An eye recognition access control system based on neural network

Abstract

The present invention discloses an eyeball recognition access control system based on a neural network, which includes an information storage module, an identity recognition module, an image acquisition module, an eyeball information processing and analysis module, a control module, a communication and alarm module, an illuminance acquisition module, a daylight simulation module, a distance sensing module, a processing and calculation module, an infrared thermal imaging module, and a mobile phone application terminal. The beneficial effects of the present invention are as follows: By calculating the length of the line connecting the vertices of the inner canthus and the outer canthus and the angle formed between the line and the horizontal line, it is determined whether the eyeball information of the recognized person is the same as the eyeball information of the household granted the door opening permission. The requirement for the acquisition lens is low, thus solving the problems of high equipment cost and difficult promotion. By collecting the environmental light intensity and performing light supplementation, the angle of light supplementation is adjusted according to the distance between the person to be recognized and the acquisition device, making the image captured by the lens clear and avoiding the situation of misrecognition.

Description

Technical Field

[0001] The present invention relates to the technical field of eye recognition access control, and specifically provides an eye recognition access control system based on a neural network. Background Art

[0002] Access control refers to the prohibited permission of a "door", which is a kind of guard against the "door". Here, the "door" generally refers to various passages that can be passed through, including doors for people to pass through, doors for vehicles to pass through, etc. The access control security management system at the entrance and exit is a new type of modern security management system. It integrates microcomputer automatic recognition technology and modern security management measures, and involves many new technologies such as electronics, machinery, optics, computer technology, communication technology, and biotechnology. It is an effective measure to solve the security prevention management at the entrances and exits of important departments and is applicable to various places. Eye recognition technology is a biometric technology that performs identity recognition based on the eye patterns on both sides of the user's eye iris. It is a new biometric technology developed after face recognition and fingerprint recognition.

[0003] Existing eye recognition technology is based on the unique characteristics of the iris, that is, the information contained in each person's iris is different, and the possibility of having exactly the same iris tissue is much lower than that of other tissues. However, iris recognition still has many disadvantages. For example, the size of the device for obtaining images is too large, and it is extremely difficult to optimize the size. The cost of iris recognition devices is relatively high, making it difficult to promote. In addition, the lens for collecting the iris may cause image distortion, which affects the reliability of iris recognition. The clarity of the image collected by the lens is also related to the light intensity. If the light intensity is insufficient, there may be misrecognition.

[0004] Based on the above problems, there is an urgent need to propose an eye recognition access control system based on a neural network. By calculating the length of the line connecting the vertices of the inner canthus and the outer canthus and the angle formed by the line and the horizontal line, it is determined whether the eye information of the currently recognized person is the same as the eye information of the household with the granted access permission. The requirements for the lens for collecting images are low, thus solving the problems of high equipment cost and difficult promotion. In addition, by collecting the light intensity in the current environment and comparing it with the light intensity threshold, corresponding light supplementation is carried out, and the angle of light supplementation is adjusted according to the distance between the person to be recognized and the collection device, so that the image collected by the lens is clear and misrecognition is avoided. Summary of the Invention

[0005] The purpose of the present invention is to provide an eye recognition access control system based on a neural network to solve the problems raised in the above background art.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] An eye recognition access control system based on a neural network, comprising an information storage module, an identity recognition module, an image acquisition module, an eye information processing and analysis module, a control module, a communication and alarm module, an illuminance acquisition module, a daylight simulation module, a distance sensing module, a processing and calculation module, an infrared thermal imaging module, and a mobile phone application. The information storage module pre-stores the eye information of the first household that has been granted the right to open the door. The image acquisition module is used to acquire the eye image of the person whose eye information is being recognized currently. The eye information processing and analysis module is used to process and analyze the eye image of the person whose eye information is being recognized currently. The identity recognition module confirms whether the person whose eye information is being recognized currently has the right to open the door according to the comparison result between the processing and analysis result of the eye information processing and analysis module and the pre-stored household eye information in the information storage module. The control module decides whether to open the door or give an alarm according to the recognition result of the identity recognition module. The control module is also used to control the daylight simulation module. The control module sends an alarm to the household that has been granted the right to open the door pre-stored in the information storage module through the communication and alarm module. The illuminance acquisition module is used to collect the light intensity in a certain area in front of the door. The daylight simulation module is used to supplement the light. The distance sensing module is used to obtain the distance between the person whose eye recognition is being carried out in front of the door and the door. The processing and calculation module is used for the processing and calculation of the data obtained by the distance sensing module. The infrared thermal imaging module is used to detect whether there is a person to be recognized in front of the door. The mobile phone application is used to receive the alarm information sent by the communication and alarm module.

[0008] Further, the eye information of the first household that has been granted the right to open the door pre-stored in the information storage module includes the length of the intercanthal distance of the household's eyes and the degree of the angle between the line connecting the vertices of the inner canthus and the outer canthus and the horizontal line. The length of the inner canthal distance of each person is different. Moreover, combined with the difference in eye shape, different eye shapes will cause each person's eyes to be inclined to different degrees with respect to the horizontal line, that is, there are slight differences in the angle between the line connecting the vertices of the inner canthus and the outer canthus and the horizontal line. If only relying on the length of the inner distance or the inclination angle alone, there may be a situation of misidentification. However, by combining them to judge whether the eye information of the person to be recognized matches the eye information of the household that has been granted the right to open the door pre-stored, the situation of misidentification can be avoided, and the requirements for the acquisition equipment are low, thus solving the problems of high equipment cost and difficult promotion.

[0009] Further, the eye information processing and analysis module connects the inner canthus vertex and the outer canthus vertex of the acquired eye image. The connection line is the first straight line. A first rectangular coordinate system is established with the inner canthus vertex as the origin of the coordinate axis. The horizontal axis direction of the first rectangular coordinate system is the same as the direction from the inner canthus vertex to the outer canthus vertex. Calculate the first angle θ formed between the first straight line and the horizontal axis and the length L of the canthus distance. The length of the canthus distance is the length of the first straight line. Then, compare and analyze the calculated first angle θ and the length L of the canthus distance with the pre-stored eye information of the first household granted the door opening permission in the information storage module. Through the double comparison of the first straight line and the first angle θ, determine whether the eye information of the currently identified person matches the eye information of the household granted the door opening permission, so as to realize the permission management of the access control.

[0010] Further, when the eye information processing and analysis module performs the comparison and analysis, it first compares the difference between the canthus distance lengths of the identified person and the first household. When the difference is less than or equal to the threshold, the eye information processing and analysis module proceeds to the next step of comparing and analyzing whether the first angles θ formed between the first straight lines of the identified person and the first household and the horizontal axis of the first rectangular coordinate system are equal. The eye information processing and analysis module outputs the comparison and analysis result to the control module. If the control module receives a comparison and analysis result indicating that the eye information of the currently identified person matches the eye information of the first household, it controls the door to open. If the comparison and analysis result indicates that the eye information of the currently identified person does not match the eye information of the first household, it sends an alarm message to the mobile application of the first household through the communication and alarm module, establishing a connection with the household through the communication and alarm module, enabling the household to know in real time whether the eye access control system is being illegally invaded and enabling them to take precautions in advance.

[0011] Further, the distance sensing module obtains the distance S between the person undergoing eye recognition in front of the door and the door. The daylight simulation module and the image acquisition module are both arranged on the door. The daylight simulation module is located directly above the image acquisition module. The distance between the daylight simulation module and the image acquisition module is H. The eyes of the currently identified person and the image acquisition module are on the same horizontal line. The processing and calculation module establishes a second rectangular coordinate system with this horizontal line as the coordinate horizontal axis. The connection line between the image acquisition module and the eyes of the currently identified person is the first straight line. The processing and calculation module calculates the second angle ɑ formed between the first straight line and the horizontal axis of the second rectangular coordinate system. The second angle The processing and calculation module outputs the calculation result to the daylight simulation module, adjusting the irradiation angle of the supplementary light of the daylight simulation module through the second angle ɑ. In an environment with insufficient light intensity, it can also make the images collected by the image acquisition device clear enough, thus avoiding the situation of misidentification.

[0012] Further, the daylight simulation module is a lighting supplement device that can move up and down freely on the surface of the door to adjust the irradiation beam angle. The daylight simulation module adjusts the irradiation angle of the supplementary light according to the second angle ɑ, and the irradiation angle of the supplementary light is the second angle ɑ, which is adjusted to the optimal irradiation angle to make the captured image clear.

[0013] Further, the illuminance acquisition module is used to acquire the light intensity in the current environment. If the light intensity is less than or equal to the light intensity threshold, the daylight simulation module is used to turn on the light supplement.

[0014] Further, the infrared thermal imaging module detects whether there is a person to be identified in front of the door. The judgment criteria for the person to be identified are the staying time of the person in front of the door and the third angle β formed between the second straight line and the first plane. Two shoulder peak points of the image of the person in front of the door are selected. The two shoulder peak points include shoulder peak point A and shoulder peak point B. The second straight line is the connection line between shoulder peak point A and shoulder peak point B. The first plane is the plane where the door is located. When the infrared thermal imaging module detects that there is a staying person in front of the door, it starts timing. When the staying time of the person in front of the door exceeds the time t, the infrared thermal imaging module includes this person in the queue of persons to be identified. Judging the person to be identified for the first time by the staying time of the person in front of the door is to prevent the person passing by in front of the door from being regarded as a person to be identified, thus causing the acquisition device to perform image acquisition.

[0015] Further, the processing and calculation module calculates the third angle β, that is, calculates the angle formed between the connection line of the two shoulder peak points and the first plane. Draw a perpendicular line from shoulder peak point A perpendicular to the first plane, and the foot of the perpendicular is C. Draw a perpendicular line from shoulder peak point D perpendicular to the first plane, and the foot of the perpendicular is D. Then connect the foot of the perpendicular C and the foot of the perpendicular D. The third angle β is the angle formed between the second straight line and the straight line CD. When the second straight line is perpendicular to the first plane, the third angle β is 90 degrees. In daily life, there may be a situation where a non-person to be identified stays in front of the door. Therefore, it is possible to judge whether this person is a person to be identified according to the angle between the current staying person and the first plane where the door is located. Because when performing eye recognition, the eyes need to be aligned with the acquisition device, and the angle formed between the human body and the first plane must be within a certain angle range so that the acquisition device can capture the eye image of the person. Therefore, it is extremely reliable to judge whether the current staying person is a person to be identified according to the third angle.

[0016] Further, the processing and calculation module calculates the third angle deviation Among them, β0 is the third angle threshold. If the calculated third angle deviation p is less than or equal to the threshold, the person staying in front of the door currently is determined to be a person to be recognized, and the image acquisition module acquires the eye image of the person to be recognized. If the calculated third angle deviation p is greater than the threshold, the person staying in front of the door currently is determined not to be a person to be recognized.

[0017] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: The present invention calculates the length of the line connecting the vertex of the inner canthus angle and the vertex of the outer canthus angle and the included angle between the line and the horizontal line to determine whether the eye information of the currently recognized person is the same as the eye information of the household granted the door opening permission. The requirement for the lens of the collected image is low, thus solving the problems of high equipment cost and difficult promotion. In addition, by collecting the light intensity in the current environment and comparing it with the light intensity threshold, corresponding light supplementation is carried out, and the angle of the light supplementation is adjusted according to the distance between the person to be recognized and the acquisition device, so that the image collected by the lens is clear and the situation of misrecognition is avoided. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0019] Figure 1 is a module schematic diagram of an eye recognition access control system based on a neural network according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0021] Please refer to Figure 1 , the present invention provides the following technical solutions:

[0022] An eye recognition access control system based on a neural network, comprising an information storage module, an identity recognition module, an image acquisition module, an eye information processing and analysis module, a control module, a communication and alarm module, an illuminance acquisition module, a daylight simulation module, a distance sensing module, a processing and calculation module, an infrared thermal imaging module, and a mobile application terminal. The information storage module pre-stores the eye information of the first household granted the access permission. The image acquisition module is used to acquire the eye image of the person currently undergoing eye information recognition. The eye information processing and analysis module is used to process and analyze the eye image of the person currently undergoing eye information recognition. The identity recognition module confirms whether the person currently undergoing eye information recognition has the access permission according to the comparison result between the processing and analysis result of the eye information processing and analysis module and the eye information of the household pre-stored in the information storage module. The control module decides to open the door or give an alarm according to the recognition result of the identity recognition module. The control module is also used to control the daylight simulation module. The control module alarms the household granted the access permission pre-stored in the information storage module through the communication and alarm module. The illuminance acquisition module is used to collect the light intensity within a certain area in front of the door. The daylight simulation module is used to supplement the light. The distance sensing module is used to obtain the distance between the person undergoing eye recognition in front of the door and the door. The processing and calculation module is used to process and calculate the data obtained by the distance sensing module. The infrared thermal imaging module is used to detect whether there is a person to be recognized in front of the door. The mobile application terminal is used to receive the alarm information sent by the communication and alarm module.

[0023] The eye information of the first household granted the access permission pre-stored in the information storage module includes the length of the canthal distance of the household's eyes and the degree of the angle between the line connecting the vertices of the medial canthus and the lateral canthus and the horizontal line.

[0024] The eye information processing and analysis module connects the vertices of the medial canthus and the lateral canthus of the acquired eye image. The connection line is the first straight line. A first rectangular coordinate system is established with the vertex of the medial canthus as the origin of the coordinate axis. The horizontal axis direction of the first rectangular coordinate system is the same as the direction from the vertex of the medial canthus to the vertex of the lateral canthus. The first angle θ formed between the first straight line and the horizontal axis and the length L of the canthal distance are calculated. The length of the canthal distance is the length of the first straight line. The calculated first angle θ and the length L of the canthal distance are compared and analyzed with the eye information of the first household granted the access permission pre-stored in the information storage module.

[0025] When the eye information processing and analysis module conducts comparison and analysis, it first compares the difference in the distance between the corners of the eyes of the person to be recognized and the first household. When the difference is less than or equal to the threshold, the eye information processing and analysis module proceeds to the next step of comparing and analyzing whether the first angle θ formed between the first straight line of the person to be recognized and the first household and the horizontal axis of the first rectangular coordinate system is equal. The eye information processing and analysis module outputs the comparison and analysis result to the control module. If the control module receives a comparison and analysis result indicating that the eye information of the current person to be recognized matches that of the first household, it controls the door to open. If the comparison and analysis result indicates that the eye information of the current person to be recognized does not match that of the first household, it sends an alarm message to the mobile application of the first household through the communication and alarm module.

[0026] The distance sensing module obtains the distance S between the person undergoing eye recognition in front of the door and the door. The daylight simulation module and the image acquisition module are both set on the door. The daylight simulation module is located directly above the image acquisition module, and the distance between the daylight simulation module and the image acquisition module is H. The eyes of the current person to be recognized and the image acquisition module are on the same horizontal line. The processing and calculation module establishes a second rectangular coordinate system with the horizontal line as the coordinate horizontal axis. The connection line between the image acquisition module and the eyes of the current person to be recognized is the first straight line. The processing and calculation module calculates the second angle ɑ formed between the first straight line and the horizontal axis of the second rectangular coordinate system. The second angle The processing and calculation module outputs the calculation result to the daylight simulation module.

[0027] The daylight simulation module is a lighting supplement device embedded in the surface of the door that can move up and down freely to adjust the irradiation beam angle. The daylight simulation module adjusts the irradiation angle of the supplementary light according to the second angle ɑ, and the irradiation angle of the supplementary light is the second angle ɑ.

[0028] The illuminance acquisition module is used to acquire the illuminance in the current environment. If the illuminance is less than or equal to the illuminance threshold, the daylight simulation module is used to turn on the light supplement.

[0029] The infrared thermal imaging module detects whether there is a person to be recognized in front of the door. The judgment criteria for the person to be recognized are the staying time of the person in front of the door and the third angle β formed between the second straight line and the first plane. Select the acromion points of the two shoulders of the person image in front of the door. The two acromion points of the shoulders include acromion point A and acromion point B. The second straight line is the connection line between acromion point A and acromion point B. The first plane is the plane where the door is located. When the infrared thermal imaging module detects a staying person in front of the door, it starts timing. When the staying time of the person in front of the door exceeds the time t, the infrared thermal imaging module includes this person in the queue of persons to be recognized.

[0030] The processing and calculation module calculates the third angle β, that is, calculates the angle formed between the line connecting the acromion points of the two shoulders and the first plane. A perpendicular line is drawn from the acromion point A to the first plane, and the foot of the perpendicular is C. A perpendicular line is drawn from the acromion point D to the first plane, and the foot of the perpendicular is D. The feet of the perpendiculars C and D are connected. The third angle β is the angle formed between the second line and the line CD. When the second line is perpendicular to the first plane, the third angle β is 90 degrees.

[0031] The processing and calculation module calculates the third angle deviation degree. The third angle deviation degree where β0 is the third angle threshold. If the calculated third angle deviation degree p is less than or equal to the threshold, the person staying in front of the door currently is determined to be a person to be recognized. The image acquisition module acquires the eye image of the person to be recognized. If the calculated third angle deviation degree p is greater than the threshold, the person staying in front of the door currently is determined not to be a person to be recognized.

[0032] The working principle of the present invention:

[0033] S1: Detect whether there is a person to be recognized in front of the door through the infrared thermal imaging module. The detection method of the person to be recognized includes the following steps:

[0034] S11: Judge whether the staying time of the person staying in front of the door exceeds the preset time threshold. If the staying time is greater than or equal to the time threshold, proceed to the next detection of the person to be recognized;

[0035] S12: Collect the image of the person staying in front of the door, extract the acromion points of the two shoulders of the person staying in front of the door in the image, connect the acromion points of the two shoulders, calculate the angle formed between the connecting line and the plane where the door is located, and further calculate the angle deviation degree, and judge whether the calculated result meets the determination conditions of the person to be recognized;

[0036] S2: If the detection of the person to be recognized passes, collect the light intensity in the current environment through the illuminance acquisition module. If the light intensity is lower than the preset threshold, turn on the light supplement and calculate the best light supplement angle;

[0037] S3: The image acquisition module collects the eye image of the person to be recognized, and the identity recognition module judges whether the eye information of the current person to be recognized conforms to the eye information of the householders who have been granted the door opening permission and stored in advance, that is, judges whether the current person to be recognized has the door opening permission. If it conforms, the control module opens the door. If it does not conform, an alarm message is sent to the mobile application of the householder through the communication and alarm module.

[0038] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0039] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An eye recognition access control system based on a neural network, characterized in that: It includes an information storage module, an identity recognition module, an image acquisition module, an eyeball information processing and analysis module, a control module, a communication and alarm module, an illuminance acquisition module, a daylight simulation module, a distance sensing module, a processing and calculation module, an infrared thermal imaging module, and a mobile phone application. The information storage module pre-stores the eyeball information of the first household with the granted door-opening permission. The image acquisition module is used to acquire the eye image of the person whose eyeball information is being recognized currently. The eyeball information processing and analysis module is used to process and analyze the eye image of the person whose eyeball information is being recognized currently. The identity recognition module confirms whether the person whose eyeball information is being recognized currently has the door-opening permission according to the comparison result between the processing and analysis result of the eyeball information processing and analysis module and the pre-stored household eyeball information in the information storage module. The control module decides whether to open the door or alarm according to the recognition result of the identity recognition module. The control module is also used to control the daylight simulation module. The control module alarms the household with the granted door-opening permission pre-stored in the information storage module through the communication and alarm module. The illuminance acquisition module is used to acquire the light intensity in a certain area in front of the door. The daylight simulation module is used to supplement the light. The distance sensing module is used to obtain the distance between the person whose eyeball is being recognized in front of the door and the door. The processing and calculation module is used for the processing and calculation of the data obtained by the distance sensing module. The infrared thermal imaging module is used to detect whether there is a person to be recognized in front of the door. The mobile phone application is used to receive the alarm information sent by the communication and alarm module; The eyeball information processing and analysis module connects the inner canthus vertex and the outer canthus vertex of the acquired eye image. The connection line is the first straight line. A first rectangular coordinate system is established with the inner canthus vertex as the coordinate axis origin. The horizontal axis direction of the first rectangular coordinate system is the same as the direction from the inner canthus vertex to the outer canthus vertex. Calculate the first angle θ formed between the first straight line and the horizontal axis and the length L of the eye corner distance. The length of the eye corner distance is the length of the first straight line. And compare and analyze the calculated first angle θ and the length L of the eye corner distance with the pre-stored eyeball information of the first household with the granted door-opening permission in the information storage module; The infrared thermal imaging module detects whether there is a person to be recognized in front of the door. The judgment criterion for the person to be recognized is the staying time of the person in front of the door and the third angle β formed between the second straight line and the first plane. Select the two acromion points of the person image in front of the door. The two acromion points include acromion point A and acromion point B. The second straight line is the connection line between acromion point A and acromion point B. The first plane is the plane where the door is located. When the infrared thermal imaging module detects that there is a staying person in front of the door, start timing. When the staying time of the person in front of the door exceeds the time t, the infrared thermal imaging module includes this person in the queue of persons to be recognized.

2. The eye recognition access control system based on a neural network according to claim 1, characterized in that: The pre-stored eyeball information of the first household with the granted door-opening permission in the information storage module includes the length of the eye corner distance of the household's eyes, the included angle degree between the connection line of the inner canthus vertex and the outer canthus vertex and the horizontal line.

3. The eyeball recognition access control system based on a neural network according to claim 1 or 2, characterized in that: When the eye information processing and analysis module conducts comparison and analysis, it first compares the difference in the distance between the inner and outer corners of the eyes of the person to be recognized and the first household. When the difference is less than or equal to the threshold value, the eye information processing and analysis module proceeds to the next step of comparing and analyzing whether the first angle θ formed between the first straight line of the person to be recognized and the first household and the horizontal axis of the first rectangular coordinate system is equal. The eye information processing and analysis module outputs the comparison and analysis result to the control module. If the control module receives a comparison and analysis result indicating that the eye information of the current person to be recognized matches that of the first household, it controls the door to open. If the comparison and analysis result indicates that the eye information of the current person to be recognized does not match that of the first household, it sends an alarm message to the mobile application of the first household through the communication and alarm module.

4. The eyeball recognition access control system based on a neural network according to claim 1, characterized in that: The distance sensing module obtains the distance S between the person undergoing eye recognition in front of the door and the door. The daylight simulation module and the image acquisition module are both arranged on the door. The daylight simulation module is directly above the image acquisition module, and the distance between the daylight simulation module and the image acquisition module is H. The eyes of the currently recognized person and the image acquisition module are on the same horizontal line. The processing and calculation module establishes a second rectangular coordinate system with the horizontal line as the coordinate horizontal axis. The line connecting the image acquisition module and the eyes of the currently recognized person is the first straight line. The processing and calculation module calculates the second angle ɑ formed between the first straight line and the horizontal axis of the second rectangular coordinate system. The second angle , and the processing and calculation module outputs the calculation result to the daylight simulation module.

5. The eyeball recognition access control system based on a neural network according to claim 1 or 4, characterized in that: The daylight simulation module is a lighting supplement device embedded in the surface of the door that can move up and down freely to adjust the irradiation beam angle. The daylight simulation module adjusts the irradiation angle of the supplementary light according to the second angle ɑ, and the irradiation angle of the supplementary light is the second angle ɑ.

6. The eye recognition access control system based on a neural network according to claim 1, wherein: The illuminance acquisition module is used to acquire the illuminance intensity in the current environment. If the illuminance intensity is less than or equal to the illuminance intensity threshold, it turns on the supplement of light through the daylight simulation module.

7. The eye recognition access control system based on a neural network according to claim 1, characterized in that: The processing and calculation module calculates the third angle β, that is, calculates the angle formed between the line connecting the acromion points of the two shoulders and the first plane. Draw a perpendicular line from the acromion point A perpendicular to the first plane, and the foot of the perpendicular is C. Draw a perpendicular line from the acromion point D perpendicular to the first plane, and the foot of the perpendicular is D. Then connect the foot of the perpendicular C and the foot of the perpendicular D. The third angle β is the angle formed between the second straight line and the straight line CD. When the second straight line is perpendicular to the first plane, the third angle β is 90 degrees.

8. The eyeball recognition access control system based on a neural network according to claim 7, characterized in that: The processing and calculation module calculates a third angle deviation degree, and the third angle deviation degree , where is a third angle threshold. If the calculated third angle deviation degree p is less than or equal to the threshold, the person staying in front of the current door is determined to be a person to be recognized, and the image acquisition module acquires the eye image of the person to be recognized. If the calculated third angle deviation degree p is greater than the threshold, the person staying in front of the current door is determined not to be a person to be recognized.

Images