CN107766834B - Face recognition method and system - Google Patents
Face recognition method and system Download PDFInfo
- Publication number
- CN107766834B CN107766834B CN201711057760.6A CN201711057760A CN107766834B CN 107766834 B CN107766834 B CN 107766834B CN 201711057760 A CN201711057760 A CN 201711057760A CN 107766834 B CN107766834 B CN 107766834B
- Authority
- CN
- China
- Prior art keywords
- identification
- face
- camera module
- module
- interval
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a face recognition method and a face recognition system, wherein the face recognition method comprises the following steps: acquiring height data; determining an identification interval to which the height data belongs; acquiring an identification group; processing the face photos in the identification group to obtain preferred face photos; identifying the preferred face photo and outputting a face identification result; the first recognition interval is a shooting range of the first shooting module, and the second recognition interval is a shooting range of the second shooting module. The invention can adapt to users with different heights, has higher universality, can ensure shooting quality, can identify preferable face photos, and improves face recognition efficiency.
Description
Technical Field
The invention relates to the fields of pattern recognition, video monitoring and face recognition, in particular to a face recognition method and system.
Background
In pattern recognition, especially in the image recognition process, partial recognition is often lost due to limited image capturing coverage, and particularly in the face recognition and related video monitoring processes, shorter or taller people often cannot appear under the image capturing coverage, so that the position of the image capturing module is often fixed at a specific position in order to conform to the image capturing coverage of most average height people. Because the face recognition has higher requirements on image quality, children or people with higher heights cannot be easily identified in the application of face recognition access control equipment.
Fig. 1 is an illustration of a coverage area of a conventional image capturing, referring to fig. 1, in which an image capturing module is disposed at a position 1.4m away from the ground in a manner that an optical axis is parallel to a horizontal plane, the coverage area of a common high-definition camera is typically-30 degrees to +30 degrees, the optimal distance for face recognition is 0.6m to 0.9m, and the face height of a person is estimated to be 0.2m, so that the height range of the person which can be recognized is 1.25m to 1.75m when the recognition distance is 0.6 m. When the recognition distance is 0.9m, the range of the height of the person which can be recognized is 1.08m-1.91m. Therefore, under the condition of universal positions and angles of the camera modules, the height range which can be identified by face recognition is 1.08m-1.91m. Therefore, in the application of face recognition access control, young children and people with higher heights are excluded, and the universality is poor.
Disclosure of Invention
In view of the above, the invention provides a face recognition method and a face recognition system, which have a larger recognition range, can adapt to users with different heights, and solve the problem of poor universality of the face recognition system in the prior art.
The invention provides a face recognition method, which comprises the following steps:
acquiring height data;
determining an identification interval to which the height data belongs, wherein,
the identification interval comprises a first identification interval and a second identification interval, the first identification interval and the second identification interval are partially overlapped, wherein the first identification interval is the shooting range of the first shooting module, and the second identification interval is the shooting range of the second shooting module;
an identification group is obtained, wherein,
if the height data only belong to the first identification interval, controlling the first camera module to shoot, and obtaining at least two face photos to form an identification group;
if the height data only belong to the second identification interval, controlling the second camera module to shoot, and obtaining at least two face photos to form the identification group;
if the height data belong to the first identification interval and the second identification interval at the same time, controlling the first camera module and the second camera module to respectively shoot, and respectively obtaining at least one face photo to form the identification group;
processing the face photos in the identification group to obtain preferred face photos;
and identifying the preferred face photo and outputting a face identification result.
Further, the acquiring height data includes:
sensing whether a human body enters the identification area;
and when a human body is perceived to enter the identification area, measuring the human body to obtain the height data.
Further, the processing the face photos in the recognition group to obtain preferred face photos includes:
detecting the pixel quality of the face photo in the identification group;
and selecting the face photo with the highest pixel quality from the identification group as the preferred face photo.
Further, the processing the face photos in the recognition group to obtain preferred face photos includes:
and fusing at least two face photos in the identification group to obtain the preferable face photo.
Further, the method comprises the steps of,
the aperture and/or the focal length of the first camera module and the second camera module are different.
Further, the method comprises the steps of,
the minimum value of the first identification interval is smaller than the maximum value of the second identification interval.
The optical axis of the first camera module is inclined upwards, and the optical axis of the second camera module is inclined downwards.
The invention also provides a face recognition system, which comprises:
the shooting range of the first shooting module is a first identification interval;
the shooting range of the first shooting module is a second identification interval;
the height measurement module is used for acquiring height data;
the central processing module is connected with the height measuring module, the first camera shooting module and the second camera shooting module and is configured to execute the following steps:
determining an identification interval to which the height data belongs, wherein the identification interval comprises the first identification interval and the second identification interval, and the first identification interval and the second identification interval are partially overlapped;
an identification group is obtained, wherein,
if the height data only belong to the first identification interval, controlling the first camera module to shoot, and obtaining at least two face photos to form an identification group;
if the height data only belong to the second identification interval, controlling the second camera module to shoot, and obtaining at least two face photos to form the identification group;
if the height data belong to the first identification interval and the second identification interval at the same time, controlling the first camera module and the second camera module to respectively shoot, and respectively obtaining at least one face photo to form the identification group;
processing the face photos in the identification group to obtain preferred face photos;
identifying the preferred face photo and outputting a face identification result;
and the display module is connected with the central processing module.
Further, the height measurement module includes:
the sensing unit is used for sensing whether a human body enters the identification area or not, and sending a measurement instruction to the measurement unit when the sensing unit senses that the human body enters the identification area;
the measuring unit is connected with the sensing unit and is used for measuring the human body to obtain the height data when the measuring instruction is received.
Further, it is characterized in that,
the aperture and/or the focal length of the first camera module and the second camera module are different.
Further, it is characterized in that,
the first camera module and the second camera module are integrated in the display module;
the display module comprises a glass cover plate, wherein the glass cover plate comprises a first part, a second part and a third part which are all of a plane structure, the second part and the third part are positioned at two opposite ends of the first part, and included angles are formed between the first part and the second part as well as between the first part and the third part;
the first camera module is attached to the second part and shoots through the second part, and meanwhile, the optical axis of the first camera module is perpendicular to the second part;
the second camera module is attached to the third portion and shoots through the third portion, and meanwhile, the optical axis of the second camera module is perpendicular to the third portion.
Compared with the prior art, the method for expanding the image pickup coverage of the face recognition equipment has the following beneficial effects:
1) The camera module with a certain inclination and the height measurement module are adopted, the height measurement module collects height data, and different camera modules are controlled to shoot according to the height data, so that the camera module can adapt to users with different heights, and universality of a face recognition system is improved.
2) In order to match the inclined camera module and effectively avoid factors affecting the camera quality such as light scattering and reflection, a design method of the inclined glass cover plate is adopted, so that the camera module and the glass cover plate are in absolute vertical and close fit states, and the camera quality in a general mode is achieved.
3) In order to solve the problem of reduced face recognition efficiency, the invention collects a plurality of face photos and detects the quality of the face photos, only the face photo with the best quality can be recognized, and other face photos are automatically discarded.
The features of the present invention and its advantages will become apparent from the following detailed description of exemplary applications of the invention with reference to the accompanying drawings.
Drawings
FIG. 1 is a coverage area diagram of a camera module in the prior art;
fig. 2 is a flowchart of a face recognition method according to embodiment 1 of the present invention;
FIG. 3 is a schematic diagram of a positional relationship and a shooting range of two camera modules according to an embodiment of the present invention;
fig. 4 is a connection schematic diagram of a face recognition system according to embodiment 2 of the present invention;
FIG. 5 is a schematic diagram of a height measurement module according to embodiment 2 of the present invention;
FIG. 6 is a schematic diagram of a CPU module in embodiment 2 of the present invention;
FIG. 7 is a schematic diagram showing a relationship between two camera modules and a display module in an embodiment of the invention;
FIG. 8 is a schematic diagram of the positional relationship between two camera modules and a glass cover plate in an embodiment of the invention;
fig. 9 is a schematic diagram illustrating a positional relationship and coverage of two camera modules according to some alternative embodiments of the present invention.
Detailed Description
Certain terms are used throughout the description and claims to refer to particular components. Those of skill in the art will appreciate that a hardware manufacturer may refer to the same component by different names. The description and claims do not take the form of an element differentiated by name, but rather by functionality. As used throughout the specification and claims, the word "comprise" is an open-ended term, and thus should be interpreted to mean "include, but not limited to. By "substantially" is meant that within an acceptable error range, a person skilled in the art is able to solve the technical problem within a certain error range, substantially achieving the technical effect.
It should be noted that: the relative arrangement of camera modules, digital expressions and numerical values in these descriptions do not limit the scope of the present invention unless specifically stated otherwise.
The following application example description is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.
In the discussion shown herein, any particular value should be construed as merely illustrative, and not a limitation. Thus, other application examples may have different values.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.
Example 1
The embodiment provides a face recognition method, and fig. 2 is a flowchart of the face recognition method, specifically including the following steps:
step S1, obtaining height data;
specifically, whether a human body enters the identification area or not is perceived;
measuring a human body to obtain the height data when the human body is perceived to enter the identification area;
step S2, determining an identification interval to which the height data belongs;
the recognition section comprises a first recognition section and a second recognition section, as shown in fig. 3, the first recognition section and the second recognition section are partially overlapped, wherein the first recognition section is a shooting range of a first shooting module, and the second recognition section is a shooting range of a second shooting module; when the height of the user is in the shooting range, the first shooting module or the second shooting module can completely acquire the face photo of the user;
in some optional embodiments, the aperture and/or focal length of the first camera module and the second camera module are different;
as shown in fig. 3, in some alternative embodiments, the minimum value of the first identification interval is smaller than the maximum value of the second identification interval.
The optical axis of the first camera module is inclined upwards, and the optical axis of the second camera module is inclined downwards.
S3, acquiring an identification group;
if the height data only belong to the first identification section, controlling the first camera module to shoot, and obtaining at least two face photos to form an identification group;
if the height data only belong to the second identification interval, controlling the second camera module to shoot, and obtaining at least two face photos to form the identification group;
if the height data belong to the first identification interval and the second identification interval at the same time, controlling the first camera module and the second camera module to respectively shoot, and respectively obtaining at least one face photo to form the identification group;
s4, processing the face photos in the identification group to obtain preferred face photos;
specifically, detecting the pixel quality of the face photos in the recognition group;
selecting the face photo with the highest pixel quality from the identification group as the preferred face photo;
in some optional embodiments, at least two face photos in the recognition group may be fused to obtain the preferred face photo;
and S5, identifying the preferable face photo and outputting a face identification result.
The method provided by the embodiment can control different camera modules to shoot face photos according to different height data, can adapt to users with different heights, and has higher universality; the embodiment also optimizes and selects the face photos, thereby improving the accuracy and efficiency of face recognition.
Example 2
The present embodiment provides a face recognition system, and the present embodiment provides a face recognition system, as shown in fig. 4, including:
the device comprises a first camera module 10, a second camera module 20, a height measuring module 30, a central processing module 40 and a display module 50.
As shown in fig. 3, assuming that the face height of the user does not exceed 0.2m, the photographing range of the first photographing module 10 is a first recognition section; the second camera module 20, the shooting range of the second camera module 20 is the second recognition interval; the first identification interval and the second identification interval are partially overlapped; when the height of the user is within the shooting range, the first camera module 10 or the second camera module 20 can completely acquire the face photo of the user; in order to obtain better photographing effect, different apertures and focal lengths can be configured for the first photographing module 10 and the second photographing module 20.
As shown in fig. 5, the height measurement module 30 includes a sensing unit 31 and a measurement unit 32;
the sensing unit 31 may sense whether a human body enters the recognition area as shown in fig. 3, and when sensing that a human body enters the recognition area, send a measurement instruction to the measuring unit 32, and the measuring unit 32 measures the human body to obtain height data when receiving the measurement instruction.
The central processing module 40 is connected with the height measuring module 30, the first camera module 10 and the second camera module 20, and is used for controlling the first camera module 10 to take at least two face photos when the height data only belong to the first recognition section, controlling the second camera module 20 to take at least two face photos when the height data only belong to the second recognition section, and controlling the first camera module 10 and the second camera module 20 to take at least one face photo when the height data simultaneously belong to the first recognition section and the second recognition section; the first camera module 10 and the second camera module 20 transmit the photographed face photo to the central processing module 40, and the central processing module 40 performs preprocessing on the face photo to select the photo with the highest pixel quality as the preferred face photo, and identifies the preferred face photo.
As shown in fig. 6, in some alternative embodiments, the central processing module 40 includes a face photo quality detecting unit 41 and a face photo identifying unit 42, where the face photo quality detecting unit 41 is connected to the face photo identifying unit 42, and after receiving a plurality of face photos, the central processing module 40 detects the pixel quality of the plurality of face photos by the face photo quality detecting unit 41, retains the face photo with higher pixel quality as a preferred face photo, and transmits the face photo to the face photo identifying unit 42, and the face photo identifying unit 42 performs face recognition on the preferred face photo and outputs the identification result.
The display module 50 is connected with the central processing module 40, and can be used for displaying real-time face photos of the face recognition system, so that the angle and the gesture of a user can be conveniently adjusted, the face photos with good effect can be obtained, and the recognition efficiency is improved.
As shown in fig. 7, the first camera module 10 and the second camera module 20 are integrated in the display module 50.
As shown in fig. 8, the display module 50 includes a glass cover plate 51, where the glass cover plate includes a first portion 511, a second portion 512, and a third portion 513 each having a planar structure, the second portion 512 and the third portion 513 are located at opposite ends of the first portion 511, and the first portion 511 and the second portion 512, and the first portion 511 and the third portion 513 each have an included angle; the first camera module 10 is attached to the second portion 512 and shoots through the second portion 512; the second camera module 20 is attached to the third portion 513 and shoots through the third portion 513; the optical axis of the first camera module 10 is perpendicular to the second portion 512; the optical axis of the second camera module 20 is perpendicular to the third portion 513.
As shown in fig. 9, in some alternative embodiments, two third camera modules 60 and fourth camera modules 70 horizontally and horizontally placed in parallel may be added, so as to further extend the range of face recognition laterally, and at the same time, be able to recognize more faces.
As shown in fig. 3, in the present embodiment, it can be calculated that the height range of the person that can be recognized is 0.8m-2.0m when the recognition distance is 0.6 m; when the identification distance is 0.9m, the height range of the identified person is 0.5m-2.3m; therefore, in the invention, the height range which can be identified by face recognition is 0.5m-2.3m, which is larger than the height range of 1.08m-1.91m of the face recognition of the prior art shown in fig. 1.
The face recognition system provided by the embodiment has the following effects: the method of adopting the upper camera module and the lower camera module with a certain inclination angle can effectively enlarge the shooting range of face recognition, is applicable to different improvement of the universality of a face recognition system; by adopting the design method of the inclined glass cover plate, the optical axis of the camera module and the glass cover plate are in absolute vertical, so that factors affecting the camera quality such as light scattering and reflection can be effectively avoided, and the camera quality is ensured to be not lower than the prior art; the quality detection unit for the face photo is built in, the quality of the face photo collected by the plurality of camera modules can be detected, only the photo with the best quality can be identified, other photos are automatically discarded, the problem of repeated identification for many times is avoided, and the identification efficiency and the identification speed are effectively improved.
Claims (7)
1. The face recognition method is characterized by comprising the following steps of:
acquiring height data; the obtaining height data includes:
sensing whether a human body enters the identification area;
when a human body is perceived to enter the identification area, measuring the human body to obtain the height data, wherein the height range of the identifiable human body is 0.8m-2.0m when the identification distance is 0.6 m; when the identification distance is 0.9m, the height range of the identified person is 0.5m-2.3m;
determining an identification interval to which the height data belongs, wherein,
the identification interval comprises a first identification interval and a second identification interval, and the first identification interval and the second identification interval are partially overlapped; the first identification interval is a shooting range of the first shooting module, and the second identification interval is a shooting range of the second shooting module;
an identification group is obtained, wherein,
if the height data only belong to the first identification interval, controlling the first camera module to shoot, and obtaining at least two face photos to form an identification group;
if the height data only belong to the second identification interval, controlling the second camera module to shoot, and obtaining at least two face photos to form the identification group;
if the height data belong to the first identification interval and the second identification interval at the same time, controlling the first camera module and the second camera module to respectively shoot, and respectively obtaining at least one face photo to form the identification group;
processing the face photos in the identification group to obtain preferred face photos, including:
detecting the pixel quality of the face photos in the recognition group;
selecting the face photo with the highest pixel quality from the identification group as the preferred face photo;
or fusing at least two face photos in the identification group to obtain the preferable face photo;
and identifying the preferred face photo and outputting a face identification result.
2. The face recognition method of claim 1, wherein,
the aperture and/or the focal length of the first camera module and the second camera module are different.
3. The face recognition method of claim 1, wherein,
the minimum value of the first identification interval is smaller than the maximum value of the second identification interval;
the optical axis of the first camera module is inclined upwards, and the optical axis of the second camera module is inclined downwards.
4. A face recognition system implemented based on the method of claim 1, comprising: the shooting range of the first shooting module is a first identification interval;
the shooting range of the second shooting module is a second identification interval;
the height measurement module is used for acquiring height data;
the central processing module is connected with the height measuring module, the first camera shooting module and the second camera shooting module and is configured to execute the following steps:
determining an identification interval to which the height data belongs, wherein the identification interval comprises the first identification interval and the second identification interval, and the first identification interval and the second identification interval are partially overlapped;
an identification group is obtained, wherein,
if the height data only belong to the first identification interval, controlling the first camera module to shoot, and obtaining at least two face photos to form an identification group;
if the height data only belong to the second identification interval, controlling the second camera module to shoot, and obtaining at least two face photos to form the identification group;
if the height data belong to the first identification interval and the second identification interval at the same time, controlling the first camera module and the second camera module to respectively shoot, and respectively obtaining at least one face photo to form the identification group;
processing the face photos in the identification group to obtain preferred face photos;
identifying the preferred face photo and outputting a face identification result;
and the display module is connected with the central processing module and can be used for displaying real-time face photos of the face recognition system.
5. The face recognition system of claim 4, wherein the height measurement module comprises:
the sensing unit is used for sensing whether a human body enters the identification area or not, and sending a measurement instruction to the measurement unit when the sensing unit senses that the human body enters the identification area;
the measuring unit is connected with the sensing unit and is used for measuring the human body to obtain the height data when the measuring instruction is received.
6. The face recognition system of claim 4, wherein,
the aperture and/or the focal length of the first camera module and the second camera module are different.
7. The face recognition system of claim 4, wherein,
the first camera module and the second camera module are integrated in the display module;
the display module comprises a glass cover plate, wherein the glass cover plate comprises a first part, a second part and a third part which are all of a plane structure, the second part and the third part are positioned at two opposite ends of the first part, and included angles are formed between the first part and the second part as well as between the first part and the third part;
the first camera module is attached to the second part and shoots through the second part, and meanwhile, the optical axis of the first camera module is perpendicular to the second part;
the second camera module is attached to the third portion and shoots through the third portion, and meanwhile, the optical axis of the second camera module is perpendicular to the third portion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711057760.6A CN107766834B (en) | 2017-11-01 | 2017-11-01 | Face recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711057760.6A CN107766834B (en) | 2017-11-01 | 2017-11-01 | Face recognition method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107766834A CN107766834A (en) | 2018-03-06 |
| CN107766834B true CN107766834B (en) | 2023-09-26 |
Family
ID=61272012
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711057760.6A Active CN107766834B (en) | 2017-11-01 | 2017-11-01 | Face recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107766834B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109607339B (en) * | 2018-12-08 | 2021-02-09 | 广东伟邦科技股份有限公司 | Calling landing system with double face recognition modules |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001056859A (en) * | 1999-08-19 | 2001-02-27 | Toshiba Corp | Face image recognition device and passage controller |
| JP2007249132A (en) * | 2006-03-20 | 2007-09-27 | Casio Comput Co Ltd | Imaging apparatus, automatic focusing method, and program |
| CN201838010U (en) * | 2010-05-26 | 2011-05-18 | 中国科学院自动化研究所 | Remote iris-face integrated image acquisition and identification device |
| CN102930256A (en) * | 2012-11-14 | 2013-02-13 | 汉王科技股份有限公司 | Face recognition device and face image recognition method |
| CN103729625A (en) * | 2013-12-31 | 2014-04-16 | 青岛高校信息产业有限公司 | Face identification method |
| CN105011903A (en) * | 2014-04-30 | 2015-11-04 | 上海华博信息服务有限公司 | Intelligent health diagnosis system |
| CN105554385A (en) * | 2015-12-18 | 2016-05-04 | 天津中科智能识别产业技术研究院有限公司 | Remote multimode biometric recognition method and system thereof |
| CN106295536A (en) * | 2016-08-02 | 2017-01-04 | 北京无线电计量测试研究所 | A kind of self-adapting type iris identification device and utilize the method that this device carries out iris identification |
| CN106408695A (en) * | 2016-08-29 | 2017-02-15 | 神思电子技术股份有限公司 | Apparatus and method for iris identification of intelligent lock |
| CN106791681A (en) * | 2016-12-31 | 2017-05-31 | 深圳市优必选科技有限公司 | Video monitoring and face recognition method, device and system |
| CN106960200A (en) * | 2017-04-01 | 2017-07-18 | 罗旗舞 | A kind of face recognition device |
| CN107292300A (en) * | 2017-08-17 | 2017-10-24 | 湖南创合未来科技股份有限公司 | A kind of face recognition device and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3026291A1 (en) * | 2014-09-26 | 2016-04-01 | Morpho | DEVICE FOR USE IN IDENTIFYING OR AUTHENTICATING A SUBJECT |
-
2017
- 2017-11-01 CN CN201711057760.6A patent/CN107766834B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001056859A (en) * | 1999-08-19 | 2001-02-27 | Toshiba Corp | Face image recognition device and passage controller |
| JP2007249132A (en) * | 2006-03-20 | 2007-09-27 | Casio Comput Co Ltd | Imaging apparatus, automatic focusing method, and program |
| CN201838010U (en) * | 2010-05-26 | 2011-05-18 | 中国科学院自动化研究所 | Remote iris-face integrated image acquisition and identification device |
| CN102930256A (en) * | 2012-11-14 | 2013-02-13 | 汉王科技股份有限公司 | Face recognition device and face image recognition method |
| CN103729625A (en) * | 2013-12-31 | 2014-04-16 | 青岛高校信息产业有限公司 | Face identification method |
| CN105011903A (en) * | 2014-04-30 | 2015-11-04 | 上海华博信息服务有限公司 | Intelligent health diagnosis system |
| CN105554385A (en) * | 2015-12-18 | 2016-05-04 | 天津中科智能识别产业技术研究院有限公司 | Remote multimode biometric recognition method and system thereof |
| CN106295536A (en) * | 2016-08-02 | 2017-01-04 | 北京无线电计量测试研究所 | A kind of self-adapting type iris identification device and utilize the method that this device carries out iris identification |
| CN106408695A (en) * | 2016-08-29 | 2017-02-15 | 神思电子技术股份有限公司 | Apparatus and method for iris identification of intelligent lock |
| CN106791681A (en) * | 2016-12-31 | 2017-05-31 | 深圳市优必选科技有限公司 | Video monitoring and face recognition method, device and system |
| CN106960200A (en) * | 2017-04-01 | 2017-07-18 | 罗旗舞 | A kind of face recognition device |
| CN107292300A (en) * | 2017-08-17 | 2017-10-24 | 湖南创合未来科技股份有限公司 | A kind of face recognition device and method |
Non-Patent Citations (3)
| Title |
|---|
| Yongkang Wong等.Patch-based probabilistic image quality assessment for face selection and improved video-based face recognition.CVPR 2011 WORKSHOPS.2011,第74-81页. * |
| 人脸与证件对比系统设计与实现探究;郭迎达;于杨;曹正;丁一坤;闫永征;;中小企业管理与科技(中旬刊)(第01期);全文 * |
| 鲁鹏等.基于立体视觉的人脸三维空间位置定位方法.计算机应用研究.2010,第2766-2769页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107766834A (en) | 2018-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10956715B2 (en) | Decreasing lighting-induced false facial recognition | |
| TWI537842B (en) | People counting system | |
| US8675090B2 (en) | Image generating apparatus, image generating method, and recording medium | |
| KR20120053275A (en) | Method and apparatus for estimating 3d face position | |
| US11625828B2 (en) | Cost effective, mass producible system for rapid detection of fever conditions based on thermal imaging | |
| JP2003244521A (en) | Information processing method and apparatus, and recording medium | |
| US11948363B2 (en) | Person detection device and person detection method | |
| US20170364724A1 (en) | Image processing apparatus, image processing method, and image processing system | |
| CN112084813A (en) | Abnormal target detection method and device and storage medium | |
| JP7030451B2 (en) | Image processing equipment | |
| CN110728703B (en) | Registration fusion method for visible light image and solar blind ultraviolet light image | |
| US20090202180A1 (en) | Rotation independent face detection | |
| CN107766834B (en) | Face recognition method and system | |
| US20180082129A1 (en) | Information processing apparatus, detection system, and information processing method | |
| TWI671707B (en) | Image analysis method, electronic system and non-transitory computer-readable recording medium | |
| JP6789410B2 (en) | Image processing device, control method and control program | |
| JP6244960B2 (en) | Object recognition apparatus, object recognition method, and object recognition program | |
| JP2019027882A (en) | Object distance detector | |
| JP6296769B2 (en) | Object detection device | |
| CN110956054A (en) | Iris image acquisition method and terminal | |
| CN113011222B (en) | Living body detection system, living body detection method and electronic equipment | |
| KR20220079753A (en) | Method for measuring of object based on face-recognition | |
| KR102432735B1 (en) | Motion sensing apparatus | |
| US12125312B2 (en) | Decreasing lighting-induced false facial recognition | |
| TWI420424B (en) | System and method for monitoring baby sleeping |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |