CN114299579A - Image recognition system and method based on convolutional neural algorithm - Google Patents
Image recognition system and method based on convolutional neural algorithm Download PDFInfo
- Publication number
- CN114299579A CN114299579A CN202111627045.8A CN202111627045A CN114299579A CN 114299579 A CN114299579 A CN 114299579A CN 202111627045 A CN202111627045 A CN 202111627045A CN 114299579 A CN114299579 A CN 114299579A
- Authority
- CN
- China
- Prior art keywords
- module
- face
- convolutional neural
- camera
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an image recognition system and a recognition method based on a convolution neural algorithm, wherein the image recognition system based on the convolution neural algorithm comprises external equipment and an internal system, the external equipment comprises a bracket, an electric telescopic rod, a mounting plate, a camera, a control panel and a display screen, the internal system comprises a master control end, a display end and a working end, and the recognition method of the image recognition system based on the convolution neural algorithm comprises the following steps of installing the external equipment, and using the external equipment and the internal system to start working. According to the scheme, the height of the camera is automatically adjusted and controlled by related personnel, so that the camera can be suitable for people with different heights, and the efficiency and accuracy of face image recognition are favorably ensured.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to an image recognition system and method based on a convolution neural algorithm.
Background
The convolutional neural network is a feedforward neural network containing convolutional calculation and having a deep structure, is one of representative algorithms for deep learning, has a characteristic learning capability, can perform translation invariant classification on input information according to a hierarchical structure of the convolutional neural network, is also called as a translation invariant artificial neural network, and is rapidly developed after twenty-first century along with the proposal of a deep learning theory and the improvement of numerical computing equipment, and is applied to the fields of computer vision, natural language processing and the like.
The image recognition is a technology for processing, analyzing and understanding images by using a computer to recognize various targets and objects in different modes, and is a practical application of applying a deep learning algorithm; image recognition technology at present is generally divided into face recognition and commodity recognition, and the face recognition is mainly applied to security inspection, identity verification and mobile payment; the commodity identification is mainly applied to the commodity circulation process, in particular to the unmanned retail fields such as unmanned goods shelves, intelligent retail cabinets and the like; the traditional image identification process is divided into four steps: the method comprises the steps of image acquisition, image preprocessing, feature extraction and image recognition, wherein the image obtained by image processing is subjected to feature extraction and classification by the image recognition, and a neural network method is a common recognition method.
Now, each district, house building or company enterprise office building often can use the entrance guard or the equipment of checking the card that uses face identification as the basis, through the scanning to people's facial feature, and compare with the database, judge whether for the regional crowd of entrance guard that can get into, and automatic recording business turn over time etc., however, the device of current face scanning generally all is fixed mounting at certain high position, often appear too high or the low condition of crossing to the people of difference, the condition of face identification is not convenient for carry out, especially the people who gets into simultaneously are too much, the device of face scanning just scans the face of a plurality of differences simultaneously easily, lead to face image recognition efficiency step-down or unable accurate recognition.
Disclosure of Invention
The invention mainly aims to provide an image recognition system based on a convolutional neural algorithm, so as to solve the problem that in the related art, a face scanning device of an entrance guard or a card punching device is fixedly arranged at a certain height position, and the recognition efficiency is lowered or the face cannot be accurately recognized due to the fact that different people often have too high or too low conditions.
In order to achieve the above object, the present invention provides an image recognition system based on a convolutional neural algorithm, comprising an external device and an internal system;
the external equipment comprises a support, an electric telescopic rod, a mounting plate, a camera, a control panel and a display screen, wherein the electric telescopic rod is fixedly mounted at the top of the support, the mounting plate is fixedly connected to the upper end of the electric telescopic rod, the camera is fixedly mounted at the top of the mounting plate, the control panel is fixedly mounted on the upper side of the support through a support rod, a control button is arranged on the control panel, the control button is in telecommunication connection with the electric telescopic rod, the display screen is fixedly mounted on the upper side of the mounting plate through a fixing rod, the display screen is in telecommunication connection with the camera, the number of the fixing rods is two, and the two fixing rods are mutually symmetrical;
the internal system comprises a master control end, a display end and a working end;
the master control end is used for controlling the work of the display end and the work end;
the display end is in electric communication with the master control end and is used for displaying an image identification result;
and the working end is in electric connection with the master control end and is used for carrying out related work of image identification.
In one embodiment of the invention, the support comprises a base and four support legs, the support legs are fixedly welded at the bottom of the base, and the four support legs are distributed at four corners of the base.
In one embodiment of the invention, the lower ends of the supporting legs are fixedly connected with a base plate, the surface of the base plate is a rough surface, and a plurality of mounting holes are uniformly formed in the base plate.
In one embodiment of the invention, two guide rods are fixedly welded on the top of the base, the upper ends of the guide rods penetrate through the mounting plate in a sliding manner, and the two guide rods are symmetrically distributed on two sides of the electric telescopic rod.
In one embodiment of the invention, the master control end comprises a central processing module, a logging module, a storage module, a statistical module and a setting module;
the central processing module is used for calculating all relevant data including images and personal information;
the input module is in telecommunication connection with the central processing module and is used for uploading images and personal information of related personnel;
the storage module is in telecommunication connection with the central processing module and is used for storing images and personal information of related personnel;
the statistical module is in telecommunication connection with the central processing module and is used for classifying and counting the images and personal information of related personnel;
the setting module is in telecommunication connection with the central processing module and is used for carrying out relevant setting on system operation.
In one embodiment of the present invention, the display end includes a first display module and a second display module;
the first display module is in telecommunication connection with the central processing module, is in telecommunication connection with the display screen, and is used for displaying face images of related persons shot by the camera;
the second display module is in telecommunication connection with the central processing module and is used for displaying the face images of the related personnel shot by the camera to background operation management personnel.
In one embodiment of the invention, the working end comprises an image acquisition module, a face detection module, a learning training module and a face recognition module;
the image acquisition module is in telecommunication connection with the central processing module, is in telecommunication connection with the camera and is used for acquiring face image information of related personnel;
the face detection module is in telecommunication connection with the central processing module and the image acquisition module, and performs feature extraction and subsequent identification on face image information of related personnel acquired by the image acquisition module through a convolutional neural network algorithm;
the learning training module is in telecommunication connection with the central processing module, trains the face image by adopting a convolutional neural network algorithm to obtain a convolutional neural network model, and is connected with the face detection module and the face recognition module;
the face recognition module is in telecommunication connection with the central processing module, the face recognition module is in telecommunication connection with the face detection module, and the face recognition module performs recognition work according to the feature information of the face image information of the related personnel extracted by the face detection module.
In one embodiment of the invention, the camera is configured as a high-definition wide-angle camera.
In one embodiment of the invention, the display is configured as a high-definition liquid crystal display.
The invention also provides an identification method of the image identification system based on the convolution neural algorithm, which comprises the following steps:
s1, installing external equipment: firstly, placing external equipment at an entrance of a residential area, a residential building or an office building of a company and an enterprise, and then fixedly installing the external equipment at the entrance by using objects such as bolts through the installation holes on the base plate;
s2, using an external device: when related personnel need to enter a community, a residential building or an office building of a company and an enterprise, the personnel firstly stand facing to the camera, then use the control button to control the electric telescopic rod to work, drive the mounting plate to lift, regulate and control the camera to be parallel and opposite to the face of the person, and enable the face of the person to be completely displayed on the display screen;
s3, the internal system starts to work:
s301, the image acquisition module acquires face image information of related personnel through a camera;
s302, the face detection module performs feature extraction on face image information of related personnel acquired by the image acquisition module through a convolutional neural network algorithm;
s303, training the face image by adopting a convolutional neural network algorithm through a learning training module to obtain a convolutional neural network model;
s304, the face recognition module performs recognition work according to the feature information of the face image information of the related personnel extracted by the face detection module;
s305, if the face data of the person entering and exiting are allowed to be successfully matched, the entrance guard equipment is opened and released.
Compared with the prior art, the invention has the beneficial effects that: when the image recognition system based on the convolutional neural algorithm is used, when related personnel need to enter a residential area, a residential building or an office building of a company and enterprise, the related personnel firstly stand facing to the camera, then the control button is used for controlling the electric telescopic rod to work to drive the mounting plate to lift, the camera is regulated and controlled to be parallel and opposite to the human face, so that the human face is completely displayed on the display screen, the height of the camera is automatically regulated and controlled by the related personnel is realized, the camera can be suitable for people with different heights, then, the image acquisition module acquires the human face image information of the related personnel through the camera, the human face detection module performs feature extraction on the human face image information of the related personnel acquired by the image acquisition module through the convolutional neural network algorithm, the learning and training module trains the human face image by adopting the convolutional neural network algorithm to acquire the convolutional neural network model, the face recognition module carries out recognition work according to the feature information of the face image information of the related personnel extracted by the face detection module, and if the face data of the personnel entering and exiting are allowed to be successfully matched, the access control equipment is opened and released, so that the face image recognition efficiency and accuracy can be guaranteed.
Drawings
Fig. 1 is a schematic diagram of a main view structure of an external device of an image recognition system based on a convolutional neural algorithm provided in an embodiment of the present invention;
FIG. 2 is a system block diagram of an internal system of an image recognition system based on a convolutional neural algorithm provided according to an embodiment of the present invention;
FIG. 3 is a system block diagram of a master control end of the image recognition system based on the convolutional neural algorithm provided in the embodiment of the present invention;
FIG. 4 is a system block diagram of a display end of an image recognition system based on a convolutional neural algorithm provided according to an embodiment of the present invention;
fig. 5 is a system block diagram of a working end of an image recognition system based on a convolutional neural algorithm according to an embodiment of the present invention.
In the figure: 100. an external device; 110. a support; 111. a base; 112. a support leg; 113. a base plate; 114. a guide bar; 120. an electric telescopic rod; 130. mounting a plate; 140. a camera; 150. a control panel; 160. a display screen; 170. a support bar; 180. a control button; 190. and (5) fixing the rod.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged under appropriate circumstances in order to facilitate the description of the embodiments of the invention herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the present invention, the terms "upper", "lower", "left", "right", "front", "rear", "top", "bottom", "inner", "outer", "center", "vertical", "horizontal", "lateral", "longitudinal", and the like indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings. These terms are used primarily to better describe the invention and its embodiments and are not intended to limit the indicated devices, elements or components to a particular orientation or to be constructed and operated in a particular orientation.
Moreover, some of the above terms may be used to indicate other meanings besides the orientation or positional relationship, for example, the term "on" may also be used to indicate some kind of attachment or connection relationship in some cases. The specific meanings of these terms in the present invention can be understood by those skilled in the art as appropriate.
In addition, the term "plurality" shall mean two as well as more than two.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
Example 1
Referring to fig. 1 to 5, the present invention provides an image recognition system based on a convolutional neural algorithm, which includes an external device 100 and an internal system, wherein the external device 100 is installed at an entrance of a cell, a residential building, or an office building of a company and an enterprise, and the internal system is used for performing image recognition of face information.
Referring to fig. 1, the external device 100 includes a bracket 110, an electric telescopic rod 120, a mounting plate 130, a camera 140, a control panel 150, and a display screen 160;
the support 110 comprises a base 111 and four legs 112, wherein the legs 112 are fixedly welded at the bottom of the base 111 and used for supporting the base 111, the four legs 112 are arranged, and the four legs 112 are distributed at the four corners of the base 111, so that the legs 112 can support the legs 112 more stably;
the lower ends of the supporting legs 112 are fixedly connected with the backing plates 113, the surfaces of the backing plates 113 are rough surfaces, friction between the backing plates 113 and the ground is increased, the supporting legs 112 and the backing plates 113 can be placed on the ground more stably, the backing plates 113 are uniformly provided with a plurality of mounting holes, the backing plates 113 can be fixedly mounted on the ground by using objects such as bolts, and therefore the external equipment 100 is more stable;
the electric telescopic rod 120 is fixedly installed at the top of the bracket 110 and used for driving the installation plate 130 and the camera 140 to ascend and descend, so that the camera 140 is suitable for people with different heights;
the mounting plate 130 is fixedly connected to the upper end of the electric telescopic rod 120 and is used for mounting the camera 140 and the display screen 160;
in order to enable the mounting plate 130 to be lifted more stably, the guide rods 114 are fixedly welded to the top of the base 111, the upper ends of the guide rods 114 penetrate through the mounting plate 130 in a sliding manner, two guide rods 114 are arranged, and the two guide rods 114 are symmetrically distributed on two sides of the electric telescopic rod 120;
the camera 140 is fixedly installed at the top of the installation plate 130 and is used for collecting face information of people who need to enter a community, a residential building or an office building of a company and an enterprise;
the camera 140 is configured as a high-definition wide-angle camera;
the control panel 150 is fixedly arranged on the upper side of the bracket 110 through a support rod 170, a control button 180 is arranged on the control panel 150, and the control button 180 is in telecommunication connection with the electric telescopic rod 120 and is used for controlling the work of the electric telescopic rod 120 so that a person needing to enter a community, a residential building or an office building of a company and an enterprise can automatically adjust the height of the camera 140;
the display screen 160 is fixedly arranged on the upper side of the mounting plate 130 through a fixing rod 190, the display screen 160 is in telecommunication connection with the camera 140 and is used for displaying the face shot by the camera 140 so that people who need to enter a cell, a residential building or an office building of a company and an enterprise can independently watch the shooting condition of the camera 140;
the display 160 is configured as a high-definition display;
the fixing bars 190 are provided in two, and the two fixing bars 190 are symmetrical to each other, so that the display screen 160 can be more stably supported.
Referring to fig. 2, fig. 3, fig. 4 and fig. 5, the internal system includes a master control end, a display end and a working end;
the master control end is used for controlling the work of the display end and the work end;
the master control end comprises a central processing module, an input module, a storage module, a statistical module and a setting module;
the central processing module is used for calculating all relevant data including images and personal information;
the input module is in telecommunication connection with the central processing module and is used for uploading the image and personal information of the related personnel;
the storage module is in telecommunication connection with the central processing module and is used for storing images and personal information of related personnel;
the statistical module is in telecommunication connection with the central processing module and is used for classifying and counting the images and personal information of related personnel;
the setting module is in telecommunication connection with the central processing module and is used for carrying out relevant setting on system operation;
the display end is in electric communication with the master control end and is used for displaying the image recognition result;
the display end comprises a first display module and a second display module;
the first display module is in telecommunication connection with the central processing module, is in telecommunication connection with the display screen 160, and is used for displaying face images of relevant persons shot by the camera 140;
the second display module is in telecommunication connection with the central processing module and is used for displaying the face images of the related personnel shot by the camera 140 to the background operation manager;
the working end is in electric communication connection with the master control end and is used for carrying out relevant work of image recognition;
the working end comprises an image acquisition module, a face detection module, a learning training module and a face recognition module;
the image acquisition module is in telecommunication connection with the central processing module, is in telecommunication connection with the camera 140 and is used for acquiring face image information of related personnel;
the face detection module is in telecommunication connection with the central processing module and the image acquisition module, and performs feature extraction and subsequent identification on face image information of related personnel acquired by the image acquisition module through a convolutional neural network algorithm;
the learning training module is in telecommunication connection with the central processing module, trains the face image by adopting a convolutional neural network algorithm to obtain a convolutional neural network model, and is connected with the face detection module and the face recognition module;
the face recognition module is in telecommunication connection with the central processing module, the face recognition module is in telecommunication connection with the face detection module, and the face recognition module performs recognition work according to the feature information of the face image information of the related personnel extracted by the face detection module.
The invention also provides an identification method of the image identification system based on the convolution neural algorithm, which comprises the following steps:
s1, mounting external device 100: firstly, placing the external equipment 100 at an entrance of a community, a residential building or an office building of a company and an enterprise, and then fixedly installing the external equipment 100 at the entrance by using objects such as bolts through the installation holes on the base plate 113;
s2, using external device 100: when a relevant person needs to enter a community, a residential building or an office building of a company and an enterprise, the person stands facing the camera 140, then controls the electric telescopic rod 120 to work by using the control button 180, drives the mounting plate 130 to lift, controls the camera 140 to be parallel and opposite to the face, and enables the face to be displayed on the display screen 160 completely;
s3, the internal system starts to work:
s301, the image acquisition module acquires face image information of related personnel through the camera 140;
s302, the face detection module performs feature extraction on face image information of related personnel acquired by the image acquisition module through a convolutional neural network algorithm;
s303, training the face image by adopting a convolutional neural network algorithm through a learning training module to obtain a convolutional neural network model;
s304, the face recognition module performs recognition work according to the feature information of the face image information of the related personnel extracted by the face detection module;
s305, if the face data of the person entering and exiting are allowed to be successfully matched, the entrance guard equipment is opened and released.
Specifically, the working principle of the image recognition system based on the convolutional neural algorithm is as follows: when the device is used, firstly, the external device 100 is placed at an entrance of a residential building, a company and enterprise building, then the external device 100 is fixedly installed at the entrance by using bolts and other articles through the installation holes on the base plate 113, then, when related personnel need to enter the residential building, the residential building or the company and enterprise building, the relevant personnel firstly stand facing the camera 140, then the control button 180 is used for controlling the electric telescopic rod 120 to work to drive the installation plate 130 to lift, the camera 140 is regulated and controlled to be parallel and opposite to the human face, so that the human face is completely displayed on the display screen 160, and finally, the image acquisition module acquires the human face image information of the related personnel through the camera 140,
the face detection module extracts the features of the face image information of the related personnel acquired by the image acquisition module through a convolutional neural network algorithm, the learning training module trains the face image through the convolutional neural network algorithm to acquire a convolutional neural network model, the face recognition module performs recognition work according to the feature information of the face image information of the related personnel extracted by the face detection module, and if the matching of the face data of the personnel entering and exiting is allowed to be successful, the access control equipment is opened and released.
It should be noted that: the model specifications of the electric telescopic rod 120, the camera 140 and the display screen 160 need to be determined by type selection according to the actual specification of the device, and the specific type selection calculation method adopts the prior art in the field, so detailed description is omitted.
The power supply and the principle of the power supply of the power extension pole 120, the camera 140 and the display screen 160 will be clear to those skilled in the art and will not be described in detail herein.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An image recognition system based on a convolutional neural algorithm is characterized by comprising
External equipment (100), external equipment (100) includes support (110), electric telescopic handle (120), mounting panel (130), camera (140), control panel (150) and display screen (160), electric telescopic handle (120) fixed mounting is in the top of support (110), mounting panel (130) fixed connection is in the upper end of electric telescopic handle (120), camera (140) fixed mounting is in the top of mounting panel (130), control panel (150) pass through bracing piece (170) fixed mounting in the upside of support (110), be provided with control button (180) on control panel (150), control button (180) with electric telescopic handle (120) telecommunications connection, display screen (160) pass through dead lever (190) fixed mounting in the upside of mounting panel (130), display screen (160) with camera (140) telecommunications connection, two fixing rods (190) are arranged, and the two fixing rods (190) are symmetrical to each other;
the internal system comprises a master control end, a display end and a working end;
the master control end is used for controlling the work of the display end and the work end;
the display end is in electric communication with the master control end and is used for displaying an image identification result;
and the working end is in electric connection with the master control end and is used for carrying out related work of image identification.
2. The convolutional neural algorithm-based image recognition system as claimed in claim 1, wherein the support (110) comprises a base (111) and four legs (112), the legs (112) are fixedly welded to the bottom of the base (111), the four legs (112) are provided, and the four legs (112) are distributed at four corners of the base (111).
3. The image recognition system based on the convolutional neural algorithm as claimed in claim 2, wherein a pad plate (113) is fixedly connected to the lower end of the leg (112), the surface of the pad plate (113) is provided with a rough surface, and a plurality of mounting holes are uniformly formed in the pad plate (113).
4. The image recognition system based on the convolutional neural algorithm as claimed in claim 2, wherein a guide rod (114) is fixedly welded on the top of the base (111), the upper end of the guide rod (114) slidably penetrates through the mounting plate (130), two guide rods (114) are arranged, and the two guide rods (114) are symmetrically distributed on two sides of the electric telescopic rod (120).
5. The image recognition system based on the convolutional neural algorithm as claimed in claim 1, wherein the master control end comprises a central processing module, a recording module, a storage module, a statistical module and a setting module;
the central processing module is used for calculating all relevant data including images and personal information;
the input module is in telecommunication connection with the central processing module and is used for uploading images and personal information of related personnel;
the storage module is in telecommunication connection with the central processing module and is used for storing images and personal information of related personnel;
the statistical module is in telecommunication connection with the central processing module and is used for classifying and counting the images and personal information of related personnel;
the setting module is in telecommunication connection with the central processing module and is used for carrying out relevant setting on system operation.
6. The convolutional neural algorithm-based image recognition system of claim 5, wherein said display terminal comprises a first display module and a second display module;
the first display module is in telecommunication connection with the central processing module, is in telecommunication connection with the display screen (160), and is used for displaying a face image of a relevant person shot by the camera (140);
the second display module is in telecommunication connection with the central processing module and is used for displaying the face images of the related persons shot by the camera (140) to a background operation manager.
7. The convolutional neural algorithm-based image recognition system of claim 5, wherein the working end comprises an image acquisition module, a face detection module, a learning training module and a face recognition module;
the image acquisition module is in telecommunication connection with the central processing module, is in telecommunication connection with the camera (140), and is used for acquiring face image information of related personnel;
the face detection module is in telecommunication connection with the central processing module and the image acquisition module, and performs feature extraction and subsequent identification on face image information of related personnel acquired by the image acquisition module through a convolutional neural network algorithm;
the learning training module is in telecommunication connection with the central processing module, trains the face image by adopting a convolutional neural network algorithm to obtain a convolutional neural network model, and is connected with the face detection module and the face recognition module;
the face recognition module is in telecommunication connection with the central processing module, the face recognition module is in telecommunication connection with the face detection module, and the face recognition module performs recognition work according to the feature information of the face image information of the related personnel extracted by the face detection module.
8. The convolutional neural algorithm-based image recognition system of claim 1, wherein the camera (140) is configured as a high-definition wide-angle camera.
9. An image recognition system based on a convolutional neural algorithm as claimed in claim 1, characterized in that the display (160) is configured as a high-definition display.
10. A recognition method of an image recognition system based on a convolution neural algorithm is characterized by comprising the following steps:
s1, mounting external device (100): firstly, placing the external equipment (100) at an entrance of a community, a residential building or an office building of a company and an enterprise, and then fixedly installing the external equipment (100) at the entrance by using objects such as bolts through the installation holes on the backing plate (113);
s2, using external device (100): when related personnel need to enter a residential area, a residential building or an office building of a company and an enterprise, the personnel firstly stand facing the camera (140), then use the control button (180) to control the electric telescopic rod (120) to work, drive the mounting plate (130) to lift, regulate and control the camera (140) to be parallel and opposite to the human face, and enable the human face to be completely displayed on the display screen (160);
s3, the internal system starts to work:
s301, the image acquisition module acquires face image information of related personnel through a camera (140);
s302, the face detection module performs feature extraction on face image information of related personnel acquired by the image acquisition module through a convolutional neural network algorithm;
s303, training the face image by adopting a convolutional neural network algorithm through a learning training module to obtain a convolutional neural network model;
s304, the face recognition module performs recognition work according to the feature information of the face image information of the related personnel extracted by the face detection module;
s305, if the face data of the person entering and exiting are allowed to be successfully matched, the entrance guard equipment is opened and released.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111627045.8A CN114299579A (en) | 2021-12-28 | 2021-12-28 | Image recognition system and method based on convolutional neural algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111627045.8A CN114299579A (en) | 2021-12-28 | 2021-12-28 | Image recognition system and method based on convolutional neural algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114299579A true CN114299579A (en) | 2022-04-08 |
Family
ID=80971299
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111627045.8A Pending CN114299579A (en) | 2021-12-28 | 2021-12-28 | Image recognition system and method based on convolutional neural algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114299579A (en) |
-
2021
- 2021-12-28 CN CN202111627045.8A patent/CN114299579A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112562161A (en) | Based on 5G thing networking and AI intelligent entrance guard integrated management system | |
| CN109902628B (en) | Library seat management system based on vision thing networking | |
| CN201993822U (en) | School safety management system | |
| CN110660472A (en) | Hospital management early warning system and method based on face recognition technology | |
| CN110414381A (en) | Tracing type face identification system | |
| Thein et al. | Students’ attendance management system based on RFID and fingerprint reader | |
| CN109903412A (en) | A kind of intelligent check class attendance system based on face recognition technology | |
| CN110689389A (en) | Computer vision-based shopping list automatic maintenance method and device, storage medium and terminal | |
| CN114299579A (en) | Image recognition system and method based on convolutional neural algorithm | |
| CN107451797A (en) | Based on the labor service big data management system and application method for referring to hand vein recognition | |
| CN112395948A (en) | Intelligent sign-in system integrating face recognition and data analysis | |
| CN110570571A (en) | Standing-type identity authentication device and method integrating functions of people and certificate | |
| CN113326747A (en) | Teaching worker face recognition attendance checking method and system | |
| CN107798312B (en) | Automatic attendance checking method based on visual head detection | |
| CN107203647B (en) | Student information acquisition method and device based on biological characteristics | |
| CN114205565B (en) | Monitoring video distribution method and system | |
| Gomathy et al. | Face recognition based student detail collection using opencv | |
| CN210924687U (en) | Foreign person classification management and control system based on face recognition technology | |
| CN207198963U (en) | A kind of hotel's intelligence foreground | |
| CN111738884A (en) | Student behavior diagnosis and management method based on intelligent campus student position information | |
| CN206805584U (en) | A kind of comparison type testimony of a witness veritifies device | |
| CN112216043A (en) | Wisdom library | |
| CN218413614U (en) | Information acquisition device based on thing networking campus management | |
| CN210354118U (en) | Unmanned foreground | |
| Yang et al. | Research on the application of face deep learning technology in university management |
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 |