TW202217760A - Iot security system and method thereof - Google Patents

Abstract

An IoT security method includes: capturing at least one facial image on an unidentified face with a camera unit in a security monitoring area; searching at least one facial block on the facial image and retrieving at least one facial recognizable feature from the facial block; detecting a unidentified target data corresponding to the unidentified face or a peripheral target thereof; retrieving at least one identifiable feature; identifying the facial recognizable feature of the facial image with a facial recognition procedure to obtain a facial recognition result and further identifying the identifiable feature to obtain an auxiliary verification result; and verifying the facial recognition result with the auxiliary verification result to obtain a final verification result.

Description

Internet of things security system and method thereof

The present invention relates to an Internet of Things (IoT, Internet of Things) security system and method thereof; in particular, to a security system and method for multiple identification of the Internet of Things.

For example, regarding conventional security systems and methods, such as the invention patent application for "Internet-level smart home security system and method" in Patent Publication No. TW-201739284 of the Republic of China, which discloses a network-level smart home security system Security systems and methods. The network-level smart home security method is a method for controlling access from a wide area network (WAN) to a local area network (LAN). The method is implemented via a gateway, and the gateway is configured between the local area network and the wide area network.

Continuing from the above, the method of the aforementioned No. TW-201739284 includes: sending a gateway LAN access secret to a mobile device via a first local communication path, and the first local communication path does not include the wide area network; After the gateway LAN access secret, only one traffic is allowed, and the traffic is from an IP address on a white list maintained by the gateway, and the traffic is from the wide area network to the local area network; via the The WAN receives a remote access information from the mobile device, and the remote access information includes [i] an authentication information, and the authentication information is obtained from the gateway LAN access secret and (ii) an IP address and the IP address range is associated with one or more IP addresses of the mobile device; and the gateway verifies the authentication information and responsively adds the IP address range to the whitelist.

Another conventional security system and its method, eg: Republic of China Patent Announcement No. TW-I574232 for the invention patent of "Security Host with Internet of Things Communication Function", which discloses a security host with Internet of Things communication function. The security host includes a connection module, a communication module, a security central control module and a sound output module.

Continuing from the above, the connection module of the aforementioned No. TW-I574232 is connected to a detector, and receives the detection result of the detector. The communication module connects a cloud and an electronic device through a communication network, and receives a control signal or a playing signal sent by the cloud or the electronic device. The security central control module is connected to the connection module and the communication module, and the security central control module has a security state or a security release state. In the security state, it is judged whether an abnormality occurs according to the detection result of the detector, and an abnormality alarm is issued when the judgment result is abnormal, and is transmitted to the cloud through the communication module. When the security is released, the security central control module stops judging whether an abnormality occurs or the detector stops detecting.

Continuing from the above, the sound output module of the aforementioned No. TW-I574232 is connected to the security central control module, and emits a warning sound according to the abnormal alarm, and the warning sound plays a corresponding sound according to the playback signal. The security central control module generates a control command, a driving signal or a security setting signal according to the control signal, and the control command is transmitted to the other electronic device through the communication module, and the other electronic device according to the control commands to operate. In addition, the driving signal is transmitted to the detector through the connection module, so that the detector operates according to the driving signal. In addition, the security central control module switches to the security state or the security release state according to the security setting signal.

Another conventional security system and method therefor, such as the invention patent of "The Mutual Aid and Sharing Security System of the Internet of Households" in Patent Publication No. TW-I606428 of the Republic of China, which discloses a security system of mutual assistance and sharing of the Internet of Households. The mutual assistance and sharing security system of the household network includes a security host, and the security host includes a communication module, a central control module, an access control card swiping module, a Time module and several area detector expansion modules.

Continuing from the above, the communication module of the aforementioned No. TW-I606428 is used for information sharing and routing among group neighbors in a household network, and is used for the transmission and reception of control messages in a cloud and an electronic device. The detection result from the detector module and its control are received through the area detector expansion module, and the detector module is connected to the communication module.

Continuing from the above, the central control module of the aforementioned No. TW-I606428 receives an abnormal alarm from the detector via the communication module, and sends out a corresponding light signal buzzer module according to a pre-set security state. A warning sound is displayed and an LED light is displayed. In addition, the abnormal alarm is also selected to be simultaneously pushed and broadcast to a group of neighbors through a local area network of the household network and the cloud and electronic device with the Internet of Things communication function.

Continuing from the above, the access control card swiping module and the time module of the aforementioned No. TW-I606428 are based on mutual assistance and sharing among more than one neighbor. In addition, when assisting in troubleshooting on-site abnormal alarms, you can choose to swipe the card and record the time stamp to determine a reciprocal point, so that the reciprocal point can be given priority to the neighbor who swiped the card first. The area detector expansion module (#n) is externally connected to the detector module (#m).

However, the aforementioned Patent Publication No. TW-201739284 discloses a network-level smart home security system and method, Announcement No. TW-I574232 discloses a security host with Internet of Things communication function, and Announcement No. TW-I606428 discloses mutual assistance sharing of home networking There must still be a potential need for further improvement in the security system.

The aforementioned invention patent application of ROC Patent Publication No. TW-201739284, Patent Publication No. TW-I574232 and Patent Publication No. TW-I606428 are only for reference of the technical background of the present invention and to illustrate the current state of technological development. It is not intended to limit the scope of the present invention.

In view of this, in order to meet the above requirements, the present invention provides An Internet of Things security system and method thereof, which utilize an image capturing unit to capture at least one face image on a face to be identified in a security monitoring area, search for at least one face block in the face image, and sample at least one face Identifying features, and correspondingly detecting at least one target-to-be-identified data on the face to be identified or its surrounding objects, and extracting at least one recognizable feature from the target-to-be-identified data, and then using the face identification feature to perform a face recognition Recognition operation to obtain a face recognition result, and further identify the identifiable feature to obtain an auxiliary verification result, and use the face recognition result and the auxiliary verification result for verification and comparison to obtain a [final] verification Compare the results in order to greatly improve the reliability and security of face recognition.

The main purpose of the preferred embodiments of the present invention is to provide an Internet of Things security system and method thereof, which utilize an image capturing unit to capture at least a face image on a face to be identified in a security monitoring area, and record the face image on the face image. Finding at least one face block and sampling at least one face recognition feature, and correspondingly detecting at least one target to be recognized data on the to-be-recognized face or its surrounding objects, and extracting at least one recognizable feature from the target to-be-recognized data , and then use the face recognition feature to perform a face recognition operation to obtain a face recognition result, and further identify the identifiable feature to obtain an auxiliary verification result, and use the face recognition result and the auxiliary verification result to carry out Verification and comparison are performed to obtain a [final] verification and comparison result, so as to achieve the purpose of improving the reliability and security of face recognition.

In order to achieve the above purpose, the Internet of Things security method according to the preferred embodiment of the present invention includes:

Using an image capturing unit to capture at least a face image on a face to be identified in a security monitoring area;

Finding at least one face block in the face image and sampling at least one face recognition feature;

The face to be recognized or its surrounding objects are also detected correspondingly to One less target to be identified;

extracting at least one identifiable feature from the target data to be identified;

Use the face recognition feature to perform a face recognition operation to obtain a face recognition result, and further identify the recognizable feature to obtain an auxiliary verification result; and

The face recognition result and the auxiliary verification result are used for verification and comparison to obtain a [final] verification and comparison result, so as to perform pairing verification.

In order to achieve the above-mentioned purpose, the Internet of Things security system of the preferred embodiment of the present invention includes:

an image capturing unit, which captures at least a face image of a face to be identified in a security monitoring area;

a calculation and processing unit, which is connected to the image capturing unit, and searches for at least one face block in the face image and samples at least one face recognition feature;

a face recognition unit, which is connected to the calculation and processing unit, and uses the face recognition feature to perform a face recognition operation to obtain a face recognition result; and

an auxiliary recognition unit, which is connected to the calculation and processing unit, and correspondingly detects at least one target to be recognized data on the to-be-recognized face or its surrounding objects, and extracts at least one recognizable feature from the target to-be-recognized data ;

The face recognition feature is used to perform a face recognition operation to obtain a face recognition result, and the recognizable feature is further identified to obtain an auxiliary verification result, and the face recognition result and the auxiliary verification result are used for verification. Alignment to obtain a [final] validation alignment.

In a preferred embodiment of the present invention, the target data to be recognized is selected from a voice data to be recognized, a fingerprint data to be recognized, a license plate image to be recognized Like data or any combination thereof.

In the preferred embodiment of the present invention, the recognizable feature is selected from a voiceprint feature, a fingerprint feature, a license plate image feature or any combination thereof.

In a preferred embodiment of the present invention, the image capturing unit is disposed in a car passage, an access control passage, an equipment machine, or any combination thereof.

A preferred embodiment of the present invention connects and transmits the face recognition result, the auxiliary verification result and the verification comparison result to a cloud Internet of Things system.

In a preferred embodiment of the present invention, the method for identifying the authenticity of a face image includes: capturing at least an infrared image of a face on the face to be identified; searching for at least one temperature distribution feature in the infrared image of the face; using a temperature comparison unit to The temperature distribution feature is compared with the authenticity of the temperature parameter of a face block, so as to generate a comparison result of the authenticity of a person's face.

The temperature distribution feature of the preferred embodiment of the present invention includes a face distribution temperature, a body contour distribution temperature and a background environment distribution temperature.

The temperature distribution feature of the preferred embodiment of the present invention is used to identify a fever body temperature feature or a hyperthermia feature.

In a preferred embodiment of the present invention, the temperature parameter of the face block is between a minimum body temperature and a maximum body temperature.

In a preferred embodiment of the present invention, the temperature parameter of the face block is combined with an ambient temperature parameter.

The face image of the preferred embodiment of the present invention generates a compensated face image according to an ambient temperature.

In a preferred embodiment of the present invention, the temperature comparison unit or the face recognition unit is connected to an output unit, so as to output the face authenticity comparison result or the face recognition result.

In a preferred embodiment of the present invention, the output unit is connected to operate a standby device, so as to output the face authenticity comparison result or the face recognition result to the standby device.

The temperature distribution feature of the preferred embodiment of the present invention is compared with the fake temperature feature of a fake face image.

The preferred embodiment of the present invention adopts a fingerprint image authenticity identification system including:

a fingerprint image capturing unit, which captures at least one finger infrared image and at least one fingerprint image on a finger to be identified; a calculation and processing unit, which is connected to the fingerprint image capturing unit and searches for at least one temperature in the finger infrared image distributing features, and finding at least one fingerprint block in the fingerprint image and sampling at least one fingerprint identification feature;

a temperature comparison unit, which is connected to the calculation and processing unit, and performs authenticity comparison between the temperature distribution feature and a finger block temperature parameter, so as to generate a finger authenticity comparison result; and

A fingerprint identification unit is connected to the calculation and processing unit, and uses the fingerprint identification feature to perform a fingerprint identification operation to obtain a fingerprint identification result.

The temperature distribution feature of the preferred embodiment of the present invention includes a finger distribution temperature, a finger contour distribution temperature and a background environment distribution temperature.

The temperature distribution feature of the preferred embodiment of the present invention is used to identify a fever body temperature feature or a hyperthermia feature.

In a preferred embodiment of the present invention, the temperature parameter of the finger block is between a minimum body temperature and a maximum body temperature.

In a preferred embodiment of the present invention, the temperature parameter of the finger block is combined with an ambient temperature parameter.

In a preferred embodiment of the present invention, the temperature comparison unit or the fingerprint identification unit is connected to an output unit, so as to output the finger authenticity comparison result or the fingerprint identification result.

The output unit of the preferred embodiment of the present invention is connected to a medical management center, so as to output a fever body temperature signature or a hyperthermia signature to the Medical Management Center.

In a preferred embodiment of the present invention, the output unit is connected to operate a standby device, so as to output the finger authenticity comparison result or the fingerprint identification result to the standby device.

The temperature distribution characteristic of the preferred embodiment of the present invention is compared with the fake temperature characteristic of a fake finger image.

The temperature distribution characteristic of the preferred embodiment of the present invention is compared with an ambient temperature characteristic.

1: Wireless security system

100: Cloud IoT System

101: Central Control Center

102: Mobile Browsing Devices

103: Medical Management Center

1A: Infrared image of human face

1B: Copy face image picture

1C: Fingerprint infrared image

1D: Copy the fingerprint image picture

10: Image capture unit

10a: Fingerprint image capture unit

10b: Microphone unit

11: Gateway host

12: Sensing network

121: Short-range wireless communication device

13: Control monitoring device

131: Warning device

2: Temperature detection unit

20: Calculation and processing unit

21: Temperature comparison unit

30: Face recognition unit

30a: Fingerprint recognition unit

31: Auxiliary identification unit

40: Verifying the alignment unit

51: Standby computer device

52: Standby mobile communication device

6: Face image authenticity recognition system

7: Fingerprint image authenticity identification system

A: face image

2A: License plate image

B: Voice data to be recognized

Figure 1: A schematic diagram of the architecture of the Internet of Things security system according to the preferred embodiment of the present invention.

Fig. 2 is a schematic flow chart of the Internet of Things security method according to the preferred embodiment of the present invention.

Figure 3: A block schematic diagram of the Internet of Things security system according to a preferred embodiment of the present invention.

Fig. 4 is a block diagram of the Internet of Things security system adopting a non-communication structure according to a preferred embodiment of the present invention.

Fig. 5 is a block diagram of the Internet of Things security system according to the first preferred embodiment of the present invention.

Fig. 6 is a block diagram of the Internet of Things security system according to the second preferred embodiment of the present invention.

FIG. 7 is a schematic flow chart of the method for authenticating the authenticity of a face image in the IoT security system according to the preferred embodiment of the present invention.

Fig. 8 is a block diagram of a facial image authenticity identification system used in the IoT security system according to the preferred embodiment of the present invention.

Fig. 9 is a schematic flow chart of the method for identifying the authenticity of fingerprint images in the Internet of Things security system according to the preferred embodiment of the present invention.

Figure 10: The Internet of Things security system according to the preferred embodiment of the present invention adopts the index Block diagram of the texture image authenticity identification system.

Fig. 11: A schematic block diagram of the Internet of Things security system connected to the medical management center according to the preferred embodiment of the present invention.

In order to fully understand the present invention, preferred embodiments will be exemplified below and described in detail in conjunction with the accompanying drawings, which are not intended to limit the present invention.

The Internet of Things security system and method thereof according to the preferred embodiment of the present invention can be applied to the pre-processing of the security system for face, voiceprint or fingerprint image recognition, and it is suitable for various face, voiceprint or fingerprint image authenticity identification devices and Its related application equipment, such as: various types of computer systems, home appliance product control systems (such as the Internet of Things), automation control systems, medical care systems, museum security systems, access control systems or their related security systems, but they are not intended to limit the present invention. scope of application.

FIG. 1 discloses a schematic diagram of the structure of the Internet of Things security system according to the preferred embodiment of the present invention. Referring to FIG. 1, for example, the IoT security system according to the preferred embodiment of the present invention includes a wireless security system 1, a gateway host 11, a sensing network 12, and a short-range wireless communication device [For example: ZigBee or other short-range wireless communication] 121, a control monitoring device 13, a warning device [for example: warning light, buzzer or other warning device] 131 and a cloud IoT system 100, as shown in FIG. 1 The lower part is shown, and other peripheral devices can be omitted or added according to different needs.

Please refer to the upper part of FIG. 1 again, for example, the cloud IoT system 100 is connected to a central control center 101 for communication, so that at least one command is output to the cloud IoT system 100 through the central control center 101 , In order to control and operate the cloud IoT system 100 . In addition, the cloud Internet of Things system 100 can optionally connect to a mobile browsing device 102 for logging in to the cloud Internet of Things system 100 .

FIG. 2 discloses the Internet of Things security method according to the preferred embodiment of the present invention. Figure 3 shows a schematic block diagram of the Internet of Things security system according to a preferred embodiment of the present invention, which corresponds to the Internet of Things security method in Figure 2. Referring to Figures 2 and 3, for example, the IoT security system according to the preferred embodiment of the present invention further includes an image capture unit 10, a calculation and processing unit 20, a face recognition unit 30, and an auxiliary recognition unit 31 and a verification and comparison unit 40, and other peripheral devices can be omitted or added according to different requirements.

Referring to FIG. 3 again, for example, the image capturing unit 10 can be selected from a photographing device, and the photographing device is disposed in a car passage, an access control passage, an equipment machine, or any combination thereof. In addition, the auxiliary identification unit 31 can be selected from a photographing device, a fingerprint image capturing device, a microphone device or any combination thereof.

Please refer to FIG. 3 again, for example, the calculation and processing unit 20 is connected to the image capturing unit 10 by appropriate technical means, and the face recognition unit 30 and the auxiliary recognition unit 31 are connected to the image capture unit 31 by appropriate technical means The calculation and processing unit 20, and the verification and comparison unit 40 are connected to the face recognition unit 30 and the auxiliary recognition unit 31 by appropriate technical means.

FIG. 4 discloses a block diagram of the Internet of Things security system adopting a communication-free structure according to a preferred embodiment of the present invention, which corresponds to the Internet of Things security system of FIG. 1 . Referring to Figures 1 and 4, for example, the Internet of Things security system of the preferred embodiment of the present invention chooses to connect and communicate several electromechanical devices, a layout board, a web system, and a control room by wireless communication. other equipment or systems.

Please refer to Figures 2 and 3 again. For example, the IoT security method according to the preferred embodiment of the present invention includes step S1A: first, in a security monitoring area (for example, a commercial building, a corporate headquarters, a residential building or Others] use the image capturing unit 10 to capture at least one or several (a series) of face images A on a face (or several faces to be identified) to be identified.

Please refer to Figures 2 and 3 again. For example, the IoT security method according to the preferred embodiment of the present invention includes step S1B: then, use the image capture within a predetermined time (for example: 0.1 second or other time) The unit 10 also detects at least one target to be identified data corresponding to the face to be identified or its surrounding objects. The target to-be-recognized data can be selected from a to-be-recognized voice data, a to-be-recognized fingerprint data, or a to-be-recognized license plate image data.

Referring again to Figures 2 and 3, for example, the IoT security method according to the preferred embodiment of the present invention includes step S2A: then, the calculation and processing unit 20 is used to find at least one face area in the face image A A block [facial block, the size of the image block is w × h ] and sampling at least one face recognition feature [facial recognizable feature], such as: T-shaped part.

Referring again to Figures 2 and 3, for example, the IoT security method according to the preferred embodiment of the present invention includes step S2B: then, the calculation and processing unit 20 is used to extract at least one identifiable data from the target to be identified. Identify features. The identifiable feature is selected from a voiceprint feature, a fingerprint feature, or a license plate image feature (eg, character or numerical feature).

Referring again to Figures 2 and 3, for example, the IoT security method of the preferred embodiment of the present invention includes step S3: then, the face recognition feature is used to perform a face recognition operation by the face recognition unit 30 , to obtain a face recognition result, and further use the auxiliary recognition unit 31 to recognize the recognizable feature to obtain an auxiliary verification result.

Referring again to Figures 2 and 3, for example, the IoT security method according to the preferred embodiment of the present invention includes step S4: then, the verification and comparison unit 40 is used to perform the facial recognition results and the auxiliary verification results. Validation alignment to obtain a [final] validation alignment for pair-wise validation. The face recognition result, the auxiliary verification result and the verification comparison result are connected and transmitted to a cloud Internet of Things system.

FIG. 5 discloses a block diagram of the Internet of Things security system according to the first preferred embodiment of the present invention. Please refer to Figures 3 and 5, for example, The first preferred embodiment of the present invention further includes a microphone device 10b corresponding to detecting a to-be-recognized voice data B, and using the calculation and processing unit 20 to extract a voiceprint feature from the to-be-recognized voice data B, and through the auxiliary The recognition unit 31 performs voiceprint recognition.

FIG. 6 discloses a block diagram of the Internet of Things security system according to the second preferred embodiment of the present invention. Please refer to FIGS. 3 and 6, for example, compared with the first embodiment, the image capturing unit 10 of the second preferred embodiment of the present invention also detects a license plate image 2A correspondingly, so as to collect the to-be-recognized license plate image data, and use the calculation and processing unit 20 to extract the image features of the license plate from the target data to be recognized, and perform license plate recognition through the auxiliary recognition unit 31 .

FIG. 7 discloses a schematic flowchart of a method for authenticating a face image in an IoT security system according to a preferred embodiment of the present invention. FIG. 8 discloses a block diagram of a facial image authenticity identification system used in the IoT security system according to the preferred embodiment of the present invention. Please refer to FIGS. 7 and 8. For example, the facial image authenticity identification system 6 according to the preferred embodiment of the present invention includes an image capturing unit 10, a calculation and processing unit 20, a temperature comparison unit 21, A face recognition unit 30 and a verification and comparison unit 40 are provided, and the verification and comparison unit 40 may be omitted or other peripheral devices may be added according to different requirements.

Please refer to FIGS. 7 and 8 again, for example, the calculation and processing unit 20 is connected to the image input unit 10 by appropriate technical means, and the temperature comparison unit 21 and the face recognition unit 30 are connected by appropriate technical means It is connected to the calculation and processing unit 20, and the verification and comparison unit 40 is connected to the temperature comparison unit 21 and the face recognition unit 30 by appropriate technical means. In addition, the verification and comparison unit 40 is a display unit or a unit with similar functions, or the verification and comparison unit 40 is connected to a display unit or a unit with similar functions by appropriate technical means.

Please refer to FIGS. 7 and 8 again, for example, the image capturing unit 10 is a camera unit or an image capturing unit, and the image capturing unit 10 is used for inputting or capturing At least one or several (series) face images, and the face images include a single face image or several face images ( m × n ) or image blocks of different persons.

Referring again to Figures 7 and 8, for example, the method for identifying the authenticity of a face image according to a preferred embodiment of the present invention includes step S1A: First, for example, the image capturing unit 10 is used to identify at least one face image to be identified. At least one or several (series) infrared images 1A of the human face are captured on the face (or several faces to be identified), so as to avoid using a duplicate face image picture 1B for the face image recognition operation.

Referring again to Figures 7 and 8, for example, the method for identifying the authenticity of a face image according to a preferred embodiment of the present invention includes step S1B: then, for example, within a predetermined time [for example: 0.1 second or At other times] use the image capturing unit 10 to capture at least one or more face images (for example: the pixel coordinates of the image are ( x , y )) on the face (or several faces to be identified) to ensure that The face image corresponds to the face infrared image 1A, otherwise it is determined that the face image recognition operation is failed or restarted.

Referring again to Figures 7 and 8, for example, the method for identifying the authenticity of a human face image according to a preferred embodiment of the present invention includes step S2A: then, for example, using the calculation and processing unit 20 to identify the human face The infrared image 1A is calculated to find at least one thermal feature distribution and other features, such as body surface temperature (about 36.5°C).

Please refer to Figures 7 and 8. For example, the temperature distribution features include a face distribution temperature, a body contour distribution temperature and a background environment distribution temperature, and the human body contour distribution temperature can be used to define a human head The contour shape is used to confirm whether it is a real human head by using the contour shape of the human head of the human body contour distribution temperature.

Please refer to Figures 7 and 8, for example, the temperature distribution feature of another preferred embodiment of the present invention is used to identify a fever temperature characteristic Symptoms [eg: between 37°C and 38°C, low-grade fever or above 38°C] or a hyperthermic feature (eg: between 39°C and 40°C, high fever or above 40°C). In another preferred embodiment of the present invention, the temperature distribution feature is compared with the temperature feature of a fake face image (eg, the body surface temperature is not expressed or a non-living human face) is true and false.

Referring again to Figures 7 and 8, for example, the method for identifying the authenticity of a face image according to a preferred embodiment of the present invention includes step S2B: then, for example, the calculation and processing unit 20 is used to identify the face of the human face. The image searches for at least one face block and samples at least one face recognition feature, such as the T-shaped part.

Referring again to Figures 7 and 8, for example, the method for identifying the authenticity of a face image according to a preferred embodiment of the present invention includes step S3: then, for example, using the temperature comparison unit 21 to distribute the temperature The feature is compared with the authenticity of a face block temperature parameter, so as to generate a face authenticity comparison result, and the temperature parameter of the face block can be selected between a minimum body temperature and a maximum body temperature or other suitable range, and the temperature parameter of the face block is combined with an ambient temperature parameter, such as: summer ambient temperature, winter ambient temperature, severe cold ambient temperature, daytime ambient temperature, night ambient temperature, high temperature working environment temperature, low temperature working environment temperature or other environments temperature.

Please refer to Figures 7 and 8 again, for example, the face image of another preferred embodiment of the present invention is based on an environmental temperature (for example: summer, winter, severe cold, day, night, high temperature or low temperature working environment ] generates a compensated face image, so as to improve the authenticity recognition of the face image and the reliability of the face image recognition.

Referring again to Figures 7 and 8, for example, the method for recognizing the authenticity of a face image according to a preferred embodiment of the present invention includes step S4: then, for example, using the face recognition unit 30 to identify the face Recognition feature to perform a face recognition operation to obtain a face recognition result; if the face is real When the false comparison result is "not real face", choose to terminate the face recognition operation immediately, and record the face image and its face recognition features in the system.

Please refer to Figures 7 and 8 again. For example, since the temperature comparison unit 21 or the face recognition unit 30 is connected to the verification and comparison unit 40 or an output unit, the result of the authenticity comparison of the face is obtained. Or the face recognition result is outputted through the output unit, and the face image and the face recognition feature of which the recognition failed can also be selected to be output.

FIG. 9 discloses a schematic flowchart of a method for authenticating a fingerprint image by the Internet of Things security system according to a preferred embodiment of the present invention. FIG. 10 discloses a block diagram of a fingerprint image authenticity identification system used in the IoT security system according to the preferred embodiment of the present invention.

Referring to Figures 9 and 10, for example, the fingerprint image authenticity identification system 7 according to the preferred embodiment of the present invention includes a fingerprint image capturing unit 10a, a calculation and processing unit 20, a temperature comparison unit 21, A fingerprint identification unit 30a and a verification and comparison unit 40, and the verification and comparison unit 40 may be omitted or other peripheral devices may be added according to different requirements.

Referring again to Figures 9 and 10, for example, the calculation and processing unit 20 is connected to the fingerprint image capturing unit 10a by appropriate technical means, and the temperature comparison unit 21 and the fingerprint identification unit 30a are connected by appropriate technical means It is connected to the calculation and processing unit 20, and the verification and comparison unit 40 is connected to the temperature comparison unit 21 and the fingerprint identification unit 30a by appropriate technical means. In addition, the verification and comparison unit 40 is a display unit or a unit with similar functions, or the verification and comparison unit 40 is connected to a display unit or a unit with similar functions by appropriate technical means.

Please refer to Figures 9 and 10, for example, the fingerprint image capturing unit 10a is a photographing unit or an image capturing unit, and the fingerprint image capturing unit 10a is used to input or capture at least one or several [a A series of finger images and fingerprint images, and the finger images include a single finger image (or fingerprint image) or several finger images (or fingerprint images) [ m × n ] or image squares of different persons.

Referring again to Figures 9 and 10, for example, the method for identifying the authenticity of a fingerprint image according to a preferred embodiment of the present invention includes step S1A: First, for example, the fingerprint image capturing unit 10a is used for at least one to-be-identified image. At least one or several infrared images 1C of the fingers are captured on the finger (or several fingers to be recognized), so as to avoid using a duplicate fingerprint image picture 1D to perform a fingerprint image recognition operation.

Referring again to Figures 9 and 10, for example, the method for identifying the authenticity of a fingerprint image according to a preferred embodiment of the present invention includes step S1B: then, for example, within a predetermined time [for example: 0.1 second or other time] using the fingerprint image capturing unit 10a to capture at least one or several fingerprint images (for example: the pixel coordinates of the image are ( x , y )) on the finger (or several fingers to be identified) to ensure that the fingerprint The image corresponds to the infrared image 1C of the finger, otherwise it is determined that the fingerprint image recognition operation is failed or restarted.

Referring again to Figures 9 and 10, for example, the method for identifying the authenticity of a fingerprint image according to a preferred embodiment of the present invention includes step S2A: then, for example, using the calculation and processing unit 20 to detect the infrared image of the finger 1C calculation looks for at least one temperature distribution feature and other features, for example: body surface temperature [about 36.5°C].

Please refer to Figures 9 and 10, for example, the temperature distribution feature includes a finger distribution temperature, a finger contour distribution temperature and a background environment distribution temperature, and the finger contour distribution temperature can be used to define a finger contour shape , so as to use the finger contour shape of the finger contour distribution temperature to confirm whether it is a real finger. The temperature distribution feature of the preferred embodiment of the present invention is compared with the temperature feature of a fake finger image (for example, not reaching the body surface temperature or a non-living finger).

Referring again to Figures 9 and 10, for example, the method for identifying the authenticity of a fingerprint image according to a preferred embodiment of the present invention includes step S2B: then, for example, using the calculation and processing unit 20 to search for the fingerprint image At least one fingerprint block (fingerprint block, the size of the image block is w × h ) and sampling at least one fingerprint recognizable feature (fingerprint recognizable feature), for example: extracting the singular point of the fingerprint image, and the singular point includes the core point and the triangle point.

For example, the types of fingerprints include right loop, left loop, tented arch, plain arch (arch), vortex ( whorl, that is, spiral pattern], eddy pattern (eddy) and S-shaped pattern or double annular pattern (S-type or twin loop).

Referring again to Figures 9 and 10, for example, the method for identifying the authenticity of a fingerprint image according to a preferred embodiment of the present invention includes step S3: then, for example, using the temperature comparison unit 21 to characterize the temperature distribution Perform authenticity comparison with a finger block temperature parameter, so as to generate a finger authenticity comparison result, and the finger block temperature parameter can be selected between a minimum body temperature and a maximum body temperature or other appropriate ranges, And the finger block temperature parameter is combined with an ambient temperature parameter, such as: summer ambient temperature, winter ambient temperature, severe cold ambient temperature, day ambient temperature, night ambient temperature, high temperature working ambient temperature, low temperature working ambient temperature or other ambient temperatures.

Referring again to Figures 9 and 10, for example, the method for identifying the authenticity of a fingerprint image according to a preferred embodiment of the present invention includes step S4: Next, for example, the fingerprint identification unit 30a is used to perform a fingerprint identification feature. Fingerprint identification operation to obtain a fingerprint identification result; if the authenticity comparison result of the finger is "not a real finger", choose to terminate the fingerprint identification operation immediately, and record the fingerprint image and its fingerprint identification characteristics in the system.

Please refer to Figures 9 and 10. For example, since the temperature comparison unit 21 or the fingerprint identification unit 30a is connected to the verification and comparison unit 40 or an output unit, the authenticity comparison result or fingerprint of the finger is obtained. distinguish The identification result is outputted through the output unit, and the fingerprint image and its fingerprint identification features that fail to be identified can also be selected to be output.

FIG. 11 shows a schematic block diagram of the Internet of Things security system connected to the medical management center according to the preferred embodiment of the present invention. Referring to FIG. 11, compared to the first embodiment, the facial image authenticity identification system 6 or the fingerprint image authenticity identification system 7 according to the third preferred embodiment of the present invention is connected to a medical management center 103 so as to output a Fever body temperature signature or a hyperthermic body temperature signature [or body temperature signature record data, data profile] to the medical management center 103, and the medical management center 103 is selected from a cloud medical management center or a cloud epidemic prevention management center [eg: Covid 19 epidemic prevention ], and another combination to generate a contact history or activity track, such as a cell phone signal track, an internal or external movement track, a travel track, or any combination thereof.

Please refer to FIG. 11 again, for example, the face image authenticity identification system 6 or the fingerprint image authenticity identification system 7 is connected to a temperature detection unit 2 so as to use the temperature detection unit 2 to detect the environment temperature, and the calculation and processing unit 20 calculates and generates the ambient temperature parameter, and compares the temperature distribution feature with an ambient temperature feature.

Please refer to FIG. 11 again. For example, the face image authenticity identification system 6 or the fingerprint image authenticity identification system 7 is connected to operate a standby device, so as to output the finger authenticity comparison result or the fingerprint identification result to the standby device, and the standby device includes a standby computer device 51, a standby mobile communication device 52 or other standby devices, such as a standby door lock device or a standby electrical device, and the standby computer device 51 or the standby mobile communication device 52 can be Select to connect the communication to the medical management center 103 .

The foregoing preferred embodiment is only an example of the present invention and its technical features, and the technology of this embodiment can still be implemented in various substantially equivalent modifications and/or alternative ways; therefore, the scope of the right of the present invention is subject to the appended patent application The scope defined by the scope shall prevail. The copyright in this case is restricted to be used for the purposes of the ROC patent application.

1: Wireless security system

100: Cloud IoT System

101: Central Control Center

102: Mobile Browsing Devices

11: Gateway host

12: Sensing network

121: Short-range wireless communication device

13: Control monitoring device

131: Warning device

Claims (10)

An Internet of Things security method, which includes: Using an image capturing unit to capture at least a face image on a face to be identified in a security monitoring area; Finding at least one face block in the face image and sampling at least one face recognition feature; Correspondingly detect at least one target to-be-identified data on the face to be identified or its surrounding objects; extracting at least one identifiable feature from the target data to be identified; Use the face recognition feature to perform a face recognition operation to obtain a face recognition result, and further identify the recognizable feature to obtain an auxiliary verification result; and The face recognition result and the auxiliary verification result are used for verification and comparison to obtain a verification and comparison result. According to the Internet of Things security method described in item 1 of the scope of the application, the target data to be recognized is selected from a voice data to be recognized, a fingerprint data to be recognized, an image data of a license plate to be recognized, or any combination thereof. According to the Internet of Things security method described in item 1 of the claimed scope, the recognizable feature is selected from a voiceprint feature, a fingerprint feature, a license plate image feature or any combination thereof. According to the Internet of Things security method described in item 1 of the scope of the patent application, the image capturing unit is disposed in a car passage, an access control passage, an equipment machine or any combination thereof. According to the Internet of Things security method described in item 1 of the scope of the patent application, the face recognition result, the auxiliary verification result and the verification comparison result are connected and transmitted to a cloud Internet of Things system. An Internet of Things security system, which includes: an image capturing unit, which captures at least a face image of a face to be identified in a security monitoring area; an arithmetic and processing unit connected to the image capture unit and in the Finding at least one face block in the face image and sampling at least one face recognition feature; a face recognition unit, which is connected to the calculation and processing unit, and uses the face recognition feature to perform a face recognition operation to obtain a face recognition result; and an auxiliary recognition unit, which is connected to the calculation and processing unit, and correspondingly detects at least one target-to-be-recognized data on the to-be-recognized face or its surrounding objects, and extracts at least one recognizable feature from the target to-be-recognized data ; The face recognition feature is used to perform a face recognition operation to obtain a face recognition result, and the recognizable feature is further identified to obtain an auxiliary verification result, and the face recognition result and the auxiliary verification result are used for verification. Alignment to obtain a validating alignment result. According to the Internet of Things security system described in item 6 of the patent application scope, the target data to be recognized is selected from a voice data to be recognized, a fingerprint data to be recognized, an image data of a license plate to be recognized, or any combination thereof. According to the Internet of Things security system described in item 6 of the scope of the application, the identifiable feature is selected from a voiceprint feature, a fingerprint feature, a license plate image feature or any combination thereof. According to the Internet of Things security system described in item 6 of the scope of the patent application, wherein the image capturing unit is arranged in a car passage, an access control passage, an equipment machine or any combination thereof. According to the Internet of Things security system described in Item 6 of the scope of the patent application, the face recognition result, the auxiliary verification result and the verification comparison result are connected and transmitted to a cloud Internet of Things system.

Images