
The exposure parameter of picture.Illustratively, it can be calculated required according to the light metering weight and brightness of image in each area Ce Guang
Exposure parameter, and current exposure parameter is adjusted according to required exposure parameter.Since the weight of human face region is higher than
Other areas Ce Guang, therefore calculate the exposure demand that resulting exposure parameter preferentially meets human face region.
After exposure parameter is adjusted, image collecting device shoots image with the exposure parameter through adjusting, so that institute
The exposure status of human face region in the image of shooting can satisfy the requirement of subsequent recognition of face.It, can be effective based on this
The phenomenon that influencing face normal exposure because calculating exposure parameter on the basis of full figure is avoided, it is poor to solve light and shade under night vision scene
Away from human face region exposure effect larger problem affected by environment caused by larger, to improve the efficiency of recognition of face simultaneously
Improve the accuracy of recognition of face.
It is understood that this method preferentially meets the brightness demand of human face region, i.e., other regions may be excessively dark at this time
Or it is excessively bright, but this has no effect on subsequent recognition of face.For example, in backlight scene, since scene parts zonal ray is too strong,
To make entire scene not overexposure, human face region may be imaged it is black, so that effective recognition of face can not be carried out to human face region.
Therefore, after increasing the light metering weight of human face region, when human face region brightness is relatively low, since it is weighed in overall picture
Again bigger than other regions, image collecting device can preferentially guarantee the brightness of human face region, by increasing exposure parameter so that people
Face regional exposure is to the value needed or ideal value, to meet the needs of recognition of face.At this point, the region other than human face region can
Energy overexposure, but since recognition of face is based only on the image of human face region part, may not necessarily consider the non-of other overexposures
Region Of Interest.Similarly, when human face region brightness is higher, due to increasing the light metering weight of human face region, exposure parameter at this time
The overexposure to reduce or avoid face split screen can be reduced.That is, human face region is exposure feelings in image to be processed
Condition need to meet the region of predetermined demand, and the region except region corresponding with preferred coordinates region can be unsatisfactory for for exposure status
The region of pre-provisioning request.
In one embodiment, adjustment module 230 dynamically adjusts institute by adjusting image gain and/or infrared lamp brightness
State the brightness of human face region.Specifically, when the brightness of the human face region is relatively low, image gain is turned up and/or infrared lamp is bright
Degree, to improve the brightness of the human face region;When the brightness of the human face region is relatively low, turns down gain and/or infrared lamp is bright
Degree, to reduce the brightness of the human face region.Illustratively, the infrared lamp is the near-infrared light compensating lamp of 850 nano wave lengths.?
In one embodiment, it is possible to use the light compensating lamp of more than one wavelength, such as both mended using the near infrared light of 850 nano wave lengths
Light, and use the near infrared light light filling of 940 nano wave lengths.
In another embodiment, described device 200 further includes light source adjusting module, for determining in the image to be processed
Light emitting source position;And reduce the light metering weight of the light emitting source position.By reducing light emitting source position
Light metering weight can reduce influence of the excessive brightness of light emitting source to overall exposing parameter, to avoid depositing due to light emitting source
And keep overall exposing parameter too low, cause human face region excessively dark.
Illustratively, light source adjusting module includes the mobile phone terminal configuration interface provided a user, by user configuration light emitting source
Position, and accordingly reduce light emitting source region light metering weight.Illustratively, the light emitting source includes image collecting device
Street lamp, garden lamp in installation site picture etc..
In one embodiment, described device 200 further includes face recognition module, for treated the image into
Row recognition of face.
Face recognition module can carry out recognition of face by trained deep learning neural network.Neural network is first
Feature vector is extracted to facial image to be identified.Such as LBP (local binary patterns), HoG (direction gradient histogram can be used
Figure), the various face feature extraction methods appropriate such as PCA (Principal Component Analysis) or neural network extract people to be identified
Face characteristic in face image simultaneously generates face feature vector, to be used for recognition of face.Neural network then and calculates resulting
Similarity in facial image to be identified and bottom library between the feature vector of facial image, if similarity is greater than similarity threshold
Value, then it is assumed that belong to the same person, otherwise then think to be not belonging to the same person.The feature vector of bottom library face can be deposits in advance
Storage.For example, storing the feature vector of bottom library face in storage medium when constructing bottom library.
Based on the human face region determined by face detection module 220, and the light metering weight carried out by adjustment module 230
It adjusts and the brightness regulation that carries out accordingly, the exposure status of the human face region in the image that can make that treated meets face knowledge
Other demand.
Based on above description, image processing apparatus according to an embodiment of the present invention solves human face region picture only
Exposure/under-exposure problem is obvious to the effect promoting of night vision scene human face identification.
