CN109785343A - Face based on clarity scratches the preferred method and device of figure picture - Google Patents
Face based on clarity scratches the preferred method and device of figure picture Download PDFInfo
- Publication number
- CN109785343A CN109785343A CN201910043316.1A CN201910043316A CN109785343A CN 109785343 A CN109785343 A CN 109785343A CN 201910043316 A CN201910043316 A CN 201910043316A CN 109785343 A CN109785343 A CN 109785343A
- Authority
- CN
- China
- Prior art keywords
- scoring
- face
- clarity
- picture
- noise
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses preferred method and device that a kind of face based on clarity scratches figure picture, wherein this method comprises: the video original image to sequence of frames of video carries out Face datection, obtains face picture；Clarity detection is carried out to face picture and calculates clarity scoring, noise detection is carried out to face picture and calculates noise scoring, and the scoring of face area is calculated according to the face area and video artwork area of face picture；Lighting scoring is carried out to clarity scoring and noise scoring respectively to calculate, and obtains clarity lighting scoring and noise lighting scoring, and face overall score is calculated according to the scoring of clarity lighting scoring, noise lighting scoring and face area；It determines to capture and is spaced the highest face picture of interior overall score, and face picture is carried out to scratch figure.Technical solution of the present invention can select the face picture more less than more visible, noise, be able to ascend stingy figure picture effect.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of face based on clarity to scratch the preferred of figure picture
Method, apparatus, terminal and storage medium.
Background technique
It is monitoring or is capturing in video, generalling use the stingy diagram technology of face and pluck out face figure from the image of sequence of frames of video
Piece.When night-time scene scratches figure to monitor video progress face snap, the picture that can usually encounter the stingy figure result of face compares mould
It pastes, the problem more than noise.But having part face in the face in video is than more visible, and noise is fewer.In order to improve people
Face scratches figure effect, preferably goes out than more visible, the fewer face picture of noise becomes industry urgent problem to be solved.
In view of this, it is necessary to propose that scratching diagram technology to current face is further improved.
Summary of the invention
To solve an above-mentioned at least technical problem, it is stingy that the main object of the present invention is to provide a kind of face based on clarity
Preferred method, device, terminal and the storage medium of figure picture.
To achieve the above object, a technical solution adopted by the present invention are as follows: it is stingy to provide a kind of face based on clarity
The preferred method of figure picture, comprising:
Face datection is carried out to the video original image of sequence of frames of video, obtains face picture；
Clarity detection is carried out to face picture and calculates clarity scoring, noise detection is carried out to face picture and is counted
Noise scoring is calculated, and the scoring of face area is calculated according to the face area and video artwork area of face picture；
Lighting scoring is carried out to clarity scoring and noise scoring respectively to calculate, and obtains clarity lighting scoring and noise point
Lamp scoring, and face overall score is calculated according to the scoring of clarity lighting scoring, noise lighting scoring and face area；
It determines to capture and is spaced the highest face picture of interior overall score, and face picture is carried out to scratch figure.
It is wherein, described that clarity detection is carried out to face picture and calculates clarity scoring, comprising:
Face picture is converted to grayscale image and only retains Y-component；
Convolutional filtering processing is carried out to grayscale image using Laplace operator, and is normalized to 0-255；
Calculate the mean and variance of grayscale image；
The scoring of face picture clarity is calculated according to variance.
It is wherein, described that noise detection is carried out to face picture and calculates noise scoring, comprising:
Face picture is converted to the picture of BGR format；
Calculate the mean value and standard deviation of the picture of face BGR format；
Using mean value as signal, standard deviation is noise, and the ratio of signal and noise is shown that face picture noise scores.
Wherein, the video original image to sequence of frames of video carries out Face datection, obtains face picture, comprising:
Face datection is carried out to the video original image of sequence of frames of video, obtains multiple face frame coordinates；
Face picture is plucked out from video original image according to multiple face frame coordinates.
Wherein, the face area according to face picture and video artwork area calculate the scoring of face area, comprising:
Face width and height are calculated according to face frame coordinate, obtains the face area of face picture；And
It scores using face area and the ratio of video artwork area as face area.
Wherein, described that lighting scoring calculating is carried out to clarity scoring and noise scoring respectively, it obtains clarity lighting and comments
Divide and noise lighting scored, comprising:
If clarity scoring is less than the first refusal threshold value, clarity lighting scoring is 0；If clarity scoring is big
When the first acceptance threshold, then clarity lighting scoring is 100；If clarity scoring is less than or equal to the first acceptance threshold and big
In being equal to the first refusal threshold value, then clarity lighting scoring is 1；
If noise scoring is less than the second refusal threshold value, noise lighting scoring is 0；If noise scoring is greater than second
When acceptance threshold, then noise lighting scoring is 100；If noise scoring is less than or equal to the second acceptance threshold and is more than or equal to second
Refuse threshold value, then noise lighting scoring is 1.
Wherein, described that face general comment is calculated according to the scoring of clarity lighting scoring, noise lighting scoring and face area
Point, comprising:
Face general comment is divided into the sum of a* clarity lighting scoring, a* noise lighting scoring and b* face area scoring three,
Wherein, a is lighting scoring coefficient, and b is face partition coefficient, a=100, b=100.
To achieve the above object, two technical solutions that the present invention uses are as follows: it is stingy to provide a kind of face based on clarity
The preferred embodiment of figure picture, comprising:
Face detection module carries out Face datection for the video original image to sequence of frames of video, obtains face picture；
Computing module, for face picture carry out clarity detection and calculate clarity scoring, to face picture into
Row noise detects and calculates noise scoring, and calculates face according to the face area and video artwork area of face picture
Area scoring；
Statistical module calculates for carrying out lighting scoring to clarity scoring and noise scoring respectively, obtains clarity point
Lamp scoring and noise lighting scoring, and calculated according to the scoring of clarity lighting scoring, noise lighting scoring and face area
Face overall score；
Determining module is spaced the highest face picture of interior overall score for determining to capture, and carries out scratching figure to face picture.
To achieve the above object, the third technical solution that the present invention uses are as follows: a kind of terminal is provided, including memory,
Processor and storage are on a memory and the program that can run on a processor, which is characterized in that described in the processor execution
The step of above method is realized when program.
To achieve the above object, the 4th technical solution that the present invention uses are as follows: provide a kind of readable storage medium storing program for executing, thereon
The step of being stored with program, above-mentioned method realized when described program is executed by processor.
Technical solution of the present invention mainly using first Face datection is carried out to the video original image of sequence of frames of video, obtains face
Picture；Then clarity detection is carried out to face picture and calculates clarity scoring, noise detection is carried out simultaneously to face picture
Noise scoring is calculated, and the scoring of face area is calculated according to the face area and video artwork area of face picture；?
Lighting scoring is carried out to clarity scoring and noise scoring respectively to calculate, and obtains clarity lighting scoring and noise lighting scoring,
And face overall score is calculated according to the scoring of clarity lighting scoring, noise lighting scoring and face area；Finally determination is grabbed
Clap overall score highest face picture in being spaced, and face picture carried out to scratch figure, it is preferable to select definition effect, noise compared with
Few face picture is able to ascend stingy figure picture effect.
Detailed description of the invention
Fig. 1 is the method flow diagram for the preferred method that one embodiment of the invention scratches figure picture based on the face of clarity；
Fig. 2 is the block diagram for the preferred embodiment that one embodiment of the invention scratches figure picture based on the face of clarity；
Fig. 3 is the internal structure chart of one embodiment of the invention terminal.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiment is only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
His embodiment, shall fall within the protection scope of the present invention.
It is to be appreciated that the description of " first ", " second " involved in the present invention etc. is used for description purposes only, and should not be understood as
Its relative importance of indication or suggestion or the quantity for implicitly indicating indicated technical characteristic.Define as a result, " first ",
The feature of " second " can explicitly or implicitly include at least one of the features.In addition, the technical side between each embodiment
Case can be combined with each other, but must be based on can be realized by those of ordinary skill in the art, when the combination of technical solution
Conflicting or cannot achieve when occur will be understood that the combination of this technical solution is not present, also not the present invention claims guarantor
Within the scope of shield.
Fig. 1 is please referred to, Fig. 1 is the method for the preferred method that one embodiment of the invention scratches figure picture based on the face of clarity
Flow chart.In embodiments of the present invention, the preferred method of figure picture should be scratched based on the face of clarity, comprising:
Step S10, Face datection is carried out to the video original image of sequence of frames of video, obtains face picture；
Step S20, clarity detection is carried out to face picture and calculates clarity scoring, noise is carried out to face picture
It detects and calculates noise scoring, and face area is calculated with video artwork area according to the face area of face picture and is commented
Point；
Step S30, lighting scoring is carried out to clarity scoring and noise scoring respectively to calculate, obtain clarity lighting scoring
And noise lighting scoring, and to calculate face total according to the scoring of clarity lighting scoring, noise lighting scoring and face area
Scoring；
Step S40, it determines to capture and is spaced the highest face picture of interior overall score, and face picture is carried out to scratch figure.
Sequence of frames of video in the present embodiment is thought on hi3559 platform captured by camera based on sea, the lattice of video frame
Formula is NV21, video resolution 960*540.Have plurality of pictures in one sequence of frames of video, each video original image be both needed into
Row Face datection obtains multiple face frame coordinates.Later further according to face frame coordinate from the 960*540 original image of the NV21 of video
Deduct face picture, data format NV21.Then the clarity of face picture and noise are detected, obtain clarity and
Noise scoring；And face area is calculated according to face frame coordinate, and calculate according to face area and video artwork area
The scoring of face area.Clarity scoring can be distinguished using lighting algorithm and noise scoring carries out lighting scoring and calculates, and obtained clear
Clear degree lighting scoring and noise lighting scoring, and according to clarity lighting scoring, noise lighting scoring and face areal calculation
Face overall score out.It determines to capture and is spaced the highest face picture of interior overall score, and face picture is carried out to scratch figure.
Technical solution of the present invention mainly using first Face datection is carried out to the video original image of sequence of frames of video, obtains face
Picture；Then clarity detection is carried out to face picture and calculates clarity scoring, noise detection is carried out simultaneously to face picture
Noise scoring is calculated, and the scoring of face area is calculated according to the face area and video artwork area of face picture；?
Lighting scoring is carried out to clarity scoring and noise scoring respectively to calculate, and obtains clarity lighting scoring and noise lighting scoring,
And face overall score is calculated according to the scoring of clarity lighting scoring, noise lighting scoring and face area；Finally determination is grabbed
Clap overall score highest face picture in being spaced, and face picture carried out to scratch figure, it is preferable to select definition effect, noise compared with
Few face picture is able to ascend stingy figure picture effect.
It is described that clarity detection is carried out to face picture and calculates clarity scoring in a specific embodiment,
Include:
Face picture is converted to grayscale image and only retains Y-component；
Convolutional filtering processing is carried out to grayscale image using Laplace operator, and is normalized to 0-255；
Calculate the mean and variance of grayscale image；
The scoring of face picture clarity is calculated according to variance.
In the present embodiment, face picture format is NV21, removes U, V component data, only retains Y-component.Grayscale image utilizes
The Laplce of 3*3, which calculates, carries out convolutional filtering processing, and is normalized to 0-255.Laplace operator convolutional filtering can be used out
Source library opencv included function is realized:
Laplacian (gray1, gray1, CV_16S, 3): grayscale image is normalized to 0-255 also, open source library can be used
Opencv included function realizes convertScaleAbs (gray1, gray1).Calculate the mean value and variance of grayscale image.Mean value
For the average value of all Y-components.Variance is σ2, the specific formula for calculation of variance is as follows:
σ2For population variance, X is variable, and μ is population mean, and N is sample format.Above-mentioned X is Y-component.Variance is removed
It scores using 10000 as face picture clarity.If clarity scoring is greater than 1, allows it to be equal to 1, clarity is scored
As a result it is normalized to 0-1.
It is described that noise detection is carried out to face picture and calculates noise scoring in a specific embodiment, comprising:
Face picture is converted to the picture of BGR format；
Calculate the mean value and standard deviation of the picture of face BGR format；
Using mean value as signal, standard deviation is noise, and the ratio of signal and noise is shown that face picture noise scores.
In the present embodiment, face picture format is NV21, and the format can be directly translated into corresponding BGR lattice by conversion
After formula picture, the mean value and standard deviation of the picture of face BGR format are calculated；Mean value and standard deviation, the standard deviation are the calculation of variance
Art square root can calculate corresponding mean value and standard deviation accordingly；It then, will using standard deviation as noise using mean value as signal
Mean value/standard deviation scores as face picture noise, and noise is scored divided by 10, if it is greater than 1, it is allowed to be equal to 1, will
Noise appraisal result is normalized to 0-1.
In a specific embodiment, the video original image to sequence of frames of video carries out Face datection, obtains face figure
Piece, comprising:
Face datection is carried out to the video original image of sequence of frames of video, obtains multiple face frame coordinates；
Face picture is plucked out from video original image according to multiple face frame coordinates.
In the present embodiment, face frame coordinate is 4, and 4, face frame coordinate surrounds rectangle, to facilitate from video original image
In pluck out rectangle face picture.
In a specific embodiment, the face area according to face picture and video artwork area calculate face
Area scoring, comprising:
Face width and height are calculated according to face frame coordinate, obtains the face area of face picture；And
It scores using face area and the ratio of video artwork area as face area.
In the present embodiment, the width and height of face picture can be calculated according to face frame coordinate, and then pass through width
With highly find out face area, the ratio of the face area found out and video artwork area is as the scoring of face area.
In a specific embodiment, described that lighting scoring calculating is carried out to clarity scoring and noise scoring respectively, it obtains
It scores to clarity lighting scoring and noise lighting, comprising:
If clarity scoring is less than the first refusal threshold value, clarity lighting scoring is 0；If clarity scoring is big
When the first acceptance threshold, then clarity lighting scoring is 100；If clarity scoring is less than or equal to the first acceptance threshold and big
In being equal to the first refusal threshold value, then clarity lighting scoring is 1；
If noise scoring is less than the second refusal threshold value, noise lighting scoring is 0；If noise scoring is greater than second
When acceptance threshold, then noise lighting scoring is 100；If noise scoring is less than or equal to the second acceptance threshold and is more than or equal to second
Refuse threshold value, then noise lighting scoring is 1.
In the present embodiment, clarity scoring is calculated, after noise scoring, this 2 scorings is given to lighting algoritic module and calculates
Clarity lighting scoring and noise lighting scoring out, specifically, calculating clarity lighting scoring: if clarity scoring is less than the
When one refusal threshold value (0.1), then clarity lighting scoring is 0；If clarity scoring is greater than the first acceptance threshold (0.4),
Then clarity lighting scoring is 100；If clarity scoring is less than or equal to the first acceptance threshold (0.4), and is more than or equal to first
Refuse threshold value (0.1), then allowing clarity lighting scoring is 1.First acceptance threshold and the first refusal threshold value can be according to actual
It is required that design.Calculate noise lighting scoring: if noise scoring is less than the second refusal threshold value (0.07), noise lighting is commented
It is divided into 0；If noise scoring is greater than the second acceptance threshold (0.1), noise lighting scoring is 100；If noise scoring is small
In refusing threshold value (0.07) equal to the second acceptance threshold (0.1), and more than or equal to second, then noise lighting scoring is 1.
In a specific embodiment, described scored according to clarity lighting scoring, noise lighting scoring and face area is counted
Calculate face overall score, comprising:
Face general comment is divided into the sum of a* clarity lighting scoring, a* noise lighting scoring and b* face area scoring three,
Wherein, a is lighting scoring coefficient, and b is face partition coefficient, a=100, b=100.
In the present embodiment, face overall score=a* (clarity lighting scoring+noise lighting scoring)+b* face area is commented
Point.The specific value of lighting points-scoring system a and face partition coefficient b can be designed with actual requirement.
Referring to figure 2., Fig. 2 is the module for the preferred embodiment that one embodiment of the invention scratches figure picture based on the face of clarity
Block diagram.In an embodiment of the present invention, the preferred embodiment of figure picture should be scratched based on the face of clarity, comprising:
Face detection module 10 carries out Face datection for the video original image to sequence of frames of video, obtains face picture；
Computing module 20, for carrying out clarity detection to face picture and calculating clarity scoring, to face picture
It carries out noise detection and calculates noise scoring, and people is calculated according to the face area and video artwork area of face picture
Face product scoring；
Statistical module 30 calculates for carrying out lighting scoring to clarity scoring and noise scoring respectively, obtains clarity
Lighting scoring and noise lighting scoring, and scored and calculated according to clarity lighting scoring, noise lighting scoring and face area
Face overall score out；
Determining module 40 is spaced the highest face picture of interior overall score for determining to capture, and carries out to face picture stingy
Figure.
In the present embodiment, sequence of frames of video is thought on hi3559 platform captured by camera based on sea, the lattice of video frame
Formula is NV21, video resolution 960*540.Have plurality of pictures in one sequence of frames of video, each video original image be both needed to through
It crosses face detection module 10 and carries out Face datection, obtain multiple face frame coordinates.Later further according to face frame coordinate from video
Face picture, data format NV21 are deducted in the 960*540 original image of NV21.Using computing module 20 to the clear of face picture
Degree and noise are detected, and clarity and noise scoring are obtained；And face area is calculated according to face frame coordinate, and according to
Face area and video artwork area calculate the scoring of face area.Statistical module 30, can be clear respectively using lighting algorithm
Degree scoring and noise scoring carry out lighting scoring and calculate, and obtain clarity lighting scoring and noise lighting scoring, and according to clear
Clear degree lighting scoring, noise lighting scoring and face areal calculation go out face overall score.Finally, being determined using determining module 40
The highest face picture of overall score in being spaced is captured, and face picture is carried out to scratch figure, so, it is possible to ensure that night scratches figure result
Clearly, noise is few, is able to ascend stingy figure effect.
Referring to figure 3., Fig. 3 is the internal structure chart of one embodiment of the invention terminal.In one embodiment, which includes
Processor, memory and the network interface connected by system bus.Wherein, the processor of the terminal is calculated and is controlled for providing
Ability processed.The memory of the terminal includes non-volatile memory medium, built-in storage.The non-volatile memory medium is stored with behaviour
Make system, program and database.The built-in storage provides for the operation of operating system and program in non-volatile memory medium
Environment.The network interface of the terminal is used to communicate with external terminal by network connection.When the program is executed by processor with
Realize that a kind of face based on clarity scratches the preferred method of figure picture.
It will be understood by those skilled in the art that structure shown in Fig. 3, only part relevant to application scheme is tied
The block diagram of structure, does not constitute the restriction for the terminal being applied thereon to application scheme, and specific terminal may include than figure
Shown in more or fewer components, perhaps combine certain components or with different component layouts.
In one embodiment, a kind of terminal is provided, including memory, processor and storage are on a memory and can be
The program run on processor, processor realize the step in above each embodiment of the method when executing program.
In one embodiment, a kind of readable storage medium storing program for executing is provided, program is stored thereon with, program is executed by processor
Step in each embodiment of the method for Shi Shixian or more.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by program, the program can be stored in a non-volatile readable and take in storage medium,
The program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, in each embodiment provided herein
Used any reference to memory, storage, database or other media, may each comprise non-volatile and/or volatibility
Memory.Nonvolatile memory may include read-only memory (ROM), programming ROM (PROM), electrically programmable ROM
(EPROM), electrically erasable ROM (EEPROM) or flash memory.Volatile memory may include random access memory (RAM)
Or external cache.By way of illustration and not limitation, RAM is available in many forms, such as static state RAM (SRAM),
It is dynamic ram (DRAM), synchronous dram (SDRAM), double data rate sdram (DDRSDRAM), enhanced SDRAM (ESDRAM), same
Walk link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) directly RAM (RDRAM), direct memory bus
Dynamic ram (DRDRAM) and memory bus dynamic ram (RDRAM) etc..
The above description is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all at this
Under the inventive concept of invention, using equivalent structure transformation made by description of the invention and accompanying drawing content, or directly/use indirectly
It is included in other related technical areas in scope of patent protection of the invention.
Claims (10)
1. the preferred method that a kind of face based on clarity scratches figure picture, which is characterized in that the face based on clarity
Scratch the preferred method of figure picture, comprising:
Face datection is carried out to the video original image of sequence of frames of video, obtains face picture；
Clarity detection is carried out to face picture and calculates clarity scoring, noise detection is carried out to face picture and is calculated
Noise scoring, and the scoring of face area is calculated according to the face area and video artwork area of face picture；
Lighting scoring is carried out to clarity scoring and noise scoring respectively to calculate, and obtains clarity lighting scoring and noise lighting is commented
Point, and face overall score is calculated according to the scoring of clarity lighting scoring, noise lighting scoring and face area；
It determines to capture and is spaced the highest face picture of interior overall score, and face picture is carried out to scratch figure.
2. the face based on clarity scratches the preferred method of figure picture as described in claim 1, which is characterized in that described to people
Face picture carries out clarity detection and calculates clarity scoring, comprising:
Face picture is converted to grayscale image and only retains Y-component；
Convolutional filtering processing is carried out to grayscale image using Laplace operator, and is normalized to 0-255；
Calculate the mean and variance of grayscale image；
The scoring of face picture clarity is calculated according to variance.
3. the face based on clarity scratches the preferred method of figure picture as described in claim 1, which is characterized in that described to people
Face picture carries out noise detection and calculates noise scoring, comprising:
Face picture is converted to the picture of BGR format；
Calculate the mean value and standard deviation of the picture of face BGR format；
Using mean value as signal, standard deviation is noise, and the ratio of signal and noise is shown that face picture noise scores.
4. the face based on clarity scratches the preferred method of figure picture as described in claim 1, which is characterized in that described pair of view
The video original image of frequency frame sequence carries out Face datection, obtains face picture, comprising:
Face datection is carried out to the video original image of sequence of frames of video, obtains multiple face frame coordinates；
Face picture is plucked out from video original image according to multiple face frame coordinates.
5. the face based on clarity scratches the preferred method of figure picture as claimed in claim 4, which is characterized in that the basis
The face area and video artwork area of face picture calculate the scoring of face area, comprising:
Face width and height are calculated according to face frame coordinate, obtains the face area of face picture；And
It scores using face area and the ratio of video artwork area as face area.
6. the face based on clarity scratches the preferred method of figure picture as claimed in claim 4, which is characterized in that the difference
Lighting scoring is carried out to clarity scoring and noise scoring to calculate, and obtains clarity lighting scoring and noise lighting scoring, comprising:
If clarity scoring is less than the first refusal threshold value, clarity lighting scoring is 0；If clarity scoring is greater than the
When one acceptance threshold, then clarity lighting scoring is 100；If clarity scoring be less than or equal to the first acceptance threshold and be greater than etc.
Refuse threshold value in first, then clarity lighting scoring is 1；
If noise scoring is less than the second refusal threshold value, noise lighting scoring is 0；Receive if noise scoring is greater than second
When threshold value, then noise lighting scoring is 100；If noise scoring is less than or equal to the second acceptance threshold and is more than or equal to the second refusal
Threshold value, then noise lighting scoring is 1.
7. the face based on clarity scratches the preferred method of figure picture as claimed in claim 6, which is characterized in that the basis
Clarity lighting scoring, noise lighting scoring and the scoring of face area calculate face overall score, comprising:
Face general comment is divided into the sum of a* clarity lighting scoring, a* noise lighting scoring and b* face area scoring three,
Wherein, a is lighting scoring coefficient, and b is face partition coefficient, a=100, b=100.
8. the preferred embodiment that a kind of face based on clarity scratches figure picture, which is characterized in that the face based on clarity
Scratch the preferred embodiment of figure picture, comprising:
Face detection module carries out Face datection for the video original image to sequence of frames of video, obtains face picture；
Computing module makes an uproar to face picture for carrying out clarity detection to face picture and calculating clarity scoring
Point detects and calculates noise scoring, and calculates face area according to the face area and video artwork area of face picture
Scoring；
Statistical module calculates for carrying out lighting scoring to clarity scoring and noise scoring respectively, obtains clarity lighting and comment
Divide and noise lighting is scored, and face is calculated according to the scoring of clarity lighting scoring, noise lighting scoring and face area
Overall score；
Determining module is spaced the highest face picture of interior overall score for determining to capture, and carries out scratching figure to face picture.
9. a kind of terminal including memory, processor and stores the program that can be run on a memory and on a processor, special
The step of sign is, the processor realizes any one of claims 1 to 7 the method when executing described program.
10. a kind of readable storage medium storing program for executing, is stored thereon with program, which is characterized in that realization when described program is executed by processor
The step of method described in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910043316.1A CN109785343B (en) | 2019-01-17 | 2019-01-17 | Definition-based face matting picture optimization method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910043316.1A CN109785343B (en) | 2019-01-17 | 2019-01-17 | Definition-based face matting picture optimization method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109785343A true CN109785343A (en) | 2019-05-21 |
| CN109785343B CN109785343B (en) | 2021-10-19 |
Family
ID=66500877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910043316.1A Active CN109785343B (en) | 2019-01-17 | 2019-01-17 | Definition-based face matting picture optimization method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109785343B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111369531A (en) * | 2020-03-04 | 2020-07-03 | 浙江大华技术股份有限公司 | Image definition grading method, equipment and storage device |
| CN112308043A (en) * | 2020-11-26 | 2021-02-02 | 腾讯科技（深圳）有限公司 | Image processing method, image processing apparatus, and computer-readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6571000B1 (en) * | 1999-11-29 | 2003-05-27 | Xerox Corporation | Image processing algorithm for characterization of uniformity of printed images |
| US20030151674A1 (en) * | 2002-02-12 | 2003-08-14 | Qian Lin | Method and system for assessing the photo quality of a captured image in a digital still camera |
| WO2009065151A2 (en) * | 2007-11-15 | 2009-05-22 | Certifi Media Inc. | Method for image quality assessment using quality vectors |
| CN105812706A (en) * | 2016-03-17 | 2016-07-27 | 掌赢信息科技（上海）有限公司 | Video call quality evaluation method and electronic device |
| CN107590461A (en) * | 2017-09-12 | 2018-01-16 | 广东欧珀移动通信有限公司 | Face identification method and Related product |
| CN107644219A (en) * | 2017-10-10 | 2018-01-30 | 广东欧珀移动通信有限公司 | Face registration method and related product |
| CN107977639A (en) * | 2017-12-11 | 2018-05-01 | 浙江捷尚视觉科技股份有限公司 | A kind of face definition judgment method |
-
2019
- 2019-01-17 CN CN201910043316.1A patent/CN109785343B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6571000B1 (en) * | 1999-11-29 | 2003-05-27 | Xerox Corporation | Image processing algorithm for characterization of uniformity of printed images |
| US20030151674A1 (en) * | 2002-02-12 | 2003-08-14 | Qian Lin | Method and system for assessing the photo quality of a captured image in a digital still camera |
| WO2009065151A2 (en) * | 2007-11-15 | 2009-05-22 | Certifi Media Inc. | Method for image quality assessment using quality vectors |
| CN105812706A (en) * | 2016-03-17 | 2016-07-27 | 掌赢信息科技（上海）有限公司 | Video call quality evaluation method and electronic device |
| CN107590461A (en) * | 2017-09-12 | 2018-01-16 | 广东欧珀移动通信有限公司 | Face identification method and Related product |
| CN107644219A (en) * | 2017-10-10 | 2018-01-30 | 广东欧珀移动通信有限公司 | Face registration method and related product |
| CN107977639A (en) * | 2017-12-11 | 2018-05-01 | 浙江捷尚视觉科技股份有限公司 | A kind of face definition judgment method |
Non-Patent Citations (5)
| Title |
|---|
| 傅建平等: "《火炮修后水弹试验方法与检测评估技术》", 31 October 2016, 国防工业出版社 * |
| 徐德等: "《机器人视觉测量与控制》", 31 January 2016, 国防工业出版社 * |
| 杨照金等: "《工程光学计量测试技术概论》", 29 February 2016, 国防工业出版社 * |
| 潘德炉等: "《海洋水色遥感机理及反演》", 31 December 2012, 海洋出版社 * |
| 章文辉等: "《数字视频测量技术》", 30 June 2016, 中国传媒大学出版社 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111369531A (en) * | 2020-03-04 | 2020-07-03 | 浙江大华技术股份有限公司 | Image definition grading method, equipment and storage device |
| CN111369531B (en) * | 2020-03-04 | 2023-09-01 | 浙江大华技术股份有限公司 | Image definition scoring method, device and storage device |
| CN112308043A (en) * | 2020-11-26 | 2021-02-02 | 腾讯科技（深圳）有限公司 | Image processing method, image processing apparatus, and computer-readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109785343B (en) | 2021-10-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10783354B2 (en) | Facial image processing method and apparatus, and storage medium | |
| CN109146892B (en) | Image clipping method and device based on aesthetics | |
| US10719954B2 (en) | Method and electronic device for extracting a center position of an infrared spot | |
| JP6688277B2 (en) | Program, learning processing method, learning model, data structure, learning device, and object recognition device | |
| US20150093040A1 (en) | Backlight Detection Method and Device | |
| US10861128B2 (en) | Method of cropping an image, an apparatus for cropping an image, a program and a storage medium | |
| CN110619656B (en) | Face detection tracking method and device based on binocular camera and electronic equipment | |
| CN109785343A (en) | Face based on clarity scratches the preferred method and device of figure picture | |
| US20120051593A1 (en) | Apparatus and method for detecting subject from image | |
| CN113392681A (en) | Human body falling detection method and device and terminal equipment | |
| CN112135188A (en) | Video clipping method, electronic device and computer-readable storage medium | |
| CN109711390A (en) | Face scratches the preferred method and device of figure picture | |
| CN108229281B (en) | Neural network generation method, face detection device and electronic equipment | |
| CN111652140A (en) | Method, device, equipment and medium for accurately segmenting questions based on deep learning | |
| US10535154B2 (en) | System, method, and program for image analysis | |
| CN112001336A (en) | Pedestrian boundary crossing alarm method, device, equipment and system | |
| CN113228105A (en) | Image processing method and device and electronic equipment | |
| CN111179287A (en) | Portrait instance segmentation method, device, equipment and storage medium | |
| US20220207261A1 (en) | Method and apparatus for detecting associated objects | |
| CN109978876A (en) | A kind of smog recognition methods and device based on quick bilateral filtering | |
| US10440331B2 (en) | System, method, and program for image analysis | |
| CN113691731B (en) | Processing method and device and electronic equipment | |
| CN110503605B (en) | Image processing method, device and storage medium | |
| CN111366916B (en) | Method and device for determining distance between interaction target and robot and electronic equipment | |
| JP5593884B2 (en) | Feature point determination device, feature point determination method, and feature point determination 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |