CN104036254A - Face recognition method - Google Patents
Face recognition method Download PDFInfo
- Publication number
- CN104036254A CN104036254A CN201410280208.3A CN201410280208A CN104036254A CN 104036254 A CN104036254 A CN 104036254A CN 201410280208 A CN201410280208 A CN 201410280208A CN 104036254 A CN104036254 A CN 104036254A
- Authority
- CN
- China
- Prior art keywords
- face
- facial image
- image
- denoising
- carried out
- 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
- Collating Specific Patterns (AREA)
- Image Processing (AREA)
Abstract
The invention provides a face recognition method. The face recognition method comprises the following steps of: receiving a face image; storing the face image in an image database; pre-processing the face image; extracting the characteristic points of the pre-processed face image and calculating characteristic values relative to the characteristic points, according to the characteristic points; judging whether a face in the face image is the registered face according to the calculated characteristic values relative to the characteristic points, and the characteristic values of an original face image sample in an original face image sample library; if the face in the face image is the registered face, then displaying and outputting the face image on a display screen. By virtue of the face recognition method provided by the invention, rapid recognition, accurate recognition, and high self-adaptive recognition capacity for the face image are realized.
Description
Technical field
The present invention relates to a kind of personal identification method, particularly a kind of face identification method.
Background technology
Information security issue has caused the extensive attention of various circles of society.The main path ensuring information safety is exactly that the identity of information user is accurately differentiated, whether the authority that further judges user's obtaining information by identification result is legal, thereby reaches the object that guarantee information is not leaked and ensures user's legitimate rights and interests.
Identification is reliably extremely important and necessary, the main path that living things feature recognition further becomes the core strategy technology tradition discriminating personal identification that ensures country and public safety is the perfect instrument that units at different levels issue, such as citizen ID certificate, city dweller's medical insurance card, officer's identity card, student's identity card, town dweller's residence booklet etc., the smart card of inputting in addition password is also the main path that personal identification is differentiated.The problem that these traditional identity discriminating approach exist is above: certificate, key etc. need to be carried, and convenience is poor, and volume is little, scientific and technological content is low, and they are easy to loss, stolen or imitated, have larger potential safety hazard; The safety coefficient of smart card is relatively high, but the case that has password to be cracked when current hacking technique causes occurs, and cannot guarantee authorized person's interests.Under these circumstances, biometrics identification technology, as a kind of safer, personal identification authentication technique easily, more and more receives publicity.
Existing biological identification technology comprises fingerprint recognition, iris recognition, recognition of face etc.Wherein recognition of face comprises method, the method based on invariant features, the method based on template matches, the method based on statistical model based on knowledge rule.Yet the facial image in existing face identification method does not much carry out pre-service, so the aspect such as scale form, illumination brightness, noise all becomes the key factor of the correct identification of impact facial image.On the other hand, in the method for processing at existing image denoising, Wavelet Denoising Method is relatively ripe, for example wavelet threshold denoising, can reduce boundary effect to decompositing the impact of signal, but adaptivity is poor, may affect denoising effect, compared to Wavelet Denoising Method, EMF denoising adaptivity is strong, therefore but because itself is also in developing stage, there is special edge effect, may cause the obscurity boundary of image after denoising.
For existing the problems referred to above in correlation technique, effective solution is not yet proposed at present.Therefore, the present invention proposes a kind of novel face identification method, unquestionable, novel face identification method of the present invention is suitable for identifying other images equally through suitable modification.
Summary of the invention
For solving the existing problem of above-mentioned prior art, the present invention proposes a kind of face identification method, by the present invention, utilize recognition methods corresponding to unique point to obtain fast result, strengthened the efficiency of recognition of face; By the present invention, carry out pretreatment operation, be normalized, illumination compensation and denoising especially simultaneously, the accuracy rate of recognition of face is significantly improved; By the processing of combination wavelet threshold denoising of the present invention, EMF denoising, especially on four direction, carry out wavelet threshold denoising and EMF denoising simultaneously, the advantage that has realized wavelet threshold denoising and EMF denoising is embodied in denoising method simultaneously, make denoising effect more perfect, not only boundary image is clear but also adaptive ability is strong, is suitable for the squelch in various situations.
Described method comprises: receive facial image; Facial image is kept in image data base; Facial image is carried out to pre-service; Extract the unique point of pretreated facial image, and calculate the eigenwert with respect to described unique point according to described unique point; According to the eigenwert of the primitive man's face image pattern in the calculated eigenwert with respect to described unique point and primitive man's face image pattern storehouse, judge whether the people's face in facial image is registered people's face; If the people's face in facial image is registered people's face, on display screen, show the described facial image of output.
Preferably, wherein, describedly facial image is carried out to pre-service comprise: facial image is carried out to size normalization processing, make the size of facial image identical with the size of primitive man's face image pattern in primitive man's face image pattern storehouse; The facial image having carried out after size normalization processing is carried out to illumination compensation processing, make brightness, contrast and the histogram distribution homogenising of facial image; The facial image having carried out after illumination compensation processing is carried out to denoising, make to reduce the noise of facial image.
Preferably, wherein, describedly by having carried out facial image after size normalization is processed, carry out illumination compensation and process and comprise histogram equalization.
Preferably, wherein, describedly by having carried out facial image after illumination compensation is processed, carry out denoising and comprise: by facial image respectively according to row, column, left diagonal angle and rightly one dimension is carried out in angular direction launch to obtain four vectors; Each in four vectors is carried out respectively to wavelet threshold denoising; Each in four vectors is carried out respectively to EMD denoising; According to four vectors after wavelet threshold denoising, obtain the wavelet threshold denoising image on four direction; According to four vectors after EMD denoising, obtain the EMD denoising image on four direction; EMD denoising image on wavelet threshold denoising image on four direction and four direction is summed up and on average obtains final denoising image.
Preferably, wherein, the unique point of described facial image comprises: the imago vegetarian refreshments position that has thick eyebrows, iris central pixel point position, nose center of gravity pixel position, oral area center of gravity pixel position.
Preferably, wherein, the eigenwert of described unique point comprises following parameter value: position, distance, angle, radian, curvature, shape, histogram.
Preferably, wherein, the size of the primitive man's face image pattern in described primitive man's face image pattern storehouse is 256*256 pixel.
Accompanying drawing explanation
Fig. 1 is according to the process flow diagram of the face identification method of the embodiment of the present invention.
Embodiment
Various ways can comprise the method for being embodied as for implementing the present invention, process, device, system and combination thereof.In this manual, any other form that these enforcements or the present invention can adopt can be called technology.Generally speaking, can change within the scope of the invention the step order of disclosed method.
Below with diagram the principle of the invention accompanying drawing together with the detailed description to one or more embodiment of the present invention is provided.In conjunction with such embodiment, describe the present invention, but the invention is not restricted to any embodiment.Scope of the present invention is only defined by the claims, and the present invention contain manyly substitute, modification and equivalent.Set forth in the following description many details to provide thorough understanding of the present invention.These details are provided for exemplary purposes, and also can realize the present invention according to claims without some or all details in these details.
The object of the present invention is to provide a kind of method of recognition of face.In face identification method and system, first to determine facial image, facial image can be the image that comprises people's face face-image and background image, wherein people's face face-image can be a plurality of, at facial image, comprises a plurality of people's faces.Facial image can be also the facial image through cutting, as removes most of background image and make the facial image of image subject behaviour face.In addition, facial image can be the facial image that has specific unified background and take pictures in real time.
Facial image identification comprises the important technologies such as image processing, image detection, and wherein most of processing all need to be carried out based on original image, and it is necessary therefore preserving original image.The primitive man's face Image Saving receiving in the present invention is in primitive man's face image pattern storehouse, also can directly be kept in storer, comprise and being temporarily stored in internal memory, be kept in hard disk for a long time, or be directly kept in the small fast memories such as SD card, flash card.
Image is processed (Image Processing), by computing machine, image is removed to method and the technology that noise, enhancing, recovery, division, extraction feature etc. are processed.In the present invention, for the object of facial image identification, proposed received facial image to be carried out to size normalization, illumination compensation processing and denoising, this is brand-new disposal route in face recognition technology field simultaneously.
Wherein, noise is the major reason of image disruption.May there are various noises in one images, these noises may produce in actual applications in transmission, also may in quantizing to wait processing, produce.Denoising method of the prior art comprises: EMD denoising, has appearred again in mean filter, adaptive wiener filter, medium filtering, morphology noise filtering, Wavelet Denoising Method in recent years.In the present invention, for there is the feature of people face part and background parts in facial image simultaneously, people's face figure is carried out to wavelet threshold denoising and EMD denoising simultaneously, be about in Wavelet Denoising Method edge pixel effectively and the strong advantage of EMD denoising adaptive ability is carried out combination.Meanwhile, by the vector on facial image different directions, carry out above-mentioned combination denoising, denoising effect is significantly improved.
The feature showing through pretreated facial image is to be suitable for carrying out feature extraction.Feature extraction is the calculation process that an image is carried out.Conventionally use characteristic extraction algorithm is realized, such as the method based on geometric properties, method based on statistics, elastic graph coupling, neural net method, support vector based method, hidden Markov model method etc.By feature extraction algorithm, obtain having in image the expression of specific meanings, as the eyebrow of principal character, eye, mouth, nose etc., or even scar on the face, birthmark, spot etc.By the said extracted of feature is processed to the above-mentioned unique point of determining people's face according to model, for example, by eyes or the distinctive contour structure of iris location eyes, and the position of recording iris central pixel point.Above-mentioned unique point for face characteristic is measured associated eigenvalue, comprise position, distance, angle, radian, curvature, shape, histogrammic tolerance, comprise the tolerance to color, brightness, texture etc., for example according to iris central pixel point, extend towards periphery, obtain whole location of pixels of eyes, the shape of eyes, the inclination radian at canthus, eye color etc.
In primitive man's face image pattern storehouse or Sample Storehouse, preserve primitive man's face image pattern or the experiment facial image sample of prior collection, and in Sample Storehouse, store the expression of these samples, comprise the unique point of above-mentioned aforesaid facial image, whose face the eigenwert of described unique point and described people's face are.All people's faces in Sample Storehouse are considered to registered people's face.By unique point and/or the eigenwert of the facial image of registering in the unique point of extracted facial image and/or eigenwert and Sample Storehouse are compared, determine that whose face facial image to be identified is, whether be registered people's face.Wherein above-mentioned comparison can be direct comparison, vector comparison, score comparison etc.And above-mentioned comparison can be absolute equal comparison or the comparison in error range.Take vector comparison as example, computation of characteristic values v
1, v
2..., v
n, and represent with vector V, compare the faceform's vector in vector V and face database, sorter determines whether to compare successfully according to comparative result.Particularly, range observation and the degree of correlation of carrying out between the faceform's vector in vector V and face database are measured, and determine whether to compare successfully according to the result of described range observation and degree of correlation measurement.
Fig. 1 is according to the process flow diagram of the face identification method of the embodiment of the present invention.As shown in Figure 1, implement concrete steps of the present invention as follows: step 1, receives facial image, in the preferred embodiment of the present invention, by using digital camera in real time facial image to be taken pictures to obtain facial image.Step 2, preserves the facial image receiving, and in the preferred embodiment of the present invention, facial image is kept in image data base to the preferred object-oriented database of described database.Step 3, carries out pre-service by facial image, and described pre-treatment step further comprises size normalization, looks after compensation and denoising.Step 4, extract the unique point of pretreated facial image, and calculate the eigenwert with respect to described unique point according to described unique point, in the preferred embodiment of the present invention, the unique point of described facial image comprises: the imago vegetarian refreshments position that has thick eyebrows, iris central pixel point position, nose center of gravity pixel position, oral area center of gravity pixel position, the eigenwert of described unique point comprises following parameter value: position, distance, angle, radian, curvature, shape, histogram.Step 5, according to the calculated eigenwert with respect to the eigenwert of described unique point and the primitive man's face image pattern in sample database, judge whether the people's face in facial image is registered people's face, in the preferred embodiment of the present invention, adopt directly contrast, vector contrast or score contrast.Wherein, in directly contrasting, the eigenwert of described unique point is mated with the eigenwert search of recording in the feature templates of storing in primitive man's face image pattern storehouse, by setting a threshold value, when similarity surpasses this threshold value, think that the match is successful.Step 6 if the people's face in facial image is registered people's face, shows the described facial image of output on display screen.
In the preferred embodiment of the present invention, describedly facial image is carried out to pre-service comprise: facial image is carried out to size normalization processing, make the size of facial image identical with the size of primitive man's face image pattern in primitive man's face image pattern storehouse, in one embodiment of the present invention, the size of the primitive man's face image pattern in described primitive man's face image pattern storehouse is 256*256 pixel; The facial image having carried out after size normalization processing is carried out to illumination compensation processing, wherein, describedly by having carried out facial image after size normalization is processed, carry out illumination compensation and process and comprise histogram equalization, make brightness, contrast and the histogram distribution homogenising of facial image; The facial image having carried out after illumination compensation processing is carried out to denoising, make to reduce the noise of facial image.
In the preferred embodiment of the present invention, describedly by having carried out facial image after illumination compensation is processed, carry out denoising and comprise: by facial image respectively according to row, column, left diagonal angle and rightly one dimension is carried out in angular direction launch to obtain four vectors; Each in four vectors is carried out respectively to wavelet threshold denoising; Each in four vectors is carried out respectively to EMD denoising; According to four vectors after wavelet threshold denoising, obtain the wavelet threshold denoising image on four direction; According to four vectors after EMD denoising, obtain the EMD denoising image on four direction; EMD denoising image on wavelet threshold denoising image on four direction and four direction is summed up and on average obtains final denoising image.By the vector on the facial image four direction to after size normalization and illumination compensation processing, carry out respectively wavelet threshold denoising and process and EMD denoising, denoising effect is significantly improved.
In sum, according to face identification method of the present invention, quick identification to facial image, accurately identification and stronger self-adaptation recognition capability have been realized.
Obviously, it should be appreciated by those skilled in the art, above-mentioned each step of the present invention can realize with general computing system, they can concentrate on single computing system, or be distributed on the network that a plurality of computing systems form, alternatively, they can be realized with the executable program code of computing system, thereby, they can be stored in storage system and be carried out by computing system.Like this, the present invention is not restricted to any specific hardware and software combination.
Should be understood that, above-mentioned embodiment of the present invention is only for exemplary illustration or explain principle of the present invention, and is not construed as limiting the invention.Therefore any modification of, making, be equal to replacement, improvement etc., within protection scope of the present invention all should be included in without departing from the spirit and scope of the present invention in the situation that.In addition, claims of the present invention are intended to contain whole variations and the modification in the equivalents that falls into claims scope and border or this scope and border.
Claims (7)
1. a face identification method, described method comprises:
Receive facial image;
Facial image is kept in image data base;
Facial image is carried out to pre-service;
Extract the unique point of pretreated facial image, and calculate the eigenwert with respect to described unique point according to described unique point;
According to the eigenwert of the primitive man's face image pattern in the calculated eigenwert with respect to described unique point and primitive man's face image pattern storehouse, judge whether the people's face in facial image is registered people's face;
If the people's face in facial image is registered people's face, on display screen, show the described facial image of output.
2. face identification method according to claim 1, is characterized in that, describedly facial image is carried out to pre-service comprises:
Facial image is carried out to size normalization processing, make the size of facial image identical with the size of primitive man's face image pattern in primitive man's face image pattern storehouse;
The facial image having carried out after size normalization processing is carried out to illumination compensation processing, make brightness, contrast and the histogram distribution homogenising of facial image;
The facial image having carried out after illumination compensation processing is carried out to denoising, make to reduce the noise of facial image.
3. face identification method according to claim 2, is characterized in that, describedly by having carried out facial image after size normalization is processed, carries out illumination compensation and processes and comprise histogram equalization.
4. face identification method according to claim 2, is characterized in that, describedly by having carried out facial image after illumination compensation is processed, carries out denoising and comprises:
Facial image is carried out to one dimension according to row, column, left diagonal angle and the right side to angular direction respectively and launch to obtain four vectors;
Each in four vectors is carried out respectively to wavelet threshold denoising;
Each in four vectors is carried out respectively to EMD denoising;
According to four vectors after wavelet threshold denoising, obtain the wavelet threshold denoising image on four direction;
According to four vectors after EMD denoising, obtain the EMD denoising image on four direction;
EMD denoising image on wavelet threshold denoising image on four direction and four direction is summed up and on average obtains final denoising image.
5. according to the face identification method described in arbitrary claim in claim 1-4, it is characterized in that, the unique point of described facial image comprises: the imago vegetarian refreshments position that has thick eyebrows, iris central pixel point position, nose center of gravity pixel position, oral area center of gravity pixel position.
6. according to the face identification method described in arbitrary claim in claim 1-4, it is characterized in that, the eigenwert of described unique point comprises following parameter value: position, distance, angle, radian, curvature, shape, histogram.
7. according to the face identification method described in arbitrary claim in claim 1-4, it is characterized in that, the size of the primitive man's face image pattern in described primitive man's face image pattern storehouse is 256*256 pixel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410280208.3A CN104036254A (en) | 2014-06-20 | 2014-06-20 | Face recognition method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410280208.3A CN104036254A (en) | 2014-06-20 | 2014-06-20 | Face recognition method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104036254A true CN104036254A (en) | 2014-09-10 |
Family
ID=51467020
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410280208.3A Pending CN104036254A (en) | 2014-06-20 | 2014-06-20 | Face recognition method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104036254A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408421A (en) * | 2014-11-26 | 2015-03-11 | 苏州福丰科技有限公司 | Three-dimensional face recognition method for provident fund account opening |
| CN105205482A (en) * | 2015-11-03 | 2015-12-30 | 北京英梅吉科技有限公司 | Quick facial feature recognition and posture estimation method |
| CN105740838A (en) * | 2016-02-06 | 2016-07-06 | 河北大学 | Recognition method in allusion to facial images with different dimensions |
| CN105956554A (en) * | 2016-04-29 | 2016-09-21 | 广西科技大学 | Face identification method |
| CN106169067A (en) * | 2016-07-01 | 2016-11-30 | 恒东信息科技无锡有限公司 | A kind of police dynamic human face of high flux gathers comparison method and system |
| CN107147849A (en) * | 2017-05-25 | 2017-09-08 | 潍坊科技学院 | A kind of control method of photographic equipment |
| CN107392089A (en) * | 2017-06-02 | 2017-11-24 | 广州视源电子科技股份有限公司 | Eyebrow movement detection method and device and living body identification method and system |
| CN108319933A (en) * | 2018-03-19 | 2018-07-24 | 广东电网有限责任公司中山供电局 | A kind of substation's face identification method based on DSP technologies |
| CN109271922A (en) * | 2018-09-13 | 2019-01-25 | 深圳市梦网百科信息技术有限公司 | A kind of nose localization method and system based on contrast |
| CN109493470A (en) * | 2018-10-16 | 2019-03-19 | 广州源贸易有限公司 | A kind of intelligent access control system based on block chain |
| CN109508700A (en) * | 2018-12-28 | 2019-03-22 | 广州粤建三和软件股份有限公司 | A kind of face identification method, system and storage medium |
| CN110519485A (en) * | 2019-09-09 | 2019-11-29 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN112686851A (en) * | 2020-12-25 | 2021-04-20 | 合肥联宝信息技术有限公司 | Image detection method, device and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1975759A (en) * | 2006-12-15 | 2007-06-06 | 中山大学 | Human face identifying method based on structural principal element analysis |
| CN101002682A (en) * | 2007-01-19 | 2007-07-25 | 哈尔滨工程大学 | Method for retrieval and matching of hand back vein characteristic used for identification of status |
| WO2008147039A1 (en) * | 2007-05-25 | 2008-12-04 | Inha-Industry Partnership Institute | System and method for recognizing images using t-test |
| CN101430759A (en) * | 2008-12-04 | 2009-05-13 | 上海大学 | Optimized recognition pretreatment method for human face |
| CN101739712A (en) * | 2010-01-25 | 2010-06-16 | 四川大学 | Video-based 3D human face expression cartoon driving method |
| CN102938058A (en) * | 2012-11-14 | 2013-02-20 | 南京航空航天大学 | Method and system for video driving intelligent perception and facing safe city |
| CN103324919A (en) * | 2013-06-25 | 2013-09-25 | 郑州吉瑞特电子科技有限公司 | Video monitoring system based on face recognition and data processing method thereof |
| CN103605964A (en) * | 2013-11-25 | 2014-02-26 | 上海骏聿数码科技有限公司 | Face detection method and system based on image on-line learning |
| CN103632132A (en) * | 2012-12-11 | 2014-03-12 | 广西工学院 | Face detection and recognition method based on skin color segmentation and template matching |
-
2014
- 2014-06-20 CN CN201410280208.3A patent/CN104036254A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1975759A (en) * | 2006-12-15 | 2007-06-06 | 中山大学 | Human face identifying method based on structural principal element analysis |
| CN101002682A (en) * | 2007-01-19 | 2007-07-25 | 哈尔滨工程大学 | Method for retrieval and matching of hand back vein characteristic used for identification of status |
| WO2008147039A1 (en) * | 2007-05-25 | 2008-12-04 | Inha-Industry Partnership Institute | System and method for recognizing images using t-test |
| CN101430759A (en) * | 2008-12-04 | 2009-05-13 | 上海大学 | Optimized recognition pretreatment method for human face |
| CN101739712A (en) * | 2010-01-25 | 2010-06-16 | 四川大学 | Video-based 3D human face expression cartoon driving method |
| CN102938058A (en) * | 2012-11-14 | 2013-02-20 | 南京航空航天大学 | Method and system for video driving intelligent perception and facing safe city |
| CN103632132A (en) * | 2012-12-11 | 2014-03-12 | 广西工学院 | Face detection and recognition method based on skin color segmentation and template matching |
| CN103324919A (en) * | 2013-06-25 | 2013-09-25 | 郑州吉瑞特电子科技有限公司 | Video monitoring system based on face recognition and data processing method thereof |
| CN103605964A (en) * | 2013-11-25 | 2014-02-26 | 上海骏聿数码科技有限公司 | Face detection method and system based on image on-line learning |
Non-Patent Citations (7)
| Title |
|---|
| 刘永信等: "人脸识别方法综述", 《内蒙古大学学报（自然科学版）》 * |
| 孟繁特: "人脸识别关键技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 张永德: "基于经验模态分解的小波阈值信号去噪研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 李倩: "人脸识别技术及应用", 《黑龙江科技信息》 * |
| 林玉荣等: "基于一维经验模态分解的图像细节提取方法", 《吉林大学学报（工学版）》 * |
| 郭耸 等: "利用EMD的自适应图像去噪", 《计算机工程与应用》 * |
| 龙侃 等: "基于一维小波变换的二维图像去噪算法", 《上饶师范学院学报》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104408421A (en) * | 2014-11-26 | 2015-03-11 | 苏州福丰科技有限公司 | Three-dimensional face recognition method for provident fund account opening |
| CN105205482B (en) * | 2015-11-03 | 2018-10-26 | 北京英梅吉科技有限公司 | Fast face feature recognition and posture evaluation method |
| CN105205482A (en) * | 2015-11-03 | 2015-12-30 | 北京英梅吉科技有限公司 | Quick facial feature recognition and posture estimation method |
| CN105740838A (en) * | 2016-02-06 | 2016-07-06 | 河北大学 | Recognition method in allusion to facial images with different dimensions |
| CN105956554A (en) * | 2016-04-29 | 2016-09-21 | 广西科技大学 | Face identification method |
| CN106169067A (en) * | 2016-07-01 | 2016-11-30 | 恒东信息科技无锡有限公司 | A kind of police dynamic human face of high flux gathers comparison method and system |
| CN106169067B (en) * | 2016-07-01 | 2019-05-28 | 恒东信息科技无锡有限公司 | A kind of police dynamic human face acquisition comparison method of high throughput and system |
| CN107147849A (en) * | 2017-05-25 | 2017-09-08 | 潍坊科技学院 | A kind of control method of photographic equipment |
| CN107392089A (en) * | 2017-06-02 | 2017-11-24 | 广州视源电子科技股份有限公司 | Eyebrow movement detection method and device and living body identification method and system |
| CN108319933A (en) * | 2018-03-19 | 2018-07-24 | 广东电网有限责任公司中山供电局 | A kind of substation's face identification method based on DSP technologies |
| CN109271922A (en) * | 2018-09-13 | 2019-01-25 | 深圳市梦网百科信息技术有限公司 | A kind of nose localization method and system based on contrast |
| CN109271922B (en) * | 2018-09-13 | 2022-01-04 | 深圳市梦网视讯有限公司 | Nasal part positioning method and system based on contrast |
| CN109493470A (en) * | 2018-10-16 | 2019-03-19 | 广州源贸易有限公司 | A kind of intelligent access control system based on block chain |
| CN109493470B (en) * | 2018-10-16 | 2021-08-03 | 广州一源贸易有限公司 | Intelligent access control system based on block chain |
| CN109508700A (en) * | 2018-12-28 | 2019-03-22 | 广州粤建三和软件股份有限公司 | A kind of face identification method, system and storage medium |
| CN110519485A (en) * | 2019-09-09 | 2019-11-29 | Oppo广东移动通信有限公司 | Image processing method, device, storage medium and electronic equipment |
| CN110519485B (en) * | 2019-09-09 | 2021-08-31 | Oppo广东移动通信有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
| CN112686851A (en) * | 2020-12-25 | 2021-04-20 | 合肥联宝信息技术有限公司 | Image detection method, device and storage medium |
| CN112686851B (en) * | 2020-12-25 | 2022-02-08 | 合肥联宝信息技术有限公司 | Image detection method, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104036254A (en) | Face recognition method | |
| US11244035B2 (en) | Apparatus and methods for biometric verification | |
| US8611618B2 (en) | Apparatus and method for generating representative fingerprint template | |
| CN106778450B (en) | Face recognition method and device | |
| US10922399B2 (en) | Authentication verification using soft biometric traits | |
| CN101558431A (en) | Face authentication device | |
| CN107977559A (en) | A kind of identity identifying method, device, equipment and computer-readable recording medium | |
| Singh et al. | Iris recognition system using a canny edge detection and a circular hough transform | |
| CN109376717A (en) | Personal identification method, device, electronic equipment and the storage medium of face comparison | |
| Stokkenes et al. | Multi-biometric template protection—A security analysis of binarized statistical features for bloom filters on smartphones | |
| CN108875549A (en) | Image-recognizing method, device, system and computer storage medium | |
| Kassem et al. | An enhanced ATM security system using multimodal biometric strategy | |
| CN106650616A (en) | Iris location method and visible light iris identification system | |
| JP2015041307A (en) | Collation device and collation method and collation system and computer program | |
| Sumalatha et al. | A Comprehensive Review of Unimodal and Multimodal Fingerprint Biometric Authentication Systems: Fusion, Attacks, and Template Protection | |
| Chen et al. | Iris recognition using 3D co-occurrence matrix | |
| Esan et al. | Bimodal biometrics for financial infrastructure security | |
| Rossan et al. | Impact of changing parameters when preprocessing dorsal hand vein pattern | |
| Prakash et al. | Fusion of multimodal biometrics using feature and score level fusion | |
| Aravinth et al. | A novel feature extraction techniques for multimodal score fusion using density based gaussian mixture model approach | |
| Poosarala | Uniform classifier for biometric ear and retina authentication using smartphone application | |
| Li et al. | The evolution of biometrics | |
| CN111428670B (en) | Face detection method, face detection device, storage medium and equipment | |
| Rossant et al. | A robust iris identification system based on wavelet packet decomposition and local comparisons of the extracted signatures | |
| CN107844735B (en) | Authentication method and device for biological characteristics |
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: 20140910 |