Fig. 3 shows the schematic block diagram of image processing system 300 according to an embodiment of the present invention.Image processing system
300 include storage device 310 and processor 320.
Wherein, the storage of storage device 310 is for realizing the corresponding step in image processing method according to an embodiment of the present invention
Rapid program code.Program code of the processor 320 for being stored in Running storage device 310, it is real according to the present invention to execute
The corresponding steps of the image processing method of example are applied, and for realizing the phase in image processing apparatus according to an embodiment of the present invention
Answer module.
In one embodiment, when said program code is run by processor 320 image processing system 300 is executed
Following steps: image to be processed is obtained;Face datection is carried out to the image to be processed, with determination human face region therein;Increase
The light metering weight of the big human face region, and the brightness of the image to be processed is adjusted according to the light metering weight, to be located
Image after reason.
In one embodiment, image processing system 300 is held when said program code is run by processor 320
Row: treated based on described in, and image carries out recognition of face.
In one embodiment, image processing system 300 is held when said program code is run by processor 320
Row: survey light is carried out using matrix Exposure Metering.
In one embodiment, the matrix Exposure Metering includes: that the image to be processed is divided into several areas Ce Guang is only
It is vertical to survey light, and respective light metering weight is distributed for each area Ce Guang.
In one embodiment, the light metering weight for increasing the human face region includes: the survey for making the human face region
Light weight is higher than the light metering weight in other areas Ce Guang.
In one embodiment, the brightness for adjusting the image to be processed according to the light metering weight includes: to work as institute
State human face region brightness it is relatively low when, increase the brightness of the image to be processed, to improve the brightness of the human face region;When
When the brightness of the human face region is higher, the brightness of the image to be processed is reduced, to reduce the brightness of the human face region.
In one embodiment, described to be processed to increase or decrease by adjusting image gain and/or infrared lamp brightness
The brightness of image.
In one embodiment, the human face region includes face region and its neighboring area.
In one embodiment, image processing system 300 is held when said program code is run by processor 320
Row: light emitting source position in the image to be processed is determined;Reduce the light metering weight of the light emitting source position.
In addition, according to embodiments of the present invention, additionally providing a kind of storage medium, storing program on said storage
Instruction, when described program instruction is run by computer or processor for executing the image processing method of the embodiment of the present invention
Corresponding steps, and for realizing the corresponding module in image processing apparatus according to an embodiment of the present invention.The storage medium
It such as may include the storage card of smart phone, the storage unit of tablet computer, the hard disk of personal computer, read-only memory
(ROM), Erasable Programmable Read Only Memory EPROM (EPROM), portable compact disc read-only memory (CD-ROM), USB storage,
Or any combination of above-mentioned storage medium.The computer readable storage medium can be one or more computer-readable deposit
Any combination of storage media.
In one embodiment, the computer program instructions may be implemented real according to the present invention when being run by computer
Each functional module of the image processing apparatus of example is applied, and/or image procossing according to an embodiment of the present invention can be executed
Method.
In one embodiment, the computer program instructions make computer or place when being run by computer or processor
Reason device executes following steps: obtaining image to be processed;Face datection is carried out to the image to be processed, with determination face therein
Region;Increase the light metering weight of the human face region, and adjusts the brightness of the image to be processed according to the light metering weight, with
Obtain treated image.
In one embodiment, the computer program instructions make computer or place when being run by computer or processor
Manage device to execute: treated based on described in, and image carries out recognition of face.
In one embodiment, the computer program instructions make computer or place when being run by computer or processor
Reason device executes: carrying out survey light using matrix Exposure Metering.
In one embodiment, the matrix Exposure Metering includes: that the image to be processed is divided into several areas Ce Guang is only
It is vertical to survey light, and respective light metering weight is distributed for each area Ce Guang.
In one embodiment, the light metering weight for increasing the human face region includes: the survey for making the human face region
Light weight is higher than the light metering weight in other areas Ce Guang.
In one embodiment, the brightness for adjusting the image to be processed according to the light metering weight includes: to work as institute
State human face region brightness it is relatively low when, increase the brightness of the image to be processed, to improve the brightness of the human face region;When
When the brightness of the human face region is higher, the brightness of the image to be processed is reduced, to reduce the brightness of the human face region.
In one embodiment, described to be processed to increase or decrease by adjusting image gain and/or infrared lamp brightness
The brightness of image.
In one embodiment, the human face region includes face region and its neighboring area.
In one embodiment, the computer program instructions make computer or place when being run by computer or processor
Reason device executes: determining light emitting source position in the image to be processed;Reduce the light metering weight of the light emitting source position.
Each module in image processing apparatus according to an embodiment of the present invention can pass through people according to an embodiment of the present invention
Face identifies the computer program instructions that the processor operation of electronic equipment stores in memory to realize, or can be in basis
The computer instruction stored in the computer readable storage medium of the computer program product of the embodiment of the present invention is transported by computer
Row Shi Shixian.
Image processing method, device, system and storage medium according to an embodiment of the present invention are according to the face area detected
Domain dynamic regulation light metering weight solves the problems, such as that human face region picture is excessively dark or overexposure, to the identification of night vision scene human face
Effect promoting is obvious.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in a storage medium
In, it is used including some instructions so that a terminal device executes method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of image processing method, which is characterized in that the described method includes:
Obtain image to be processed;
Face datection is carried out to the image to be processed, with determination human face region therein;
Increase the light metering weight of the human face region, and adjusts the brightness of the image to be processed according to the light metering weight, with
Obtain treated image.
2. the method according to claim 1, wherein the method also includes:
Recognition of face is carried out based on treated the image.
3. the method according to claim 1, wherein the method carries out survey light, institute using matrix Exposure Metering
Stating matrix Exposure Metering includes:
The image to be processed is divided into several areas Ce Guang and independently surveys light, and distributes respective survey light power for each area Ce Guang
Weight.
4. according to the method described in claim 3, it is characterized in that, the light metering weight for increasing the human face region includes:
The light metering weight of the human face region is set to be higher than the light metering weight in other areas Ce Guang.
5. the method according to claim 1, wherein described adjust the figure to be processed according to the light metering weight
The brightness of picture includes:
When the brightness of the human face region is relatively low, increase exposure parameter, to improve the brightness of the human face region;
When the brightness of the human face region is higher, exposure parameter is reduced, to reduce the brightness of the human face region.
6. the method according to claim 1, wherein the human face region includes face region and its periphery
Region.
7. the method according to claim 1, wherein the method also includes:
Determine light emitting source position in the image to be processed;
Reduce the light metering weight of the light emitting source position.
8. a kind of image processing apparatus, which is characterized in that described device includes:
Module is obtained, for obtaining image to be processed;
Face detection module, for carrying out Face datection to the image to be processed, with the people in the determination image to be processed
Face region;And
Module is adjusted, for increasing the light metering weight of the human face region, and it is described to be processed according to light metering weight adjustment
The brightness of image, to obtain treated image.
9. a kind of image processing system, which is characterized in that the system comprises storage device and processor, on the storage device
It is stored with the computer program run by the processor, the computer program is executed when being run by the processor as weighed
Benefit requires image processing method described in any one of 1-7.
10. a kind of storage medium, which is characterized in that be stored with computer program, the computer program on the storage medium
The image processing method as described in any one of claim 1-7 is executed at runtime.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811215311.4A CN109543523A (en) | 2018-10-18 | 2018-10-18 | Image processing method, device, system and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811215311.4A CN109543523A (en) | 2018-10-18 | 2018-10-18 | Image processing method, device, system and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109543523A true CN109543523A (en) | 2019-03-29 |
Family
ID=65844180
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811215311.4A Pending CN109543523A (en) | 2018-10-18 | 2018-10-18 | Image processing method, device, system and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109543523A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111050086A (en) * | 2019-12-18 | 2020-04-21 | 重庆金山医疗技术研究院有限公司 | Image processing method, device, equipment and storage medium |
CN112055961A (en) * | 2020-08-06 | 2020-12-08 | 深圳市锐明技术股份有限公司 | Shooting method, shooting device and terminal equipment |
CN115424383A (en) * | 2022-10-10 | 2022-12-02 | 广州睿泰智能设备科技股份有限公司 | Intelligent access control management system and method |
CN117237258A (en) * | 2023-11-14 | 2023-12-15 | 山东捷瑞数字科技股份有限公司 | Night vision image processing method, system, equipment and medium based on three-dimensional engine |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1567373A (en) * | 2003-06-24 | 2005-01-19 | 明基电通股份有限公司 | Apparatus and method for determining exposure setting of image having human face area |
KR20130047992A (en) * | 2011-11-01 | 2013-05-09 | 한국공항공사 | System and method for aligning runway visual range measuring equipment |
CN104202524A (en) * | 2014-09-02 | 2014-12-10 | 三星电子(中国)研发中心 | Method and device for backlight filming |
CN104394326A (en) * | 2014-11-10 | 2015-03-04 | 广东欧珀移动通信有限公司 | Photometry method and terminal |
CN107370961A (en) * | 2017-06-16 | 2017-11-21 | 广东欧珀移动通信有限公司 | image exposure processing method, device and terminal device |
CN107734225A (en) * | 2017-10-24 | 2018-02-23 | 维沃移动通信有限公司 | A kind of image pickup method and device |
CN107872613A (en) * | 2016-09-23 | 2018-04-03 | 中兴通讯股份有限公司 | A kind of method, device and mobile terminal that recognition of face is carried out using dual camera |
-
2018
- 2018-10-18 CN CN201811215311.4A patent/CN109543523A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1567373A (en) * | 2003-06-24 | 2005-01-19 | 明基电通股份有限公司 | Apparatus and method for determining exposure setting of image having human face area |
KR20130047992A (en) * | 2011-11-01 | 2013-05-09 | 한국공항공사 | System and method for aligning runway visual range measuring equipment |
CN104202524A (en) * | 2014-09-02 | 2014-12-10 | 三星电子(中国)研发中心 | Method and device for backlight filming |
CN104394326A (en) * | 2014-11-10 | 2015-03-04 | 广东欧珀移动通信有限公司 | Photometry method and terminal |
CN107872613A (en) * | 2016-09-23 | 2018-04-03 | 中兴通讯股份有限公司 | A kind of method, device and mobile terminal that recognition of face is carried out using dual camera |
CN107370961A (en) * | 2017-06-16 | 2017-11-21 | 广东欧珀移动通信有限公司 | image exposure processing method, device and terminal device |
CN107734225A (en) * | 2017-10-24 | 2018-02-23 | 维沃移动通信有限公司 | A kind of image pickup method and device |
Non-Patent Citations (2)
Title |
---|
刘玉萍等: "《数码摄影:从入门到精通》", 29 February 2004 * |
薛以平等: "《数码影像修饰艺术 数码影像基础》", 31 March 2013 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111050086A (en) * | 2019-12-18 | 2020-04-21 | 重庆金山医疗技术研究院有限公司 | Image processing method, device, equipment and storage medium |
CN111050086B (en) * | 2019-12-18 | 2021-10-19 | 重庆金山医疗技术研究院有限公司 | Image processing method, device and equipment |
CN112055961A (en) * | 2020-08-06 | 2020-12-08 | 深圳市锐明技术股份有限公司 | Shooting method, shooting device and terminal equipment |
CN112055961B (en) * | 2020-08-06 | 2021-09-17 | 深圳市锐明技术股份有限公司 | Shooting method, shooting device and terminal equipment |
CN115424383A (en) * | 2022-10-10 | 2022-12-02 | 广州睿泰智能设备科技股份有限公司 | Intelligent access control management system and method |
CN117237258A (en) * | 2023-11-14 | 2023-12-15 | 山东捷瑞数字科技股份有限公司 | Night vision image processing method, system, equipment and medium based on three-dimensional engine |
CN117237258B (en) * | 2023-11-14 | 2024-02-09 | 山东捷瑞数字科技股份有限公司 | Night vision image processing method, system, equipment and medium based on three-dimensional engine |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109543523A (en) | Image processing method, device, system and storage medium | |
KR102667740B1 (en) | Device and method for matching image | |
CN105335722B (en) | Detection system and method based on depth image information | |
CN110663045B (en) | Method, electronic system and medium for automatic exposure adjustment of digital images | |
JP2022547183A (en) | Biometric face detection method, device, equipment and computer program | |
CN105245786B (en) | A kind of self-timer method based on intelligent testing light, self-heterodyne system and camera terminal | |
CN106682620A (en) | Human face image acquisition method and device | |
CN106161980A (en) | Photographic method and system based on dual camera | |
CN104091176A (en) | Technology for applying figure and head portrait comparison to videos | |
US20230351809A1 (en) | Iris authentication device, iris authentication method, and recording medium | |
CN102542552A (en) | Frontlighting and backlighting judgment of video images and detection method of shooting time | |
CN111654643B (en) | Exposure parameter determination method and device, unmanned aerial vehicle and computer readable storage medium | |
CN113887387A (en) | Ski field target image generation method, system and server | |
CN110766650A (en) | Biological detection early warning method, system, device, computer equipment and storage medium | |
CN206849035U (en) | A kind of image processing apparatus and face identification system | |
CN111835961B (en) | Information processing method and device for automatic exposure of camera and storage medium | |
CN115147936A (en) | Living body detection method, electronic device, storage medium, and program product | |
CN114387548A (en) | Video and liveness detection method, system, device, storage medium and program product | |
CN108073873A (en) | Human face detection and tracing system based on high-definition intelligent video camera | |
CN109978810A (en) | Detection method, system, equipment and the storage medium of mole | |
CN110210401B (en) | Intelligent target detection method under weak light | |
CN114885096B (en) | Shooting mode switching method, electronic equipment and storage medium | |
Mukherjee et al. | Energy efficient face recognition in mobile-fog environment | |
US20210192205A1 (en) | Binding of selfie face image to iris images for biometric identity enrollment | |
JP6991771B2 (en) | Information processing equipment, information processing system, information processing method and program |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |