CN104866806A - Self-timer system and method with face positioning auxiliary function - Google Patents
Self-timer system and method with face positioning auxiliary function Download PDFInfo
- Publication number
- CN104866806A CN104866806A CN201410060677.4A CN201410060677A CN104866806A CN 104866806 A CN104866806 A CN 104866806A CN 201410060677 A CN201410060677 A CN 201410060677A CN 104866806 A CN104866806 A CN 104866806A
- Authority
- CN
- China
- Prior art keywords
- face
- self
- template image
- angle
- subsidiary function
- 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
Landscapes
- Image Processing (AREA)
Abstract
The invention provides a self-timer method with a face positioning auxiliary function. The method comprises the steps of: setting a self-timer angle; receiving face image information captured by a camera according to the angle, carrying out real-time analysis on the face image information by utilizing a multiple discriminant analysis algorithm and carrying out similarity comparison on characteristic values and characteristic vectors of the face image and a template image; and prompting a user to start shooting when the similarity of the face image and the template image reaches a threshold. The invention further provides a self-timer system with the face positioning auxiliary function. The self-timer system and method solves the problem that a user fails to shoot the whole when using a self-timer, the efficiency is improved, and the user experience is optimized.
Description
Technical field
The present invention relates to a kind of self-heterodyne system and method, especially a kind of self-heterodyne system and method with Face detection subsidiary function.
Background technology
Nowadays, mobile phone has become requisite thing in people's life, and present mobile phone has very high recreational, and when leisure out on tours is gone sightseeing, we usually to take pictures souvenir with mobile phone.Mention and take pictures, along with the pixel of current mobile phone camera improves constantly, the enhancing of the ability of image procossing, and its distinctive portability, gradually we more get used to taking pictures with mobile phone, and little by little go to instead of traditional card type digital camera.Therefore, consumer more and more takes notice of the convenience of take pictures quality and the operation of mobile phone.
Take pictures in form numerous; present young consumers is liked adopting the form of autodyning to show the individual character of oneself mostly; and the pixel of the front-facing camera of smart mobile phone is all lower mostly at present, be difficult to the demand meeting user, so usually still post-positioned pick-up head can be adopted autodyne.But because the image on the display screen in front cannot be seen, so user cannot grasp correct orientation to take complete image, therefore its effect is also unsatisfactory, in this case only to take pictures orientation in the adjustment that makes repeated attempts, perhaps can obtain a photo be relatively satisfied with after repeatedly taking pictures reluctantly, Consumer's Experience so is very poor.
Summary of the invention
In view of above content, be necessary to provide a kind of self-heterodyne system with Face detection subsidiary function to solve when user autodynes and cannot clap full puzzlement, raising efficiency optimizing user are experienced.
In addition, there is a need to provide a kind of self-timer method with Face detection subsidiary function.
Have a self-heterodyne system for Face detection subsidiary function, run in electronic installation, this system comprises: arrange module, for arranging auto heterodyne angle; Matching module, for receiving camera according to described angle catcher face image information, and utilize multiple discriminant analysis algorithm to carry out dimensionality reduction to extract its face characteristic value and proper vector, then the eigenwert of described facial image and template image and proper vector are carried out similarity comparison by nearest-neighbors method; Reminding module, for when the similarity of described facial image and described template image reaches a certain threshold value, prompting user starts to take pictures.
Have a self-timer method for Face detection subsidiary function, be applied in electronic installation, the method comprises:
Auto heterodyne angle is set;
Receive camera according to described angle catcher face image information, and utilize multiple discriminant analysis algorithm to carry out real-time analysis to it, and the eigenwert of described facial image and template image and proper vector are carried out similarity comparison by nearest-neighbors method;
When the similarity of described facial image and described template image reaches a certain threshold value, prompting user starts to take pictures.
Compared to prior art, the described self-heterodyne system with Face detection subsidiary function and method, in user's auto heterodyne process, similarity mode is carried out with the image taken in advance by being caught facial image by camera, prompt tone is sent to inform user when phase knowledge and magnanimity reach certain threshold value, a full difficult problem cannot be clapped when solving auto heterodyne with this, reach best shooting effect.
Accompanying drawing explanation
Fig. 1 is the running environment schematic diagram that the present invention has the preferred embodiment of the self-heterodyne system of Face detection subsidiary function.
Fig. 2 is the process flow diagram that the present invention has the preferred embodiment of the self-timer method of Face detection subsidiary function.
Fig. 3 is the detailed description of step S02 in the process flow diagram of Fig. 2.
Fig. 4 is the face schematic diagram of template image.
Main element symbol description
| Electronic installation | 1 |
| Self-heterodyne system | 10 |
| Camera | 11 |
| Display screen | 12 |
| Memory device | 13 |
| Processor | 14 |
| Acquisition module | 101 |
| Pretreatment module | 102 |
| Module is set | 103 |
| Matching module | 104 |
| Reminding module | 105 |
Following embodiment will further illustrate the present invention in conjunction with above-mentioned accompanying drawing.
Embodiment
As shown in Figure 1, be the running environment schematic diagram that the present invention has the self-heterodyne system preferred embodiment of Face detection subsidiary function.In this preferred embodiment, the described self-heterodyne system 10(with Face detection subsidiary function is hereinafter referred to as " self-heterodyne system 10 ") run in electronic installation 1.Described electronic installation 1 can be mobile phone, camera or PAD etc.Described electronic installation 1 comprises the camera 11, display screen 12, memory device 13 and the processor 14 that are connected by data bus.Described display screen 12 is for showing the data such as auto heterodyne image, and this display screen 12 can be the touch-screen etc. of mobile phone or panel computer.Described memory device 13 is for storing the program code and data information etc. of described self-heterodyne system 10, this memory device 13 can be the internal memory of electronic installation 1, also can be the storage facilitiess such as smart media card (smart media card), safe digital card (securedigital card), flash memory cards (flash card).Described processor 14 can be monokaryon or polycaryon processor.
In the present embodiment, described self-heterodyne system 10 can be divided into one or more module, and described one or more module to be stored in described memory device 13 and to be performed by processor 14, to complete function provided by the invention.Described self-heterodyne system 10 is divided into acquisition module 101, pretreatment module 102, arranges module 103, matching module 104 and reminding module 105.Function about each module is described in detail in the process flow diagram of Fig. 2 and Fig. 3.
Shown in figure 2, it is the process flow diagram that the present invention has the self-timer method of Face detection subsidiary function.According to different demands, the execution sequence of the step in the process flow diagram shown in Fig. 2 can change, and some step can be omitted.
Step S01, acquisition module 101 receives facial image (remember this facial image the be template image) Information Monitoring of camera 11 to auto heterodyne person certain angle.
Specifically, when using described self-heterodyne system 10 first, auto heterodyne person relies on another person by camera 11 to oneself face front, and top or below 45° angle degree or other predetermined values and left or 90 °, right angle or other predetermined values carry out man face image acquiring.
Step S02, pretreatment module 102 carries out System Partition and normalized to described template image.Such as, the major organs of described template image is positioned and analyzed, thus realize the object of gray scale normalizing and position correction.Detailed process about step S02 is described in detail in the flowchart of fig. 3.
Step S03, pretreatment module 102 utilizes multiple discriminant analysis (MultipleDiscriminate Analysis, MDA) algorithm carries out dimensionality reduction to described template image and extracts its face characteristic value and proper vector, and described face characteristic value and proper vector are stored in memory device 13, so that subsequent match.Described multiple discriminant analysis algorithm is a kind of prior art, this high dimension vector group of described template image can be carried out dimensionality reduction by this technology, thus it is lower to obtain dimension, is convenient to face characteristic value and the proper vector of analyzing and processing.
By step S01 to S03, the gather and analysis to user's face template image can be realized, thus obtain face characteristic value and the proper vector of described template image.And the interference of hair and background in described template image can be eliminated after above-mentioned steps process, be convenient to follow-up contrast the matching analysis.
Step S04, arranges module 103 and arranges auto heterodyne angle.Such as, in the present embodiment, there is provided the operation interface of an auto heterodyne angle constant input, user can select one group as auto heterodyne angle constant according to self hobby from many groups constant that system provides, and described auto heterodyne angle is the certain angle described in acquisition module 101.In addition, system is also provided with the auto heterodyne angle constant of an acquiescence, uses when not selecting this constant for user.
Step S05, matching module 104 receives camera 11 according to described angle catcher face image information, and utilize multiple discriminant analysis algorithm to carry out dimensionality reduction to extract its eigenwert and proper vector, and the eigenwert of described facial image and described template image and proper vector are carried out similarity compare of analysis by nearest-neighbors method.Described nearest-neighbors method is a kind of prior art, is the method for being carried out by training sample immediate in feature space classifying.Nearest-neighbors method adopts vector space model to classify, and concept is the case of identical category, and similarity is each other high, and by calculating the similarity with known class case, can carry out the classification that assess location classification case is possible.
Step S06, when the similarity of described facial image and described template image reaches a certain threshold value, reminding module 105 points out user to start to take pictures.Such as, the angle between camera 11 and user's face and described auto heterodyne angle close to time, the similarity of described facial image and described template image is the highest, if now described similarity reaches a certain threshold value (as 90%), then points out user to start to take pictures.
Consult the detail flowchart that Fig. 3 is step S02 in Fig. 2.
Step S021, adopts morphological method to locate the central point of two respectively at human face region.Such as, respectively the central point of described left eye and right eye is recorded as E
rand E
i(as shown in Figure 4).
Step S022, with described central point for benchmark carries out rotation correction.Specifically, described rotation correction makes the connecting line maintenance level of described central point, ensure that the consistance in face horizontal direction.
Step S023, cuts out face rectangular area according to face each several part proportionate relationship.In the present embodiment, suppose that o point is E
rand E
imid point, and
in the image of 2d × 2d, ensure that o point is fixed on (d, 0.5d) place, cutting is carried out to described facial image, ensure that the consistance in face location simultaneously.
Step S024, to the conversion that cutting facial image out adopts bilinear interpolation method to reduce and amplify, obtains the calibration chart picture of unified size.Such as, suppose that the size of regulation calibration chart picture is M × N, so the side ratio of cutting image and calibration chart picture is respectively 2d/M, 2d/N, and this ratio is not integer usually.(i, j) individual pixel of cutting image can correspond to the pixel in described calibration chart picture by side ratio, its respective coordinates is (i × 2d/M, j × 2d/N).Obviously, this respective coordinates is not generally integer, and non-integral coordinate cannot use in the discrete data of image.Therefore find by bilinear interpolation algorithm gray-scale value or the rgb value that four pixels nearest apart from this respective coordinates calculate this point.After calibration, not only obtain the geometric invariance of facial image to a certain extent, also essentially eliminate the interference of hair and background simultaneously.
Step S025, carries out gray scale stretching by described calibration chart picture, and adopts histogram modification technology to make it have unified average and variance.It is the most basic a kind of greyscale transformation that described gray scale stretches, and uses the simplest piecewise linear transform function, the dynamic range of gray level when being mainly used in improving image procossing.Described histogram modification technology is a kind of prior art, usually has histogram equalization and histogram specification two class, revises by it impact that intensity of illumination is eliminated in rear section.Can carry out to described template image the image that analyzing and processing obtains people face part through above-mentioned steps S021 to S025, eliminate the interference of hair and background, be convenient to follow-up computing and contrast the matching analysis.
It should be noted last that, above embodiment is only in order to illustrate technical scheme of the present invention and unrestricted, although with reference to preferred embodiment to invention has been detailed description, those of ordinary skill in the art is to be understood that, can modify to technical scheme of the present invention or equivalent replacement, and not depart from the spirit and scope of technical solution of the present invention.
Claims (10)
1. have a self-heterodyne system for Face detection subsidiary function, run in electronic installation, it is characterized in that, this system comprises:
Module is set, for arranging auto heterodyne angle;
Matching module, for receiving camera according to described angle catcher face image information, and utilize multiple discriminant analysis algorithm to carry out dimensionality reduction to extract its face characteristic value and proper vector, then the eigenwert of described facial image and template image and proper vector are carried out similarity comparison by nearest-neighbors method;
Reminding module, for when the similarity of described facial image and described template image reaches a certain threshold value, prompting user starts to take pictures.
2. have the self-heterodyne system of Face detection subsidiary function as claimed in claim 1, it is characterized in that, this system also comprises:
Acquisition module, for receiving the template image Information Monitoring of the face certain angle to auto heterodyne person;
Pretreatment module, for carrying out System Partition and normalized to described template image, and utilize multiple discriminant analysis algorithm to carry out dimensionality reduction to described template image to extract its face characteristic value and proper vector, and above-mentioned face characteristic value and proper vector are stored in memory device.
3. have the self-heterodyne system of Face detection subsidiary function as claimed in claim 2, it is characterized in that, described pretreatment module carries out System Partition to described template image and normalized comprises:
A () adopts morphological method to locate the central point of two respectively at the human face region of described template image;
(b) with described central point for benchmark carries out rotation correction;
C () cuts out face rectangular area according to face each several part proportionate relationship;
D conversion that () adopts bilinear interpolation method to reduce and amplify to cutting facial image out, obtains the calibration chart picture of unified size;
E described calibration chart picture is carried out gray scale stretching by (), and adopt histogram modification technology to make described calibration chart picture have unified average and variance.
4. have the self-heterodyne system of Face detection subsidiary function as claimed in claim 1, it is characterized in that, described auto heterodyne angle refers to certain angle when obtaining template image, is provided with many groups, by user's chosen in advance wherein one group in use.
5. have the self-heterodyne system of Face detection subsidiary function as claimed in claim 1, it is characterized in that, described electronic installation comprises mobile phone, camera and PAD.
6. have a self-timer method for Face detection subsidiary function, be applied in electronic installation, it is characterized in that, the method comprises:
Auto heterodyne angle is set;
Receive camera according to described angle catcher face image information, and utilize multiple discriminant analysis algorithm to carry out real-time analysis to it, and the eigenwert of described facial image and template image and proper vector are carried out similarity comparison by nearest-neighbors method;
When the similarity of described facial image and described template image reaches a certain threshold value, prompting user starts to take pictures.
7. have the self-timer method of Face detection subsidiary function as claimed in claim 6, it is characterized in that, the method also comprises:
Receive the template image Information Monitoring to the face certain angle of auto heterodyne person;
System Partition and normalized are carried out to described template image;
Utilize multiple discriminant analysis algorithm to carry out dimensionality reduction to described template image and extract its face characteristic value and proper vector, and above-mentioned face characteristic value and proper vector are stored in memory device.
8. there is the self-timer method of Face detection subsidiary function as claimed in claim 7, it is characterized in that, described the step that template image carries out System Partition and normalized to be comprised:
A () adopts morphological method to locate the central point of two respectively at the human face region of described template image;
(b) with described central point for benchmark carries out rotation correction;
C () cuts out face rectangular area according to face each several part proportionate relationship;
D conversion that () adopts bilinear interpolation method to reduce and amplify to cutting facial image out, obtains the calibration chart picture of unified size;
E described calibration chart picture is carried out gray scale stretching by (), and adopt histogram modification technology to make described calibration chart picture have unified average and variance.
9. have the self-timer method of Face detection subsidiary function as claimed in claim 6, it is characterized in that, described auto heterodyne angle refers to certain angle when obtaining template image, is provided with many groups, by user's chosen in advance wherein one group in use.
10. have the self-timer method of Face detection subsidiary function as claimed in claim 6, it is characterized in that, described electronic installation comprises mobile phone, camera and PAD.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410060677.4A CN104866806A (en) | 2014-02-21 | 2014-02-21 | Self-timer system and method with face positioning auxiliary function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410060677.4A CN104866806A (en) | 2014-02-21 | 2014-02-21 | Self-timer system and method with face positioning auxiliary function |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104866806A true CN104866806A (en) | 2015-08-26 |
Family
ID=53912627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410060677.4A Pending CN104866806A (en) | 2014-02-21 | 2014-02-21 | Self-timer system and method with face positioning auxiliary function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104866806A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105554389A (en) * | 2015-12-24 | 2016-05-04 | 小米科技有限责任公司 | Photographing method and photographing apparatus |
| WO2017084220A1 (en) * | 2015-11-20 | 2017-05-26 | 宇龙计算机通信科技(深圳)有限公司 | Photography processing method and apparatus, and terminal |
| CN106899798A (en) * | 2015-12-18 | 2017-06-27 | 林其禹 | Self-photographing unmanned aerial vehicle system and execution method thereof |
| WO2017143778A1 (en) * | 2016-02-24 | 2017-08-31 | 北京小米移动软件有限公司 | Automatic picture acquisition method and apparatus, and electronic device |
| WO2018165912A1 (en) * | 2017-03-15 | 2018-09-20 | SZ DJI Technology Co., Ltd. | Imaging method and imaging control apparatus |
| CN111316628A (en) * | 2017-11-08 | 2020-06-19 | 深圳传音通讯有限公司 | Image shooting method and image shooting system based on intelligent terminal |
| CN111709434A (en) * | 2020-06-28 | 2020-09-25 | 哈尔滨工业大学 | Robust multi-scale template matching method based on nearest neighbor feature point matching |
| CN115529417A (en) * | 2022-10-05 | 2022-12-27 | 湖南科技大学 | Post-shooting self-timer imaging method, face verification method, mobile phone and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020150280A1 (en) * | 2000-12-04 | 2002-10-17 | Pingshan Li | Face detection under varying rotation |
| CN101813868A (en) * | 2009-02-20 | 2010-08-25 | 华晶科技股份有限公司 | Camera self-timer method |
| CN102646190A (en) * | 2012-03-19 | 2012-08-22 | 腾讯科技（深圳）有限公司 | Authentication method, device and system based on biological characteristics |
| CN102970441A (en) * | 2012-12-03 | 2013-03-13 | 广东欧珀移动通信有限公司 | Self-portrait method based on rear camera of mobile phone and mobile phone |
| CN103491307A (en) * | 2013-10-07 | 2014-01-01 | 厦门美图网科技有限公司 | Intelligent selfie method through rear camera |
-
2014
- 2014-02-21 CN CN201410060677.4A patent/CN104866806A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020150280A1 (en) * | 2000-12-04 | 2002-10-17 | Pingshan Li | Face detection under varying rotation |
| CN101813868A (en) * | 2009-02-20 | 2010-08-25 | 华晶科技股份有限公司 | Camera self-timer method |
| CN102646190A (en) * | 2012-03-19 | 2012-08-22 | 腾讯科技（深圳）有限公司 | Authentication method, device and system based on biological characteristics |
| CN102970441A (en) * | 2012-12-03 | 2013-03-13 | 广东欧珀移动通信有限公司 | Self-portrait method based on rear camera of mobile phone and mobile phone |
| CN103491307A (en) * | 2013-10-07 | 2014-01-01 | 厦门美图网科技有限公司 | Intelligent selfie method through rear camera |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017084220A1 (en) * | 2015-11-20 | 2017-05-26 | 宇龙计算机通信科技(深圳)有限公司 | Photography processing method and apparatus, and terminal |
| CN106899798A (en) * | 2015-12-18 | 2017-06-27 | 林其禹 | Self-photographing unmanned aerial vehicle system and execution method thereof |
| CN106899798B (en) * | 2015-12-18 | 2020-02-07 | 林其禹 | Self-photographing unmanned aerial vehicle system and execution method thereof |
| CN105554389A (en) * | 2015-12-24 | 2016-05-04 | 小米科技有限责任公司 | Photographing method and photographing apparatus |
| WO2017143778A1 (en) * | 2016-02-24 | 2017-08-31 | 北京小米移动软件有限公司 | Automatic picture acquisition method and apparatus, and electronic device |
| WO2018165912A1 (en) * | 2017-03-15 | 2018-09-20 | SZ DJI Technology Co., Ltd. | Imaging method and imaging control apparatus |
| CN110268703A (en) * | 2017-03-15 | 2019-09-20 | 深圳市大疆创新科技有限公司 | Imaging method and imaging control apparatus |
| US11210796B2 (en) | 2017-03-15 | 2021-12-28 | SZ DJI Technology Co., Ltd. | Imaging method and imaging control apparatus |
| CN111316628A (en) * | 2017-11-08 | 2020-06-19 | 深圳传音通讯有限公司 | Image shooting method and image shooting system based on intelligent terminal |
| CN111709434A (en) * | 2020-06-28 | 2020-09-25 | 哈尔滨工业大学 | Robust multi-scale template matching method based on nearest neighbor feature point matching |
| CN111709434B (en) * | 2020-06-28 | 2022-10-04 | 哈尔滨工业大学 | Robust multi-scale template matching method based on nearest neighbor feature point matching |
| CN115529417A (en) * | 2022-10-05 | 2022-12-27 | 湖南科技大学 | Post-shooting self-timer imaging method, face verification method, mobile phone and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230117712A1 (en) | Feature density object classification, systems and methods | |
| CN104866806A (en) | Self-timer system and method with face positioning auxiliary function | |
| US11893828B2 (en) | System and method for image de-identification | |
| US9418283B1 (en) | Image processing using multiple aspect ratios | |
| US9449432B2 (en) | System and method for identifying faces in unconstrained media | |
| US9430766B1 (en) | Gift card recognition using a camera | |
| US8724910B1 (en) | Selection of representative images | |
| CN111191655B (en) | Object identification method and device | |
| WO2019033569A1 (en) | Eyeball movement analysis method, device and storage medium | |
| US9576210B1 (en) | Sharpness-based frame selection for OCR | |
| Günther et al. | The 2013 face recognition evaluation in mobile environment | |
| JP5361524B2 (en) | Pattern recognition system and pattern recognition method | |
| JP6351243B2 (en) | Image processing apparatus and image processing method | |
| US11367310B2 (en) | Method and apparatus for identity verification, electronic device, computer program, and storage medium | |
| US20090048842A1 (en) | Generalized Object Recognition for Portable Reading Machine | |
| JP2010520542A (en) | Illumination detection using a classifier chain | |
| CN109271930B (en) | Micro-expression recognition method, device and storage medium | |
| US9418316B1 (en) | Sharpness-based frame selection for OCR | |
| WO2019033570A1 (en) | Lip movement analysis method, apparatus and storage medium | |
| JP2017033372A (en) | Person recognition device and program therefor | |
| CN110363111B (en) | Face living body detection method, device and storage medium based on lens distortion principle | |
| CN109409322B (en) | Living body detection method and device, face recognition method and face detection system | |
| AU2021101072A4 (en) | DIP-Intelligent Neural Networks: Digital Image Processing Using Intelligent Neural Networks System | |
| Zabin et al. | A deep learning based approach to iris sensor identification | |
| Chihaoui et al. | Implementation of skin color selection prior to Gabor filter and neural network to reduce execution time of face detection |
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: 20150826 |