CN115830676A - Image processing and identifying system and method based on neural network - Google Patents
Image processing and identifying system and method based on neural network Download PDFInfo
- Publication number
- CN115830676A CN115830676A CN202211505112.3A CN202211505112A CN115830676A CN 115830676 A CN115830676 A CN 115830676A CN 202211505112 A CN202211505112 A CN 202211505112A CN 115830676 A CN115830676 A CN 115830676A
- Authority
- CN
- China
- Prior art keywords
- unit
- neural network
- brightness
- duration
- image acquisition
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 12
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 238000001514 detection method Methods 0.000 claims description 31
- 238000005286 illumination Methods 0.000 claims description 15
- 230000001815 facial effect Effects 0.000 claims description 10
- 238000003062 neural network model Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to an image processing and identifying system and method based on a neural network, belonging to the technical field of image data processing, wherein through the cooperation of an image acquisition unit, a neural network identification unit, a duration judgment unit, an angle deviation calculation unit and a camera shooting rotation adjustment unit, image acquisition can be carried out according to the actual face orientation of students, and the traditional 'human adaptive machine' mode is converted into a 'machine adaptive human' mode, so that the new upgrade of an entrance guard face image identifying system is realized; meanwhile, invalid face image information is screened through the duration judging unit, and related invalid data of the face in a changing state all the time are screened out, so that invalid actions are avoided; moreover, the preset duration can be identified to the student, and the situation that the student changes the face orientation all the time is avoided.
Description
Technical Field
The invention belongs to the technical field of image data processing, and particularly relates to an image processing and identifying system and method based on a neural network.
Background
At present, a simple card swiping access control system is installed on one part of domestic dormitory buildings of colleges and universities, and a human face image recognition access control system is installed on the other part of the dormitory buildings of the colleges and universities. To the current face image recognition access control system, students feed back more use defects, such as: the camera device for acquiring the face image data is in a fixed state, when the deviation of the face orientation of a student and the camera device in the camera shooting direction is large, the face image recognition cannot be successful, namely, the access control system cannot be smoothly opened, and the student can only adjust the camera shooting direction of the camera device by self in a head-biased manner, so that the experience feeling is poor.
Therefore, at present, it is necessary to design an image processing and recognition system, system and method based on neural network to solve the above problems.
Disclosure of Invention
The invention aims to provide an image processing and identifying system and method based on a neural network, which are used for solving the technical problems in the prior art, in the current-stage face image identification access control system, a camera device for acquiring face image data is in a fixed state, when the deviation between the face direction of a student and the camera shooting direction of the camera device is large, the face image identification cannot be successful, namely, the access control system cannot be opened smoothly, and the student can only adjust the camera head by self to adapt to the camera shooting direction of the camera device, so that the experience feeling is poor.
In order to achieve the purpose, the technical scheme of the invention is as follows:
the image processing and identifying system based on the neural network comprises an image acquisition unit, a neural network identifying unit, a duration judging unit, an angle deviation calculating unit, a camera shooting rotation adjusting unit and a main control unit; the main control unit is respectively connected with the image acquisition unit, the neural network identification unit, the duration judgment unit, the angle deviation calculation unit and the camera rotation regulation unit;
the image acquisition unit is used for acquiring facial image data of students;
the neural network identification unit is used for importing the facial image data into a preset neural network model and obtaining facial orientation information of students;
the duration judging unit is used for judging whether the duration for the student to maintain the face orientation information accords with preset duration;
the angle deviation calculation unit is used for comparing and analyzing the face orientation information and the orientation information of the image acquisition unit and calculating the angle deviation information of the face orientation information and the orientation information of the image acquisition unit;
the camera shooting rotation adjusting unit is used for adjusting the real-time orientation of the image acquisition unit according to the angle deviation information, so that the real-time orientation of the image acquisition unit is matched with the face orientation information.
Further, the image processing identification system is in operation; the main control unit controls the image acquisition unit and the neural network identification unit to be started, and controls the duration judgment unit, the angle deviation calculation unit and the camera rotation regulation unit to be closed;
when face orientation information of the student is obtained, the master control unit controls the duration judging unit to be started;
and when the student is judged to maintain that the duration of the face orientation information accords with the preset duration, the main control unit controls the angle deviation calculation unit and the camera shooting rotation adjustment unit to be started.
The device further comprises a height detection unit and a camera shooting lifting adjustment unit, wherein the height detection unit and the camera shooting lifting adjustment unit are respectively connected with the main control unit;
the height detection unit is used for detecting the height data of the students and judging whether the height data of the students is matched with the actual height of the image acquisition unit;
the camera shooting lifting adjusting unit is used for carrying out lifting adjustment on the image acquisition unit according to the student height data.
Further, the main control unit controls the height detection unit and the camera shooting lifting adjustment unit to be normally closed;
when the student is judged to keep the duration of the face orientation information to be in accordance with the preset duration, the main control unit controls the height detection unit to be started;
and if the student height data is judged not to be matched with the actual height of the image acquisition unit, the master control unit controls the camera shooting lifting adjusting unit to be started.
The system further comprises a brightness detection unit and a brightness adjusting unit, wherein the brightness detection unit and the brightness adjusting unit are respectively connected with the main control unit;
the brightness detection unit is used for detecting height data of the environment where the image acquisition unit is located and judging whether the brightness data reach standard brightness;
the brightness adjusting unit is used for providing standard brightness for the environment where the image acquisition unit is located.
Further, the main control unit controls the brightness detection unit and the brightness adjustment unit to be normally closed;
when the student is judged to keep the duration of the face orientation information to be in accordance with the preset duration, the main control unit controls the brightness detection unit to be started;
and if the brightness data is judged not to reach the standard brightness, the main control unit controls the brightness adjusting unit to be started.
Further, the device also comprises an illumination angle adjusting unit, wherein the illumination angle adjusting unit is connected with the main control unit;
the illumination angle adjusting unit is used for adjusting the illumination direction of the brightness adjusting unit according to the face orientation information.
Furthermore, the preset neural network model is trained by inputting historical data of the face images of the students and outputting historical data of face orientations corresponding to the face images of the students.
The image processing and identifying method based on the neural network adopts the image processing and identifying system based on the neural network to process and identify images.
Compared with the prior art, the invention has the beneficial effects that:
one of the beneficial effects of the scheme is that through the cooperation of the image acquisition unit, the neural network identification unit, the duration judgment unit, the angle deviation calculation unit and the camera rotation adjustment unit, the image acquisition can be carried out according to the actual face orientation of the student, the traditional 'human adaptive machine' mode is changed into a 'robot adaptive human' mode, and the new upgrade of the entrance guard face image identification system is realized; meanwhile, invalid face image information is screened through the duration judging unit, and related invalid data of the face in a changing state all the time are screened out, so that invalid actions are avoided; moreover, the preset duration can be identified to the student, and the situation that the student changes the face orientation all the time is avoided.
Drawings
Fig. 1 is a schematic diagram of a conventional face image recognition access control system according to an embodiment of the present disclosure;
fig. 2 is a schematic system structure diagram according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of the system operation principle according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the detailed description and specific examples, while indicating the preferred embodiment of the invention, are intended for purposes of illustration only and are not intended to limit the scope of the invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention.
In the current-stage face image recognition access control system, the camera device for acquiring the face image data is in a fixed state (as shown in fig. 1), when the deviation between the face orientation of a student and the camera shooting direction of the camera device is large, the face image recognition cannot be successful, namely, the access control system cannot be smoothly opened, and the student can only adjust the camera shooting direction of the camera device by self in a head-biased manner, so that the experience feeling is poor.
As shown in fig. 2, an image processing and recognition system based on a neural network is provided, which includes an image acquisition unit, a neural network recognition unit, a duration determination unit, an angle deviation calculation unit, a camera rotation adjustment unit, and a main control unit; the main control unit is respectively connected with the image acquisition unit, the neural network identification unit, the duration judgment unit, the angle deviation calculation unit and the camera rotation regulation unit;
the image acquisition unit is used for acquiring facial image data of students;
the neural network identification unit is used for importing the facial image data into a preset neural network model and obtaining facial orientation information of students;
the duration judging unit is used for judging whether the duration for the student to maintain the face orientation information accords with preset duration;
the angle deviation calculation unit is used for comparing and analyzing the face orientation information and the orientation information of the image acquisition unit and calculating the angle deviation information of the face orientation information and the orientation information of the image acquisition unit;
the camera shooting rotation adjusting unit is used for adjusting the real-time orientation of the image acquisition unit according to the angle deviation information, so that the real-time orientation of the image acquisition unit is matched with the face orientation information.
In the scheme, through the cooperation of the image acquisition unit, the neural network identification unit, the duration judgment unit, the angle deviation calculation unit and the camera rotation adjustment unit, the image acquisition can be carried out according to the actual face orientation of students, the traditional 'human adaptive machine' mode is changed into the 'machine adaptive robot' mode, and the new upgrade of the entrance guard face image identification system is realized; meanwhile, invalid face image information is screened through the duration judging unit, and related invalid data of the face in a changing state all the time are screened out, so that invalid actions are avoided; moreover, the preset duration can be identified to the student, and the situation that the student changes the face orientation all the time is avoided.
Further, as shown in FIG. 3, the image processing recognition system is running; the main control unit controls the image acquisition unit and the neural network identification unit to be started, and controls the duration judgment unit, the angle deviation calculation unit and the camera rotation regulation unit to be closed;
when face orientation information of the student is obtained, the master control unit controls the duration judging unit to be started;
and when the student is judged to maintain that the duration of the face orientation information accords with the preset duration, the main control unit controls the angle deviation calculation unit and the camera shooting rotation adjustment unit to be started.
In the scheme, when the image processing and recognizing system operates, the image acquisition unit and the neural network recognition unit are started firstly, the duration judgment unit is triggered to be started after face orientation information is obtained, the duration judgment unit is used for screening invalid face image information, and then the angle deviation calculation unit and the camera shooting rotation adjusting unit are started; invalid actions of a plurality of units in the system can be effectively avoided.
The device further comprises a height detection unit and a camera shooting lifting adjustment unit, wherein the height detection unit and the camera shooting lifting adjustment unit are respectively connected with the main control unit;
the height detection unit is used for detecting the height data of the students and judging whether the height data of the students is matched with the actual height of the image acquisition unit or not;
the camera shooting lifting adjusting unit is used for carrying out lifting adjustment on the image acquisition unit according to the student height data.
Further, the main control unit controls the height detection unit and the camera shooting lifting adjustment unit to be normally closed;
when the student is judged to keep the duration of the face orientation information to be in accordance with the preset duration, the main control unit controls the height detection unit to be started;
and if the student height data is judged not to be matched with the actual height of the image acquisition unit, the master control unit controls the camera shooting lifting adjusting unit to be started.
In the above-mentioned scheme, after satisfying the orientation problem, probably because the high problem between image acquisition end and the student influences the face identification precision, through the cooperation of height detecting element, the lift adjustment unit of making a video recording, can overcome the high unmatched problem.
The system further comprises a brightness detection unit and a brightness adjusting unit, wherein the brightness detection unit and the brightness adjusting unit are respectively connected with the main control unit;
the brightness detection unit is used for detecting height data of the environment where the image acquisition unit is located and judging whether the brightness data reach standard brightness;
the brightness adjusting unit is used for providing standard brightness for the environment where the image acquisition unit is located.
Further, the main control unit controls the brightness detection unit and the brightness adjustment unit to be normally closed;
when the student is judged to keep the duration of the face orientation information to be in accordance with the preset duration, the main control unit controls the brightness detection unit to be started;
and if the brightness data is judged not to reach the standard brightness, the main control unit controls the brightness adjusting unit to be started.
In the above scheme, after the orientation problem is met, the face recognition precision is possibly influenced because of the brightness problem of the image acquisition end, and the problem that the brightness does not reach the standard can be overcome through the matching of the brightness detection unit and the brightness adjusting unit.
Further, the device also comprises an illumination angle adjusting unit, wherein the illumination angle adjusting unit is connected with the main control unit;
the illumination angle adjusting unit is used for adjusting the illumination direction of the brightness adjusting unit according to the face orientation information.
Furthermore, the preset neural network model is trained by inputting historical data of the face images of the students and outputting historical data of face orientations corresponding to the face images of the students.
In the above-mentioned scheme, after satisfying the luminance problem, probably because illumination equipment's illumination direction and the unmatched problem of student's facial orientation influence face identification precision, can overcome through illumination angle adjusting unit.
The image processing and identifying method based on the neural network adopts the image processing and identifying system based on the neural network to process and identify images.
The above are preferred embodiments of the present invention, and all changes made according to the technical scheme of the present invention that produce functional effects do not exceed the scope of the technical scheme of the present invention belong to the protection scope of the present invention.
Claims (9)
1. The image processing and identifying system based on the neural network is characterized by comprising an image acquisition unit, a neural network identifying unit, a duration judging unit, an angle deviation calculating unit, a camera shooting rotation adjusting unit and a main control unit; the main control unit is respectively connected with the image acquisition unit, the neural network identification unit, the duration judgment unit, the angle deviation calculation unit and the camera rotation regulation unit;
the image acquisition unit is used for acquiring facial image data of students;
the neural network identification unit is used for importing the facial image data into a preset neural network model and obtaining facial orientation information of students;
the duration judging unit is used for judging whether the duration for the student to maintain the face orientation information accords with preset duration;
the angle deviation calculation unit is used for comparing and analyzing the face orientation information and the orientation information of the image acquisition unit and calculating the angle deviation information of the face orientation information and the orientation information of the image acquisition unit;
the camera shooting rotation adjusting unit is used for adjusting the real-time orientation of the image acquisition unit according to the angle deviation information, so that the real-time orientation of the image acquisition unit is matched with the face orientation information.
2. The neural network-based image processing identification system of claim 1, wherein the image processing identification system is run-time; the main control unit controls the image acquisition unit and the neural network identification unit to be started, and controls the duration judgment unit, the angle deviation calculation unit and the camera rotation regulation unit to be closed;
when face orientation information of the student is obtained, the master control unit controls the duration judging unit to be started;
and when the student is judged to maintain that the duration of the face orientation information accords with the preset duration, the main control unit controls the angle deviation calculation unit and the camera shooting rotation adjustment unit to be started.
3. The image processing and identifying system based on the neural network as claimed in claim 2, further comprising a height detection unit and a camera up-down adjustment unit, wherein the height detection unit and the camera up-down adjustment unit are respectively connected with the main control unit;
the height detection unit is used for detecting the height data of the students and judging whether the height data of the students is matched with the actual height of the image acquisition unit;
the camera shooting lifting adjusting unit is used for carrying out lifting adjustment on the image acquisition unit according to the student height data.
4. The image processing and identifying system based on the neural network as claimed in claim 3, wherein the main control unit controls the height detection unit and the camera shooting lifting adjustment unit to be normally closed;
when the duration that the student maintains the face orientation information is judged to accord with the preset duration, the main control unit controls the height detection unit to be started;
and if the student height data is judged not to be matched with the actual height of the image acquisition unit, the main control unit controls the camera shooting lifting adjusting unit to be started.
5. The image processing and identifying system based on the neural network as claimed in claim 2, further comprising a brightness detection unit and a brightness adjustment unit, wherein the brightness detection unit and the brightness adjustment unit are respectively connected with the main control unit;
the brightness detection unit is used for detecting height data of the environment where the image acquisition unit is located and judging whether the brightness data reach standard brightness;
the brightness adjusting unit is used for providing standard brightness for the environment where the image acquisition unit is located.
6. The image processing and identifying system based on the neural network as claimed in claim 5, wherein the main control unit controls the brightness detection unit and the brightness adjustment unit to be normally closed;
when the student is judged to keep the duration of the face orientation information to be in accordance with the preset duration, the main control unit controls the brightness detection unit to be started;
and if the brightness data is judged not to reach the standard brightness, the main control unit controls the brightness adjusting unit to be started.
7. The neural network-based image processing and identifying system according to claim 6, further comprising an illumination angle adjusting unit, wherein the illumination angle adjusting unit is connected with the main control unit;
the illumination angle adjusting unit is used for adjusting the illumination direction of the brightness adjusting unit according to the face orientation information.
8. The image processing and recognition system based on the neural network as claimed in claim 1, wherein the preset neural network model is trained by inputting historical data of student face images and outputting historical data of face orientations corresponding to the student face images.
9. The image processing and identifying method based on the neural network is characterized in that the image processing and identifying method based on the neural network is adopted for image processing and identifying according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211505112.3A CN115830676A (en) | 2022-11-28 | 2022-11-28 | Image processing and identifying system and method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211505112.3A CN115830676A (en) | 2022-11-28 | 2022-11-28 | Image processing and identifying system and method based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115830676A true CN115830676A (en) | 2023-03-21 |
Family
ID=85532356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211505112.3A Pending CN115830676A (en) | 2022-11-28 | 2022-11-28 | Image processing and identifying system and method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115830676A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116631105A (en) * | 2023-07-24 | 2023-08-22 | 成都阿卡林科技发展有限公司 | Intelligent residence electronic safety monitoring system and method based on big data |
-
2022
- 2022-11-28 CN CN202211505112.3A patent/CN115830676A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116631105A (en) * | 2023-07-24 | 2023-08-22 | 成都阿卡林科技发展有限公司 | Intelligent residence electronic safety monitoring system and method based on big data |
| CN116631105B (en) * | 2023-07-24 | 2023-12-01 | 宜昌优智科技有限公司 | Intelligent residence electronic safety monitoring system and method based on big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021036436A1 (en) | Facial recognition method and apparatus | |
| US7120278B2 (en) | Person recognition apparatus | |
| CN110728225A (en) | High-speed face searching method for attendance checking | |
| US9449217B1 (en) | Image authentication | |
| US20220318369A1 (en) | Face recognition system and method capable of updating registered face templates | |
| CN115830676A (en) | Image processing and identifying system and method based on neural network | |
| CN103902970A (en) | Automatic fingerprint gesture estimation method and system | |
| CN109542233A (en) | A kind of lamp control system based on dynamic gesture and recognition of face | |
| CN112906529A (en) | Face recognition light supplementing method and device, face recognition equipment and face recognition system | |
| CN112040198A (en) | Intelligent water meter reading identification system and method based on image processing | |
| CN110580452A (en) | multi-template face automatic input method in face recognition system based on video | |
| CN112907803B (en) | Automatic AI (Artificial Intelligence) adjustment intelligent access control system and access control detection method | |
| JP2005084824A (en) | Face image collation apparatus and face image collation method and passage controller | |
| CN111932754B (en) | Laboratory entrance guard verification system and verification method | |
| CN114708821B (en) | Intelligent LED display screen system based on multi-sensor data fusion | |
| CN107220612B (en) | Fuzzy face discrimination method taking high-frequency analysis of local neighborhood of key points as core | |
| CN109190530A (en) | One kind being based on recognition of face big data algorithm | |
| CN108830217A (en) | A kind of signature automatic distinguishing method based on the study of fuzzy mean Hash | |
| CN115464557A (en) | Method for adjusting mobile robot operation based on path and mobile robot | |
| CN111932758A (en) | Intelligent access control system based on face recognition technology | |
| CN118172860B (en) | Intelligent campus access control system based on identity recognition | |
| CN106340139A (en) | VTM (Virtual Teller Machine) capable of automatically recognizing human face | |
| CN111860047A (en) | Face rapid identification method based on deep learning | |
| CN207489119U (en) | Bio-identification access control system | |
| CN110334686A (en) | A kind of robot visible light portrait identification method |
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 |