CN103699877A - Method and system for improving face recognition effects - Google Patents
Method and system for improving face recognition effects Download PDFInfo
- Publication number
- CN103699877A CN103699877A CN201310638499.4A CN201310638499A CN103699877A CN 103699877 A CN103699877 A CN 103699877A CN 201310638499 A CN201310638499 A CN 201310638499A CN 103699877 A CN103699877 A CN 103699877A
- Authority
- CN
- China
- Prior art keywords
- recognition
- face
- environment
- exposure level
- facial image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Studio Devices (AREA)
- Image Processing (AREA)
Abstract
The invention provides a method for improving face recognition effects. The method comprises the following steps: acquiring current environmental light parameters for face recognition; according to the environmental light parameters, acquiring a face image for wide-dynamic range imaging processing when a current face recognition environment is judged to be a low-light environment or an excessive exposure environment. The invention also provides a system for improving the face recognition effects. According to the method and the system, the success rate of face recognition can be increased, and the good recognition effects are achieved.
Description
Technical field
The present invention relates to face recognition technology field, particularly relate to a kind of method that improves recognition of face effect, and a kind of system that improves recognition of face effect.
Background technology
At present, the function of mobile device from strength to strength, has the function of recognition of face on many equipment, be generally that the camera sensing device of installing on equipment carries out human face scanning; But at present the recognition of face effect of mobile device is poor, such as under light conditions or under overexposure condition, due to situations such as image definition are lower and light is darker, it is just very low that people's face is detected as power, and recognition effect is poor.
Summary of the invention
Based on this, the invention provides a kind of method and system that improves recognition of face effect, can improve the success ratio of recognition of face, recognition effect is good.
A method that improves recognition of face effect, comprises the steps:
Obtain current surround lighting parameter while carrying out recognition of face;
According to described surround lighting parameter, when the current recognition of face environment of judgement is low luminous environment or overexposure environment, obtains facial image and carry out high dynamic range imaging processing;
Facial image after processing is carried out to recognition of face.
A system that improves recognition of face effect, comprising:
Acquisition module, for obtaining current surround lighting parameter while carrying out recognition of face;
Processing module, for according to described surround lighting parameter, when the current recognition of face environment of judgement is low luminous environment or overexposure environment, obtains facial image and carries out high dynamic range imaging processing;
Identification module, carries out recognition of face for the facial image to after processing.
The method and system of above-mentioned raising recognition of face effect, obtains current environment optical parameter, when judging shooting environmental and be low luminous environment or overexposure environment, obtains facial image and carries out high dynamic range imaging processing, then the image after processing is carried out to recognition of face; High dynamic range images can provide more dynamic range and image detail, and the facial image sharpness obtaining after processing is higher, therefore in the situation that shooting environmental is poor, can improve the recognition of face success ratio of equipment, underwriter's face recognition effect.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet in one embodiment of method that the present invention improves recognition of face effect.
Fig. 2 is the structural representation in one embodiment of system that the present invention improves recognition of face effect.
Embodiment
Below in conjunction with embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are not limited to this.
As shown in Figure 1, be a kind of method that improves recognition of face effect of the present invention, comprise the steps:
S11, obtain current surround lighting parameter;
When mobile device unlatching camera carries out recognition of face, camera can gather current environmental information, now can obtain the surround lighting parameter of camera collection.
S12, according to described surround lighting parameter, when judgement current shooting environment is low luminous environment or overexposure environment, obtains facial image and carry out high dynamic range imaging processing;
Surround lighting parameter according to current, judges current shooting environmental, if low luminous environment or overexposure environment need the facial image to gathering to process, the process of processing is that high dynamic range imaging is processed;
High dynamic range imaging (High-Dynamic Range, HDR) be treated to a kind of shooting treatment technology, photographer adjusts f-number and the shutter speed of camera, shooting obtains the image of different exposure time, utilize the image of each corresponding best details of time shutter to synthesize final HDR image, this image can provide more dynamic range and image detail;
When being judged as low luminous environment or overexposure environment, if adopt conventional image acquisition flow process, the facial image collecting may be because brightness is too dark or brightness is too high, facial image second-rate, inspection does not measure the feature details such as facial contour, causes recognition of face to make mistakes or recognition failures; And in the present embodiment, the facial image gathering is carried out to high dynamic range imaging to be synthesized, obtain HDR image, the facial image sharpness after processing is higher, and more details can be provided.
S13, the facial image after processing is carried out to recognition of face;
The facial image generating after high dynamic range imaging is processed is carried out to recognition of face, because the HDR image definition obtaining after processing is higher, comprise more feature and details, therefore can improve recognition of face success ratio, underwriter's face recognition effect.
In a preferred embodiment, described surround lighting parameter is colour temperature; Described surround lighting parameter adopts color temperature parameters, can simplify the flow process of the current recognition of face environment of judgement, improves recognition speed.
In a preferred embodiment, when described color temperature value is less than default low photo threshold, be judged as low luminous environment; When described color temperature value is greater than default threshold exposure, be judged as overexposure environment;
In this step, the predeterminable low photo threshold of technician and threshold exposure, contrast the current color temperature value collecting and above-mentioned two threshold values, determines that fast current recognition of face environment is low luminous environment or overexposure environment.
In a preferred embodiment, described in obtain the step that facial image carries out high dynamic range imaging processing and be:
By adjusting the exposure level of camera, obtain multiple facial images of different exposure level;
Multiple facial images to described different exposure level synthesize, and generate high dynamic range images, obtain the facial image after described processing;
In the present embodiment, when the current shooting environmental of judgement is low luminous environment or overexposure environment, need obtains facial image and carry out high dynamic range imaging processing; The acquisition parameters of the camera sensing device of now installing in adjustment equipment, concrete acquisition parameters is exposure level, switches different exposure level parameters, the facial image under the different exposure level of Real-time Collection; Multiple facial images to the different exposure level that collect synthesize processing, adopt HDR algorithm, generate the synthetic HDR image of multiple facial images.
Further, multiple facial images of described different exposure level at least comprise the facial image of three following exposure level: exposure level is respectively 0EV, NEV and-NEV, wherein N is non-vanishing integer;
Such as, multiple facial images of described different exposure level can be three facial images, and its exposure level can be preferably 0EV, 2EV and-2EV, only need to gather the facial image of three different exposure level, can generate HDR image, the processing speed that improves image, makes equipment recognition of face quicker.
As shown in Figure 2, be a kind of structural representation that improves the system of recognition of face effect of the present invention, comprising:
When mobile device unlatching camera carries out recognition of face, camera can gather current environmental information, now can obtain the surround lighting parameter of camera collection.
Surround lighting parameter according to current, judges current shooting environmental, if low luminous environment or overexposure environment need the facial image to gathering to process, the process of processing is that high dynamic range imaging is processed;
High dynamic range imaging (High-Dynamic Range, HDR) be treated to a kind of shooting treatment technology, photographer adjusts f-number and the shutter speed of camera, shooting obtains the image of different exposure time, utilize the image of each corresponding best details of time shutter to synthesize final HDR image, this image can provide more dynamic range and image detail;
When being judged as low luminous environment or overexposure environment, if adopt conventional image acquisition flow process, the facial image collecting may be because brightness is too dark or brightness is too high, facial image second-rate, inspection does not measure the feature details such as facial contour, causes recognition of face to make mistakes or recognition failures; And in the present embodiment, the facial image gathering is carried out to high dynamic range imaging to be synthesized, obtain HDR image, the facial image sharpness after processing is higher, and more details can be provided.
The facial image generating after high dynamic range imaging is processed is carried out to recognition of face, because the HDR image definition obtaining after processing is higher, comprise more feature and details, therefore can improve recognition of face success ratio, underwriter's face recognition effect.
In a preferred embodiment, described surround lighting parameter is colour temperature; Described surround lighting parameter adopts color temperature parameters, can simplify the flow process of the current recognition of face environment of judgement, improves recognition speed.
In a preferred embodiment, described processing module also for: when described color temperature value is less than default low photo threshold, be judged as low luminous environment; When described color temperature value is greater than default threshold exposure, be judged as overexposure environment;
In the present embodiment, the predeterminable low photo threshold of technician and threshold exposure, contrast the current color temperature value collecting and above-mentioned two threshold values, determines that fast current recognition of face environment is low luminous environment or overexposure environment.
In a preferred embodiment, described processing module also for:
By adjusting the exposure level of camera, obtain multiple facial images of different exposure level;
Multiple facial images to described different exposure level synthesize, and generate high dynamic range images, obtain the facial image after described processing;
In the present embodiment, when the current shooting environmental of judgement is low luminous environment or overexposure environment, need obtains facial image and carry out high dynamic range imaging processing; The acquisition parameters of the camera sensing device of now installing in adjustment equipment, concrete acquisition parameters is exposure level, switches different exposure level parameters, the facial image under the different exposure level of Real-time Collection; Multiple facial images to the different exposure level that collect synthesize processing, adopt HDR algorithm, generate the synthetic HDR image of multiple facial images.
Further, multiple facial images of the described different exposure level in described processing module at least comprise the facial image of three following exposure level: exposure level is respectively 0EV, NEV and-NEV, wherein N is non-vanishing integer;
Such as, multiple facial images of described different exposure level can be three facial images, and its exposure level can be preferably 0EV, 2EV and-2EV, only need to gather the facial image of three different exposure level, can generate HDR image, the processing speed that improves image, makes equipment recognition of face quicker.
The present invention improves the method and system of recognition of face effect, obtains current environment optical parameter, when judging shooting environmental and be low luminous environment or overexposure environment, obtains facial image and carries out high dynamic range imaging processing, then the image after processing is carried out to recognition of face; High dynamic range images can provide more dynamic range and image detail, and the facial image sharpness obtaining after processing is higher, therefore in the situation that shooting environmental is poor, can improve the recognition of face success ratio of equipment, underwriter's face recognition effect.
The above embodiment has only expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be interpreted as the restriction to the scope of the claims of the present invention.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. a method that improves recognition of face effect, is characterized in that, comprises the steps:
Obtain current surround lighting parameter while carrying out recognition of face;
According to described surround lighting parameter, when the current recognition of face environment of judgement is low luminous environment or overexposure environment, obtains facial image and carry out high dynamic range imaging processing;
Facial image after processing is carried out to recognition of face.
2. improve according to claim 1 the method for recognition of face effect, it is characterized in that, described surround lighting parameter is colour temperature.
3. improve according to claim 2 the method for recognition of face effect, it is characterized in that, when described color temperature value is less than default low photo threshold, be judged as low luminous environment; When described color temperature value is greater than default threshold exposure, be judged as overexposure environment.
4. according to the method that improves recognition of face effect described in claims 1 to 3 any one, it is characterized in that, described in obtain the step that facial image carries out high dynamic range imaging processing and be:
By adjusting the exposure level of camera, obtain multiple facial images of different exposure level;
Multiple facial images to described different exposure level synthesize, and generate high dynamic range images, obtain the facial image after described processing.
5. improve according to claim 4 the method for recognition of face effect, it is characterized in that, multiple facial images of described different exposure level at least comprise the facial image of three following exposure level:
Exposure level is respectively 0EV, NEV and-NEV, wherein N is non-vanishing integer.
6. a system that improves recognition of face effect, is characterized in that, comprising:
Acquisition module, for obtaining current surround lighting parameter while carrying out recognition of face;
Processing module, for according to described surround lighting parameter, when the current recognition of face environment of judgement is low luminous environment or overexposure environment, obtains facial image and carries out high dynamic range imaging processing;
Identification module, carries out recognition of face for the facial image to after processing.
7. improve according to claim 6 the system of recognition of face effect, it is characterized in that, described surround lighting parameter is colour temperature.
8. improve according to claim 7 the system of recognition of face effect, it is characterized in that, described processing module also for: when described color temperature value is less than default low photo threshold, be judged as low luminous environment; When described color temperature value is greater than default threshold exposure, be judged as overexposure environment.
9. according to the system that improves recognition of face effect described in claim 6 to 8 any one, it is characterized in that, described processing module also for:
By adjusting the exposure level of camera, obtain multiple facial images of different exposure level;
Multiple facial images to described different exposure level synthesize, and generate high dynamic range images, obtain the facial image after described processing.
10. improve according to claim 9 the system of recognition of face effect, it is characterized in that, multiple facial images of described different exposure level in described processing module at least comprise the facial image of three following exposure level: exposure level is respectively 0EV, NEV and-NEV, wherein N is non-vanishing integer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310638499.4A CN103699877A (en) | 2013-12-02 | 2013-12-02 | Method and system for improving face recognition effects |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310638499.4A CN103699877A (en) | 2013-12-02 | 2013-12-02 | Method and system for improving face recognition effects |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103699877A true CN103699877A (en) | 2014-04-02 |
Family
ID=50361400
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310638499.4A Pending CN103699877A (en) | 2013-12-02 | 2013-12-02 | Method and system for improving face recognition effects |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103699877A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105227858A (en) * | 2015-10-30 | 2016-01-06 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN105224932A (en) * | 2015-10-21 | 2016-01-06 | 北京旷视科技有限公司 | A kind of face identification method and system |
| CN105450932A (en) * | 2015-12-31 | 2016-03-30 | 华为技术有限公司 | Backlight photographing method and device |
| CN106778699A (en) * | 2017-01-20 | 2017-05-31 | 贵州财经大学 | The door of face identification system and application face identification system |
| CN106846578A (en) * | 2017-01-20 | 2017-06-13 | 贵州财经大学 | Face identification system and gate control system |
| CN107862265A (en) * | 2017-10-30 | 2018-03-30 | 广东欧珀移动通信有限公司 | Image processing method and related product |
| CN108830061A (en) * | 2018-05-25 | 2018-11-16 | 努比亚技术有限公司 | Terminal unlock method, mobile terminal and readable storage medium storing program for executing based on recognition of face |
| CN109446940A (en) * | 2018-10-12 | 2019-03-08 | Oppo（重庆）智能科技有限公司 | Fingerprint identification method, electronic device and computer-readable medium |
| CN110705336A (en) * | 2018-07-10 | 2020-01-17 | 福州瑞芯微电子股份有限公司 | Image processing method, system, electronic device and readable storage medium |
| WO2020034735A1 (en) * | 2018-08-13 | 2020-02-20 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Imaging control method and electronic device |
| CN110830728A (en) * | 2018-08-13 | 2020-02-21 | 浙江宇视科技有限公司 | Exposure adjusting method and device |
| CN112001724A (en) * | 2019-05-27 | 2020-11-27 | 阿里巴巴集团控股有限公司 | Data processing method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006166226A (en) * | 2004-12-09 | 2006-06-22 | Seiko Epson Corp | Digital camera, image processing method and program, and image processing system |
| CN101068311A (en) * | 2006-05-02 | 2007-11-07 | 卡西欧计算机株式会社 | Image capture apparatus and image capture program |
| CN102271218A (en) * | 2011-01-17 | 2011-12-07 | 深圳市保千里电子有限公司 | Scene-oriented ultra-intelligent video camera and camera shooting method thereof |
| CN103095979A (en) * | 2011-11-07 | 2013-05-08 | 华晶科技股份有限公司 | Image processing method and imaging capture device of face overexposure |
-
2013
- 2013-12-02 CN CN201310638499.4A patent/CN103699877A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006166226A (en) * | 2004-12-09 | 2006-06-22 | Seiko Epson Corp | Digital camera, image processing method and program, and image processing system |
| CN101068311A (en) * | 2006-05-02 | 2007-11-07 | 卡西欧计算机株式会社 | Image capture apparatus and image capture program |
| CN102271218A (en) * | 2011-01-17 | 2011-12-07 | 深圳市保千里电子有限公司 | Scene-oriented ultra-intelligent video camera and camera shooting method thereof |
| CN103095979A (en) * | 2011-11-07 | 2013-05-08 | 华晶科技股份有限公司 | Image processing method and imaging capture device of face overexposure |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105224932A (en) * | 2015-10-21 | 2016-01-06 | 北京旷视科技有限公司 | A kind of face identification method and system |
| CN105227858A (en) * | 2015-10-30 | 2016-01-06 | 维沃移动通信有限公司 | A kind of image processing method and mobile terminal |
| CN105450932B (en) * | 2015-12-31 | 2018-11-09 | 华为技术有限公司 | Backlight photographic method and device |
| CN105450932A (en) * | 2015-12-31 | 2016-03-30 | 华为技术有限公司 | Backlight photographing method and device |
| CN106778699A (en) * | 2017-01-20 | 2017-05-31 | 贵州财经大学 | The door of face identification system and application face identification system |
| CN106846578A (en) * | 2017-01-20 | 2017-06-13 | 贵州财经大学 | Face identification system and gate control system |
| CN107862265A (en) * | 2017-10-30 | 2018-03-30 | 广东欧珀移动通信有限公司 | Image processing method and related product |
| CN108830061A (en) * | 2018-05-25 | 2018-11-16 | 努比亚技术有限公司 | Terminal unlock method, mobile terminal and readable storage medium storing program for executing based on recognition of face |
| CN110705336A (en) * | 2018-07-10 | 2020-01-17 | 福州瑞芯微电子股份有限公司 | Image processing method, system, electronic device and readable storage medium |
| CN110705336B (en) * | 2018-07-10 | 2022-09-09 | 福州瑞芯微电子股份有限公司 | Image processing method, system, electronic device and readable storage medium |
| WO2020034735A1 (en) * | 2018-08-13 | 2020-02-20 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Imaging control method and electronic device |
| CN110830728A (en) * | 2018-08-13 | 2020-02-21 | 浙江宇视科技有限公司 | Exposure adjusting method and device |
| US10630906B2 (en) | 2018-08-13 | 2020-04-21 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Imaging control method, electronic device and computer readable storage medium |
| CN109446940A (en) * | 2018-10-12 | 2019-03-08 | Oppo（重庆）智能科技有限公司 | Fingerprint identification method, electronic device and computer-readable medium |
| CN112001724A (en) * | 2019-05-27 | 2020-11-27 | 阿里巴巴集团控股有限公司 | Data processing method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103699877A (en) | Method and system for improving face recognition effects | |
| CN105208281B (en) | A kind of night scene image pickup method and device | |
| US11057592B2 (en) | Image defogging method and image capture apparatus implementing image defogging | |
| JP5981053B2 (en) | Imaging device with scene-adaptive automatic exposure compensation | |
| CN105100632B (en) | The method of adjustment and device of imaging device automatic exposure, imaging device | |
| US10453188B2 (en) | Methods and devices for improving image quality based on synthesized pixel values | |
| WO2021109620A1 (en) | Exposure parameter adjustment method and apparatus | |
| CN108337433A (en) | A kind of photographic method, mobile terminal and computer readable storage medium | |
| CN106570838B (en) | A kind of brightness of image optimization method and device | |
| JP2014053855A (en) | Image processing device and method, and program | |
| EP3162048B1 (en) | Exposure metering based on background pixels | |
| CN105430267A (en) | Method for adaptively adjusting camera parameters based on face image illumination parameters | |
| CN102790862A (en) | Method for dynamically improving effect of cell phone front camera | |
| CN105847693A (en) | Shooting method and system based on two-camera focusing | |
| CN110033418A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN109474770B (en) | Imaging device and imaging method | |
| CN110047060B (en) | Image processing method, image processing device, storage medium and electronic equipment | |
| US11678180B2 (en) | Iris recognition workflow | |
| CN104899836B (en) | A kind of Misty Image intensifier and method based near infrared multispectral imaging | |
| CN111476732B (en) | Image fusion and denoising method and system | |
| CN103297675A (en) | Image capture method and relative image capture system | |
| JP2008048251A (en) | Photographing apparatus and photographing method | |
| CN106941588B (en) | Data processing method and electronic equipment | |
| CN106506946B (en) | A kind of camera automatic focusing method and video camera | |
| CN111666869B (en) | Face recognition method and device based on wide dynamic processing and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140402 |