CN106778645B - A kind of image processing method and device - Google Patents
A kind of image processing method and device Download PDFInfo
- Publication number
- CN106778645B CN106778645B CN201611210672.0A CN201611210672A CN106778645B CN 106778645 B CN106778645 B CN 106778645B CN 201611210672 A CN201611210672 A CN 201611210672A CN 106778645 B CN106778645 B CN 106778645B
- Authority
- CN
- China
- Prior art keywords
- image
- facial images
- facial
- quality evaluation
- images
- 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.)
- Active
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
-
- 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
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
An embodiment of the present invention provides a kind of image processing method and device, the described method includes:Obtain pending image;Face datection is carried out to the pending image, obtains M facial images, the M is positive integer;The M facial images are screened, obtain N facial images, the N is the integer less than or equal to the M;The N facial images are uploaded to server.Intelligent upload image can be realized by the embodiment of the present invention.
Description
Technical field
The present invention relates to computer vision calculating fields, and in particular in cluster computing system, a kind of image processing method
Method and device.
Background technology
With economic, society, the fast development of culture, growing day by day, more and more population from other places of impact at home and abroad power
City is flowed to, these populations increase while urbanization process is accelerated, and the challenge of bigger is also brought for city management, although,
The calculating analysis of video monitoring and machine vision based on video provides urban safety technical support, still, at present,
Camera is laid out in city and comes, and the function of each camera is more independent, when needing to search for some personage, it is necessary to
The video image of each camera shooting is checked frame by frame, in this way, cannot be preferably by entire section or even entire city
Camera resource fully utilizes.In the prior art, at present, machine vision calculating relates generally in the formula concentrated calculating
The heart is, it is necessary to carry out the data such as video image to collect processing.If it is uploaded in video monitoring system when deploying to ensure effective monitoring and control of illegal activities object, as using regarding
Some face in frequency image as deploy to ensure effective monitoring and control of illegal activities object when, it is necessary to artificially intercepted to the face, then, then after uploading interception
Facial image, in this way, during object is deployed to ensure effective monitoring and control of illegal activities in upload, it is impossible to intelligently upload image;And in the gatherer process of image,
To many quality evaluation and analysis of carry out of image, and from the picture source data and one for uploading satisfactory high quality
A critically important one side, this is in existing system and cannot meet the requirements, also without accomplishing intelligent upload
Image.
The content of the invention
An embodiment of the present invention provides a kind of image processing method and device, can during object is deployed to ensure effective monitoring and control of illegal activities in upload,
Intelligently upload image.
First aspect of the embodiment of the present invention provides a kind of image processing method, including:
Obtain pending image;
Face datection is carried out to the pending image, obtains M facial images, the M is positive integer;
The M facial images are screened, obtain N facial images, the N is whole less than or equal to the M
Number;
The N facial images are uploaded to server.
It is described to the M with reference to the embodiment of the present invention in a first aspect, in the first possible embodiment of first aspect
Facial image is opened to be screened, including:
The angle information of facial image i is obtained, the angle information is following at least one:Horizontally rotate angle, pitching
Angle and gradient, the facial image i are any facial image in the M facial images;
The angle information of the facial image i is compared with predetermined angle information, in the angle of the facial image i
When information compares successfully with the predetermined angle information, retain the facial image i.
It is described to the M with reference to the embodiment of the present invention in a first aspect, in second of possible embodiment of first aspect
It opens facial image to be screened, obtains N facial images, including:
The image that human face region is not blocked in the M facial images is filtered out, obtains K facial images, the K is
Positive integer;
Image quality evaluation is carried out to the K facial images, obtains the K image quality evaluation values;
The image quality evaluation values more than predetermined threshold value are chosen from the K image quality evaluation values, are obtained described N number of
Image quality evaluation values obtain the corresponding N facial image of the N number of image quality evaluation values.
With reference to the first or second of possible embodiment of first aspect of the embodiment of the present invention or first aspect, first
It is described that the N facial images are uploaded onto the server in the third possible embodiment of aspect, including:
The N facial images are compressed, obtain the N first object facial images;
The N first object facial images and its corresponding attribute information are uploaded into the server.
With reference to the first or second of possible embodiment of first aspect of the embodiment of the present invention or first aspect, first
In the third possible embodiment of aspect, the M facial images are screened described, obtain N facial images it
Afterwards, the method further includes:
Image enhancement processing is carried out to the N facial images;
It is described that the N facial images are uploaded to server, including:
The N after image enhancement facial images are uploaded to the server.
Second aspect of the embodiment of the present invention provides a kind of image processing apparatus, including:
Acquiring unit, for obtaining pending image;
Detection unit for carrying out Face datection to the pending image, obtains M facial images, and the M is just whole
Number;
Screening unit for being screened to the M facial images, obtains N facial images, the N to be less than or
Equal to the integer of the M;
Uploading unit, for the N facial images to be uploaded to server.
With reference to second aspect of the embodiment of the present invention, in the first possible embodiment of second aspect, the screening is single
Member includes:
Acquisition module, for obtaining the angle information of facial image i, the angle information is following at least one:It is horizontal
Rotational angle, pitch angle and gradient, the facial image i are any facial image in the M facial images;
Comparing module, for the angle information of the facial image i to be compared with predetermined angle information, in the people
When the angle information of face image i compares successfully with the predetermined angle information, retain the facial image i.
With reference to second aspect of the embodiment of the present invention, in the first possible embodiment of second aspect, the screening is single
Member includes:
Screening module for filtering out the image that human face region is not blocked in the M facial images, obtains K people
Face image, the K are positive integer;
Evaluation module for carrying out image quality evaluation to the K facial images, obtains the K picture quality and comments
Value;
Module is chosen, for choosing the image quality evaluation more than predetermined threshold value from the K image quality evaluation values
Value, obtains N number of image quality evaluation values, obtains the corresponding N facial image of the N number of image quality evaluation values.
With reference to the first or second of possible embodiment of second aspect of the embodiment of the present invention or second aspect, second
In the third possible embodiment of aspect, the uploading unit includes:
Compression module for the N facial images to be compressed, obtains the N first object facial images;
Uploading module, for the N first object facial images and its corresponding attribute information to be uploaded to the clothes
Business device.
With reference to the first or second of possible embodiment of second aspect of the embodiment of the present invention or second aspect, second
In 4th kind of possible embodiment of aspect, described image processing unit further includes:
Processing unit for being screened in the screening unit to the M facial images, obtains N facial images
Afterwards, image enhancement processing is carried out to the N facial images;
The uploading unit is specifically used for:
The N after image enhancement facial images are uploaded to the server.Implement the embodiment of the present invention, have such as
Lower advantageous effect:
As can be seen that by the embodiment of the present invention, pending image is obtained, Face datection is carried out to pending image, is obtained
To M facial images, M is positive integer, and M facial images are screened, and obtains N facial images, and N is less than or equal to M
Integer, N facial images are uploaded to server, so, it can be achieved that intelligent upload image.
Description of the drawings
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is some embodiments of the present invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is a kind of first embodiment flow diagram of image processing method provided in an embodiment of the present invention;
Fig. 2 is a kind of second embodiment flow diagram of image processing method provided in an embodiment of the present invention;
Fig. 3 a are a kind of first embodiment structure diagrams of image processing apparatus provided in an embodiment of the present invention;
Fig. 3 b are the structural representations of the screening unit of the described image processing apparatus of Fig. 3 a provided in an embodiment of the present invention
Figure;
Fig. 3 c are the another structures of the screening unit of the described image processing apparatus of Fig. 3 a provided in an embodiment of the present invention
Schematic diagram;
Fig. 3 d are the structural representations of the uploading unit of the described image processing apparatus of Fig. 3 a provided in an embodiment of the present invention
Figure;
Fig. 3 e are the another structure diagrams of the described image processing apparatus of Fig. 3 a provided in an embodiment of the present invention;
Fig. 4 is a kind of second embodiment structure diagram of image processing apparatus provided in an embodiment of the present invention.
Specific embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is part of the embodiment of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained without creative efforts
Example, belongs to the scope of protection of the invention.
Term " first ", " second ", " the 3rd " in description and claims of this specification and the attached drawing and "
Four " etc. be for distinguishing different objects rather than for describing particular order.In addition, term " comprising " and " having " and it
Any deformation, it is intended that cover non-exclusive include.Such as it contains the process of series of steps or unit, method, be
The step of system, product or equipment are not limited to list or unit, but optionally further include the step of not listing or list
Member is optionally further included for the intrinsic other steps of these processes, method, product or equipment or unit.
Referenced herein " embodiment " is it is meant that a particular feature, structure, or characteristic described can wrap in conjunction with the embodiments
Containing at least one embodiment of the present invention.It is identical that each position in the description shows that the phrase might not be each meant
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
Image processing apparatus described by the embodiment of the present invention can include smart mobile phone (such as Android phone, iOS mobile phones,
Windows Phone mobile phones etc.), tablet computer, palm PC, laptop, mobile internet device (MID, Mobile
Internet Devices) or Wearable etc., above-mentioned is only citing, and non exhaustive, including but not limited to above device.Example
Such as, when above-mentioned image processing apparatus is mobile phone, the application software of the application implementation embodiment of the present invention can be installed in mobile phone, in this way,
Image can be uploaded in mobile phone terminal, for example, Security Personnel is captured to someone, then can take pictures to it, its facial image is uploaded to
Server can complete the monitoring to the people by server.
It should be noted that the image processing apparatus in the embodiment of the present invention can be connected with multiple cameras, each camera shooting
Head is used equally for capturing video image, each camera can there are one corresponding position mark, alternatively, can there are one with
Corresponding number.Under normal conditions, camera may be provided at public place, for example, school, museum, crossroad, walking
Street, office building, garage, airport, hospital, subway station, station, bus platform, supermarket, hotel, public place of entertainment etc..Camera exists
After taking video image, the memory of system where which can be saved in image processing apparatus.It can in memory
Multiple images storehouse is stored with, each image library can include the different video image of same people, and certainly, each image library can also be used
In the video image in one region of storage or the video image of some specified camera shooting.
Still optionally further, in the embodiment of the present invention, each frame video image of camera shooting corresponds to an attribute
Information, attribute information are following at least one:The shooting time of video image, the position of video image, the attribute of video image
Character features attribute in parameter (form, size, resolution ratio etc.), the number and video image of video image.Above-mentioned video figure
Character features attribute as in may include but be not limited only to:Personage's number, character positions, personage's angle in video image etc.
Deng.
Explanation is needed further exist for, the video image of each camera acquisition is usually dynamic human face image, thus, this
The angle information of facial image can be planned in inventive embodiments, above-mentioned angle information may include but be not limited only to:Water
Flat rotational angle, pitch angle or gradient.For example, can define dynamic human face image data two spacing of requirement is not less than 30 pictures
Element, it is proposed that more than 60 pixels.Horizontally rotate angle no more than ± 30 °, pitch angle be no more than ± 20 °, inclination angle be no more than ±
45°.Recommended levels rotational angle is no more than ± 15 ° no more than ± 15 °, pitch angle no more than ± 10 °, inclination angle.For example, may be used also
It is screened to whether facial image is blocked by other objects, it is generally the case that jewelry should not block face's main region, jewelry
Such as dark sunglasses, mask and exaggeration jewellery, it is of course also possible to be covered with dust all over above camera, cause facial image to be hidden
Gear.The picture format of video image in the embodiment of the present invention may include but be not limited only to:BMP, JPEG, JPEG2000, PNG etc.
Deng size can be between 10-30KB, and each video image can also correspond to a shooting time and shoot the video
The camera Unified number of image, panorama big figure corresponding with facial image such as link at information (facial image and the global image
Establish feature correspondence relational file).
Referring to Fig. 1, the first embodiment flow diagram for a kind of image processing method provided in an embodiment of the present invention.
Image processing method described in the present embodiment, comprises the following steps:
101st, pending image is obtained.
Wherein, any image that pending image can be shot by camera.Certainly, pending image may also be multiple figures
Picture.Certainly, above-mentioned pending image can be the image comprising some personage, which can voluntarily be specified by user.It waits to locate
One or more facial image can be included in reason image.
Still optionally further, other targets that user specifies can also be included in image to be checked, for example, automobile, car plate,
Etc..
Optionally, in above-mentioned steps 101, pending image is obtained, it may include following steps:
102nd, Face datection is carried out to the pending image, obtains M facial images, the M is positive integer.
Wherein, for any pending image, image processing apparatus is required to carry out Face datection to the pending image,
In this way, can extract the facial image in the pending image, when multiple faces are included in pending image, multiple people are can obtain
Face image when 1 facial image is included in pending image, can obtain 1 facial image, not include in pending image
During facial image, then after Face datection, 0 facial image is obtained.Following at least one people can be used in above-mentioned Face datection
Face detection algorithm is realized:Several frequently seen Face datection algorithm is set forth below.
Boosting graders, boosting may be considered a kind of Feature Selection algorithm, due to its simple and extensive energy
The features such as power is strong suffers from very wide application in many fields.Specifically, boosting is by the spy of original weave in
Space is levied, is selected by feature and strengthens mistake and the weight of sample is divided progressively to separate sample space.
HAAR human-face detectors, HAAR human-face detectors be earliest by Face datection be promoted to application level algorithm it
One.Algorithm is broadly divided into three parts, and Weak Classifier feature and strong classifier structure are selected in feature generation, boosting.It is special
Sign generation mainly builds many chequered with black and white rectangular blocks, and spy is generated by comparing the difference of the pixel sum of black and white rectangle
Sign, is named that be also due to its calculating process similar with the calculating process of HAAR small echos, the pixel of rectangular block and can be based on integration
Figure calculates, calculating speed and considerable overhead;Feature is selected to be carried out by boosting algorithms;Finally it will be singled out
The Weak Classifier feature come generates many strong classifiers by combinations of features.
Rigid or nonrigid object is divided into many by DPM (Deformable Part Model) human-face detector, DPM
Subassembly, by each subassembly being described come the final object for expressing wanted recognition detection, each component and subassembly pass through
HOG carries out feature description.The response filter of each part is solved by optimization algorithm.Since its calculating is relatively multiple
It is miscellaneous, limit its application in many fields.
ACF (Aggregated Channel Feature) human-face detector, ACF is ICF (Integral Channel
Feature a kind of extension) is equivalent on the basis of ICF and has done a sub-sampling, the advantage of doing so is that on the one hand reducing
The dimension of feature, two one side can increase the resilience to deformation.ACF is applied to pedestrian detection field, Zhi Houyou earliest
Its application is also achieved good effect by people with Face datection field.But since its computing cost is still bigger, feature
There are larger redundancy, room for improvement is also very big.
PICO (Pixel Intensity Comparison Object Detector) human-face detector, PICO are a kind of
Feature based on statistical property describes algorithm, and feature description is similar with Ferns, due to the simplicity and relatively by force of its calculating
Descriptive power, be used in many computer vision fields such as fields such as object detection, target identification, target following.Recently
Someone is applied in Face datection field, and precision is more general, but calculating speed is very fast.It traces it to its cause or mark sheet
Up to too simple, there is bigger room for promotion.
103rd, the M facial images are screened, obtains N facial images, the N is less than or equal to the M
Integer.
Optionally, user can choose N facial images from M facial images, it is of course also possible to by M facial image
It is ranked up according to picture quality by good to bad, so as to can preferentially choose the preferably N number of facial image of picture quality.
Optionally, in above-mentioned steps 103, the M facial images are screened, it may include following steps:
A1 the angle information of facial image i), is obtained, the angle information is following at least one:Horizontally rotate angle,
Pitch angle and gradient, the facial image i are any facial image in the M facial images;
A2), the angle information of the facial image i is compared with predetermined angle information, the facial image i's
When angle information compares successfully with the predetermined angle information, retain the facial image i.
Wherein, due to there is a certain distance between camera and face, and, it is generally the case that people be also it is dynamic, because
And the angle for the facial image that camera is captured also constantly is changing, if user movement obtains comparatively fast, then possible camera is caught
The fogging image grasped, alternatively, only half of face, alternatively, only there are one silhouette, in this way, at this stage, then it can not be to such figure
As being identified.Thus, during image is uploaded, it is necessary to the angle of angular image, if angle not in the range of some,
It is then not easy to subsequently deploy to ensure effective monitoring and control of illegal activities, predetermined angle information is then to upload image for specification, only meets the upper of the predetermined angle information
Blit picture can just upload onto the server.Predetermined angle information can include following at least one:Horizontally rotate angular range, pitching
Angular region and inclination range.For example, horizontally rotating, angle is ± 30 °, pitch angle is ± 20 °, inclination angle is ± 45 °.
Optionally, in above-mentioned steps 103, the M facial images are screened, the M facial images are carried out
Screening obtains N facial images, it may include following steps:
B1 the image that human face region is not blocked in the M facial images), is filtered out, obtains K facial images, institute
K is stated as positive integer;
B2 image quality evaluation), is carried out to the K facial images, obtains the K image quality evaluation values;
B3 the image quality evaluation values more than predetermined threshold value), are chosen from the K image quality evaluation values, obtain institute
N number of image quality evaluation values are stated, obtain the corresponding N facial image of the N number of image quality evaluation values.
Wherein, in step 41, continuous shooting mode can be used, obtain multiple corresponding images of targets preview parameter.It is above-mentioned such as
What chooses best one of picture quality from multiple images.At least one image quality evaluation index can be used respectively to image
Image quality evaluation is carried out, obtains image quality evaluation values, wherein, image quality evaluation index may include but be not limited only to:It is flat
Equal gray scale, mean square deviation, entropy, edge conservation degree, signal-to-noise ratio etc..The image quality evaluation values that may be defined as are bigger, then scheme
Image quality amount is better.
It should be noted that when being evaluated due to use single evaluation index picture quality, there is certain limitation
Property, therefore, multiple images quality evaluation index, which can be used, evaluates picture quality, and certainly, picture quality is evaluated
When, not image quality evaluation index is The more the better, because image quality evaluation index is more, the meter of image quality assessment process
Calculation complexity is higher, and also not necessarily image quality evaluation effect is better, therefore, in the situation more demanding to image quality evaluation
Under, 2~10 image quality evaluation indexs can be used, picture quality is evaluated.Specifically, image quality evaluation is chosen to refer to
Target number and which index, according to depending on specific implementation situation.Certainly, specifically scene selection picture quality must be also combined to comment
Valency index carries out carrying out under dark situation the image quality index of image quality evaluation selection under image quality evaluation and bright ring border
It can be different.
Optionally, in the case of not high to image quality evaluation required precision, an image quality evaluation index can be used
It is evaluated, for example, carrying out image quality evaluation values to pending image with entropy, it is believed that entropy is bigger, then illustrates picture quality
It is better, on the contrary, entropy is smaller, then illustrate that picture quality is poorer.
Optionally, in the case of higher to image quality evaluation required precision, multiple images quality evaluation may be employed
Index evaluates pending image, and image quality evaluation is carried out to pending image in multiple images quality evaluation index
When, the weight of each image quality evaluation index in the plurality of image quality evaluation index can be set, can obtain multiple images matter
Evaluation of estimate is measured, final image quality evaluation values, example are can obtain according to the plurality of image quality evaluation values and its corresponding weight
Such as, three image quality evaluation indexs are respectively:A indexs, B indexs and C indexs, the weight of A is a1, and the weight of B is a2, C's
Weight is a3, using A, B and C to a certain image carry out image quality evaluation when, the corresponding image quality evaluation values of A be b1, B pairs
The image quality evaluation values answered are b2, and the corresponding image quality evaluation values of C are b3, then, last image quality evaluation values=
a1b1+a2b2+a3b3.Under normal conditions, image quality evaluation values are bigger, illustrate that picture quality is better.
104th, the N facial images are uploaded to server.
Optionally, in above-mentioned steps 104, the N facial images are uploaded onto the server, including:
41), the N facial images are compressed, obtain the N first object facial images;
42) N first object facial images and its corresponding attribute information, are uploaded into the server.
Wherein, N facial images can be compressed, lossy compression method mode or lossless compression mode may be selected to the N
Facial image is opened to be compressed.In this way, it can accelerate uploading speed during the N facial images are uploaded.Certainly, press
The memory size of N after contracting facial images can be in a certain scope, for example, 10kb~30kb.
Certainly, before step 41, can also perform the following steps:
The size of above-mentioned N facial images is adjusted to consistent, then the N facial images are carried out in step 41 again
Compression.It is not of uniform size due to the facial image that is detected in pending image, mainly since camera imaging is related, from
Camera is nearer, and facial image is bigger, more remote from camera, then facial image is smaller.Thus, it can be by all people's face image
Size is adjusted to consistent, in this way, can facilitate follow-up management.
As can be seen that by the embodiment of the present invention, pending image is obtained, Face datection is carried out to pending image, is obtained
To M facial images, M is positive integer, and M facial images are screened, and obtains N facial images, and N is less than or equal to M
Integer, N facial images are uploaded to server, so, it can be achieved that intelligent upload image.
Consistent with the abovely, referring to Fig. 2, second for a kind of image processing method provided in an embodiment of the present invention implements
Example flow diagram.Image processing method described in the present embodiment, comprises the following steps:
201st, pending image is obtained.
202nd, Face datection is carried out to the pending image, obtains M facial images, the M is positive integer.
203rd, the M facial images are screened, obtains N facial images, the N is less than or equal to the M
Integer.
Optionally, the specific descriptions of above-mentioned steps 201- steps 203 can refer to the step of the described image processing methods of Fig. 1
Rapid 101- steps 103.
204th, image enhancement processing is carried out to the N facial images.
Wherein, image enhancement processing is to promote the picture quality of the N facial images, the mode of image enhancement processing
It may include but be not limited only to:Contrast stretching, histogram equalization, image restoration, wavelet transformation, certainly, due to the N faces
Image is different image, thus, the contrast of each image, average gray are different, thus, different images can be used
Enhance processing mode and image enhancement processing is carried out to the N facial images.After image enhancement processing is carried out to facial image, people
The better quality of face image is more convenient subsequent user and carries out image retrieval, alternatively, being managed and safeguarding.
Optionally, above-mentioned steps 204 carry out image enhancement processing to the N facial images, can also include following step
Suddenly:
Image quality evaluation is carried out to the N facial images, obtains N number of image quality evaluation values;
Choose X image quality evaluation values for being less than pre-set image quality threshold in N number of image quality evaluation values;
Image enhancement processing is carried out to the corresponding facial image of the X image quality evaluation values, is removed in the N facial images
The corresponding facial image of X image quality evaluation values does not make image enhancement processing then.
Wherein, above-mentioned pre-set image quality threshold can voluntarily be set or system default by user.
205th, the N after image enhancement facial images are uploaded to the server.
Wherein, can upload onto the server to the N after image enhancement facial images, certainly, server can also be to the N
It opens facial image to be identified, if in any image storehouse in a certain image and image processing apparatus in the N facial images
Image mismatch, then can establish new storehouse for preserving the facial image, if a certain image in the N facial images with
The facial image, then can be stored in the image library by the images match in a certain image library in image processing apparatus.
As can be seen that by the described image processing apparatus of the embodiment of the present invention, pending image can be obtained, treats place
It manages image and carries out Face datection, obtain M facial images, M is positive integer, and M facial images are screened, and obtains N people
Face image, N are the integer less than or equal to M, and N facial images are carried out with image enhancement processing, and by the N after image enhancement
Facial image is uploaded to server, so, it can be achieved that intelligent upload image.
Consistent with the abovely, it is specific as follows below to implement the device of above-mentioned image processing method:
Fig. 3 a are referred to, are a kind of first embodiment structural representation of image processing apparatus provided in an embodiment of the present invention
Figure.Image processing apparatus described in the present embodiment, including:Acquiring unit 301, detection unit 302,303 and of screening unit
Uploading unit 304, it is specific as follows:
Acquiring unit 301, for obtaining pending image;
Detection unit 302 for carrying out Face datection to the pending image, obtains M facial images, and the M is
Positive integer;
Screening unit 303 for being screened to the M facial images, obtains N facial images, the N be less than
Or the integer equal to the M;
Uploading unit 304, for the N facial images to be uploaded to server.
Optionally, such as Fig. 3 b, Fig. 3 b are the specific refinement of the screening unit 303 of the image processing apparatus described in Fig. 3 a
Structure, the screening unit 303 may include:Acquisition module 3031 and comparing module 3032, it is specific as follows:
Acquisition module 3031, for obtaining the angle information of facial image i, the angle information is following at least one:
Horizontally rotate angle, pitch angle and gradient, the facial image i is any facial image in the M facial images;
Comparing module 3032, for the angle information of the facial image i to be compared with predetermined angle information, in institute
It states the angle information of facial image i and when the predetermined angle information compares successfully, retains the facial image i.
Optionally, such as Fig. 3 c, Fig. 3 c are the specific refinement of the screening unit 303 of the image processing apparatus described in Fig. 3 a
Structure, the screening unit 303 may include:Screening module 3033, evaluation module 3034 and selection module 3035, it is specific as follows:
Screening module 3033 for filtering out the image that human face region is not blocked in the M facial images, obtains K
Facial image is opened, the K is positive integer;
Evaluation module 3034 for carrying out image quality evaluation to the K facial images, obtains the K image matter
Measure evaluation of estimate;
Module 3035 is chosen, for choosing the picture quality more than predetermined threshold value from the K image quality evaluation values
Evaluation of estimate obtains N number of image quality evaluation values, obtains the corresponding N facial image of the N number of image quality evaluation values.
Optionally, such as Fig. 3 d, Fig. 3 d are the specific refinement of the uploading unit 304 of the image processing apparatus described in Fig. 3 a
Structure, the uploading unit 304 may include:Compression module 3041 and uploading module 3042, it is specific as follows;
Compression module 3041 for the N facial images to be compressed, obtains the N first object face figures
Picture;
Uploading module 3042, for the N first object facial images and its corresponding attribute information to be uploaded to institute
State server.
Optionally, such as Fig. 3 e, Fig. 3 e are the another modification structures of the image processing apparatus described in Fig. 3 a, can also be wrapped
It includes:Processing unit 305, it is specific as follows:
Processing unit 305 for being screened in the screening unit 303 to the M facial images, obtains N people
After face image, image enhancement processing is carried out to the N facial images;
The uploading unit 304 is specifically used for:
The N after image enhancement facial images are uploaded to the server.
As can be seen that by the described image processing apparatus of the embodiment of the present invention, pending image can be obtained, treats place
It manages image and carries out Face datection, obtain M facial images, M is positive integer, and M facial images are screened, and obtains N people
Face image, N are the integer less than or equal to M, and N facial images are uploaded to server, so, it can be achieved that intelligent upper blit
Picture.
Consistent with the abovely, referring to Fig. 4, second for a kind of image processing apparatus provided in an embodiment of the present invention implements
Example structure diagram.Image processing apparatus described in the present embodiment, including:At least one input equipment 1000;At least one
A output equipment 2000;At least one processor 3000, such as CPU;With memory 4000, above-mentioned input equipment 1000, output
Equipment 2000, processor 3000 and memory 4000 are connected by bus 5000.
Wherein, above-mentioned input equipment 1000 concretely touch panel, physical button or mouse.
Above-mentioned output equipment 2000 concretely display screen.
Above-mentioned memory 4000 can be high-speed RAM memory or nonvolatile storage (non-volatile
), such as magnetic disk storage memory.Above-mentioned memory 4000 is above-mentioned input equipment 1000, defeated for storing batch processing code
Go out equipment 2000 and processor 3000 is used to call the program code stored in memory 4000, perform following operation:
Above-mentioned processor 3000, is used for:
Obtain pending image;
Face datection is carried out to the pending image, obtains M facial images, the M is positive integer;
The M facial images are screened, obtain N facial images, the N is whole less than or equal to the M
Number;
The N facial images are uploaded to server.
Optionally, above-mentioned processor 3000 screens the M facial images, including:
The angle information of facial image i is obtained, the angle information is following at least one:Horizontally rotate angle, pitching
Angle and gradient, the facial image i are any facial image in the M facial images;
The angle information of the facial image i is compared with predetermined angle information, in the angle of the facial image i
When information compares successfully with the predetermined angle information, retain the facial image i.
Optionally, above-mentioned processor 3000 screens the M facial images, obtains N facial images, including:
The image that human face region is not blocked in the M facial images is filtered out, obtains K facial images, the K is
Positive integer;
Image quality evaluation is carried out to the K facial images, obtains the K image quality evaluation values;
The image quality evaluation values more than predetermined threshold value are chosen from the K image quality evaluation values, are obtained described N number of
Image quality evaluation values obtain the corresponding N facial image of the N number of image quality evaluation values.
Optionally, above-mentioned processor 3000 uploads onto the server the N facial images, including:
The N facial images are compressed, obtain the N first object facial images;
The N first object facial images and its corresponding attribute information are uploaded into the server.
Optionally, above-mentioned processor 3000 screens the M facial images described, obtains N facial images
Afterwards, also particularly useful for:
Image enhancement processing is carried out to the N facial images;
It is described that the N facial images are uploaded to server, including:
The N after image enhancement facial images are uploaded to the server.
The embodiment of the present invention also provides a kind of computer storage media, wherein, which can be stored with journey
Sequence, the part or all of step of any image processing method when which performs described in including above method embodiment
Suddenly.
Although combining each embodiment herein, invention has been described, however, implementing the present invention for required protection
In the process, those skilled in the art are by checking the attached drawing, disclosure and the appended claims, it will be appreciated that and it is real
Other variations of the existing open embodiment.In the claims, " comprising " (comprising) word is not excluded for other compositions
Part or step, "a" or "an" are not excluded for multiple situations.Single processor or other units can realize claim
In several functions enumerating.Mutually different has been recited in mutually different dependent some measures, it is not intended that these are arranged
It applies to combine and generates good effect.
It will be understood by those skilled in the art that the embodiment of the present invention can be provided as method, apparatus (equipment) or computer journey
Sequence product.Therefore, in terms of the present invention can be used complete hardware embodiment, complete software embodiment or combine software and hardware
The form of embodiment.Moreover, the calculating for wherein including computer usable program code in one or more can be used in the present invention
The computer program that machine usable storage medium is implemented on (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.Computer program is stored/distributed in suitable medium, is provided together with other hardware or one as hardware
Part can also use other distribution forms, such as pass through the wired or wireless telecommunication systems of Internet or other.
The present invention be with reference to the embodiment of the present invention method, apparatus (equipment) and computer program product flow chart with/
Or block diagram describes.It should be understood that can by computer program instructions realize flowchart and/or the block diagram in each flow and/
Or the flow in box and flowchart and/or the block diagram and/or the combination of box.These computer program instructions can be provided
To the processor of all-purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to generate one
A machine so that the instruction generation performed by computer or the processor of other programmable data processing devices is used to implement
The device for the function of being specified in one flow of flow chart or multiple flows and/or one box of block diagram or multiple boxes.
These computer program instructions, which may also be stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction generation being stored in the computer-readable memory includes referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one box of block diagram or
The function of being specified in multiple boxes.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that counted
Series of operation steps is performed on calculation machine or other programmable devices to generate computer implemented processing, so as in computer or
The instruction offer performed on other programmable devices is used to implement in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although with reference to specific features and embodiment, invention has been described, it is clear that, do not departing from this hair
In the case of bright spirit and scope, it can be carry out various modifications and combined.Correspondingly, the specification and drawings are only institute
The exemplary illustration for the present invention that attached claim is defined, and be considered as covered in the scope of the invention arbitrary and all and repair
Change, change, combining or equivalent.Obviously, those skilled in the art various changes and modifications can be made to the invention without
Depart from the spirit and scope of the present invention.If in this way, these modifications and changes of the present invention belong to the claims in the present invention and its
Within the scope of equivalent technologies, then the present invention is also intended to comprising including these modification and variations.
Claims (6)
1. a kind of image processing method, which is characterized in that including:
Pending image is obtained, the pending image is any image of camera shooting;
Face datection is carried out to the pending image, obtains M facial images, the M is positive integer;
The M facial images are screened, obtain N facial images, the N is the integer less than or equal to the M;
The N facial images are uploaded to server;
It is described that the N facial images are uploaded onto the server, including:
The size of the N facial images is adjusted to consistent, and the N after adjustment facial images are compressed, is obtained
To the N first object facial images;
The N first object facial images and its corresponding attribute information are uploaded into the server, the attribute information
For personage's characteristic attribute, the character features attribute is at least one of following:Personage's number, character positions, personage's angle;
Wherein, it is described that the M facial images are screened, including:
The angle information of facial image i is obtained, the angle information includes:Horizontally rotate angle, pitch angle and gradient, it is described
Facial image i is any facial image in the M facial images;
The angle information of the facial image i is compared with predetermined angle information, in the angle information of the facial image i
When being compared successfully with the predetermined angle information, retain the facial image i, the predetermined angle information is:Horizontally rotate angle
It is ± 20 ° to spend for ± 30 °, pitch angle, inclination angle is ± 45 °.
2. according to the method described in claim 1, it is characterized in that, described screen the M facial images, N is obtained
Facial image is opened, including:
The image that human face region is not blocked in the M facial images is filtered out, obtains K facial images, the K is just whole
Number;
Image quality evaluation is carried out to the K facial images, obtains the K image quality evaluation values;
The image quality evaluation values more than predetermined threshold value are chosen from the K image quality evaluation values, obtain N number of image
Quality evaluation value obtains the corresponding N facial image of the N number of image quality evaluation values.
3. according to 1 or 2 any one of them method of claim, which is characterized in that the M facial images are carried out described
Screening, after obtaining N facial images, the method further includes:
Image enhancement processing is carried out to the N facial images;
It is described that the N facial images are uploaded to server, including:
The N after image enhancement facial images are uploaded to the server.
4. a kind of image processing apparatus, which is characterized in that including:
Acquiring unit, for obtaining pending image, the pending image is any image of camera shooting;
Detection unit for carrying out Face datection to the pending image, obtains M facial images, and the M is positive integer;
Screening unit for being screened to the M facial images, obtains N facial images, the N be less than or equal to
The integer of the M;
Uploading unit, for the N facial images to be uploaded to server;
Described device is additionally operable to:The size of the N facial images is adjusted to consistent;
Wherein, the uploading unit includes:
Compression module is compressed for the N facial images after adjusting, obtains the N first object face figures
Picture;
Uploading module, for the N first object facial images and its corresponding attribute information to be uploaded to the server,
The attribute information is personage's characteristic attribute, and the character features attribute is at least one of following:Personage's number, character positions,
Personage's angle;
Wherein, the screening unit includes:
Acquisition module, for obtaining the angle information of facial image i, the angle information includes:Horizontally rotate angle, pitch angle
And gradient, the facial image i are any facial image in the M facial images;
Comparing module, for the angle information of the facial image i to be compared with predetermined angle information, in the face figure
When being compared successfully as the angle information of i with the predetermined angle information, retain the facial image i, the predetermined angle information
For:Horizontally rotate that angle is ± 30 °, pitch angle is ± 20 °, inclination angle is ± 45 °.
5. image processing apparatus according to claim 4, which is characterized in that the screening unit includes:
Screening module for filtering out the image that human face region is not blocked in the M facial images, obtains K face figures
Picture, the K are positive integer;
Evaluation module for carrying out image quality evaluation to the K facial images, obtains the K image quality evaluation values;
Module is chosen, for choosing the image quality evaluation values more than predetermined threshold value from the K image quality evaluation values, is obtained
To N number of image quality evaluation values, the corresponding N facial image of the N number of image quality evaluation values is obtained.
6. any one of them image processing apparatus according to claim 4 or 5, which is characterized in that described image processing unit is also
Including:
Processing unit, for being screened in the screening unit to the M facial images, after obtaining N facial images,
Image enhancement processing is carried out to the N facial images;
The uploading unit is specifically used for:
The N after image enhancement facial images are uploaded to the server.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611210672.0A CN106778645B (en) | 2016-12-24 | 2016-12-24 | A kind of image processing method and device |
PCT/CN2017/114856 WO2018113523A1 (en) | 2016-12-24 | 2017-12-06 | Image processing method and device, and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611210672.0A CN106778645B (en) | 2016-12-24 | 2016-12-24 | A kind of image processing method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106778645A CN106778645A (en) | 2017-05-31 |
CN106778645B true CN106778645B (en) | 2018-05-18 |
Family
ID=58920464
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611210672.0A Active CN106778645B (en) | 2016-12-24 | 2016-12-24 | A kind of image processing method and device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106778645B (en) |
WO (1) | WO2018113523A1 (en) |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106778645B (en) * | 2016-12-24 | 2018-05-18 | 深圳云天励飞技术有限公司 | A kind of image processing method and device |
CN108875512B (en) * | 2017-12-05 | 2021-04-23 | 北京旷视科技有限公司 | Face recognition method, device, system, storage medium and electronic equipment |
CN108764149B (en) * | 2018-05-29 | 2022-02-18 | 北京中庆现代技术股份有限公司 | Training method for class student face model |
CN109101646B (en) * | 2018-08-21 | 2020-12-18 | 北京深瞐科技有限公司 | Data processing method, device, system and computer readable medium |
CN111199165B (en) * | 2018-10-31 | 2024-02-06 | 浙江宇视科技有限公司 | Image processing method and device |
CN111488768B (en) * | 2019-01-28 | 2023-09-05 | 百度在线网络技术(北京)有限公司 | Style conversion method and device for face image, electronic equipment and storage medium |
CN112860923B (en) * | 2019-11-27 | 2024-03-22 | 深圳云天励飞技术有限公司 | Image archiving method and related product |
CN111368688A (en) * | 2020-02-28 | 2020-07-03 | 深圳市商汤科技有限公司 | Pedestrian monitoring method and related product |
CN112102623A (en) * | 2020-08-24 | 2020-12-18 | 深圳云天励飞技术股份有限公司 | Traffic violation identification method and device and intelligent wearable device |
CN111967436B (en) * | 2020-09-02 | 2024-03-19 | 北京猿力未来科技有限公司 | Image processing method and device |
CN112347849B (en) * | 2020-09-29 | 2024-03-26 | 咪咕视讯科技有限公司 | Video conference processing method, electronic equipment and storage medium |
CN112269978B (en) * | 2020-10-22 | 2022-11-15 | 蚂蚁胜信(上海)信息技术有限公司 | Image acquisition method and device |
CN112785550A (en) * | 2020-12-29 | 2021-05-11 | 浙江大华技术股份有限公司 | Image quality value determination method, image quality value determination device, storage medium, and electronic device |
CN115953327B (en) * | 2023-03-09 | 2023-09-12 | 极限人工智能有限公司 | Image enhancement method, system, readable storage medium and electronic equipment |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105654043A (en) * | 2015-12-24 | 2016-06-08 | 广东欧珀移动通信有限公司 | Control method, control device and photographing system |
CN106127106A (en) * | 2016-06-13 | 2016-11-16 | 东软集团股份有限公司 | Target person lookup method and device in video |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20090101733A (en) * | 2008-03-24 | 2009-09-29 | 삼성전자주식회사 | Mobile terminal and displaying method of display information using face recognition thereof |
CN101546377A (en) * | 2009-04-28 | 2009-09-30 | 上海银晨智能识别科技有限公司 | Human face image capture system and human face image capture method |
CN102799877A (en) * | 2012-09-11 | 2012-11-28 | 上海中原电子技术工程有限公司 | Method and system for screening face images |
CN105138954B (en) * | 2015-07-12 | 2019-06-04 | 上海微桥电子科技有限公司 | A kind of image automatic screening inquiry identifying system |
CN105243638B (en) * | 2015-09-25 | 2019-11-15 | 腾讯科技(深圳)有限公司 | A kind of method and apparatus uploading image |
CN106778645B (en) * | 2016-12-24 | 2018-05-18 | 深圳云天励飞技术有限公司 | A kind of image processing method and device |
-
2016
- 2016-12-24 CN CN201611210672.0A patent/CN106778645B/en active Active
-
2017
- 2017-12-06 WO PCT/CN2017/114856 patent/WO2018113523A1/en active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105654043A (en) * | 2015-12-24 | 2016-06-08 | 广东欧珀移动通信有限公司 | Control method, control device and photographing system |
CN106127106A (en) * | 2016-06-13 | 2016-11-16 | 东软集团股份有限公司 | Target person lookup method and device in video |
Also Published As
Publication number | Publication date |
---|---|
WO2018113523A1 (en) | 2018-06-28 |
CN106778645A (en) | 2017-05-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106778645B (en) | A kind of image processing method and device | |
CN106878670B (en) | A kind of method for processing video frequency and device | |
CN107358146B (en) | Method for processing video frequency, device and storage medium | |
US8750573B2 (en) | Hand gesture detection | |
CN107291810B (en) | Data processing method, device and storage medium | |
US8792722B2 (en) | Hand gesture detection | |
US9104914B1 (en) | Object detection with false positive filtering | |
CN106791655B (en) | A kind of method for processing video frequency and device | |
CN104123544B (en) | Anomaly detection method and system based on video analysis | |
Othman et al. | A new IoT combined body detection of people by using computer vision for security application | |
CN109766779A (en) | It hovers personal identification method and Related product | |
US6774905B2 (en) | Image data processing | |
CN107169458B (en) | Data processing method, device and storage medium | |
CN107341443B (en) | Method for processing video frequency, device and storage medium | |
CN106791708B (en) | A kind of method for processing video frequency and device | |
CN108416256A (en) | The family's cloud intelligent monitor system and monitoring method of feature based identification | |
CN109815843A (en) | Object detection method and Related product | |
CN109740444A (en) | Flow of the people information displaying method and Related product | |
US10373015B2 (en) | System and method of detecting moving objects | |
CN106851199A (en) | A kind of method for processing video frequency and device | |
CN106971142B (en) | A kind of image processing method and device | |
CN102892007A (en) | Method and system for facilitating color balance synchronization between a plurality of video cameras as well as method and system for obtaining object tracking between two or more video cameras | |
CN106937087A (en) | A kind of method for processing video frequency and device | |
CN106657913B (en) | A kind of method for processing video frequency and device | |
CN107103299A (en) | A kind of demographic method in monitor video |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |