Integrated information acquisition equipment for transaction supervision

Abstract

The invention discloses integrated information acquisition equipment for transaction supervision, and relates to the technical field of acquisition equipment. Through cooperation of the control module and the detection assembly, personnel identity information is conveniently collected or verified, the ability of collecting and modifying the personnel identity information is achieved, then through cooperation of the control module and the collection assembly, personnel body information is conveniently collected, and the comprehensive information collection ability is achieved; height verification is firstly performed through the analysis module, and if height data detection is abnormal, the face recognition operation is stopped, so that the operation burden of the processor is reduced; a large amount of storage space is saved, so that storage resources of the equipment can be utilized more efficiently; according to the method, the iris features are acquired and compared after the pupil position is accurately determined, so that the iris region can be accurately divided, the integrity and accuracy of iris feature extraction are greatly improved, and the problem of identity verification errors caused by inaccurate iris region division is effectively avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of collection equipment, and in particular to an integrated information collection equipment for transaction supervision. Background Art

[0002] The integrated information collection equipment is a hardware device of the integrated personnel basic information collection system. This collection device can usually realize many functions such as computer, mobile phone information collection device, finger (palm) print collection device, second-generation ID card reader, DNA collection special drawer (cabinet), drying box, barcode reader, printer, barcode printer, portrait collection, etc., and can realize comprehensive and accurate personnel information collection with the matching software system;

[0003] However, in transaction supervision activities, there are often situations where people need to change their identity information. Although there is a department dedicated to information change, people usually tend to understand the situation through the paths they are familiar with. Therefore, some people in need will go to the registration office for help, but because the existing equipment does not have the ability to verify the change, they are told that they need to go elsewhere to solve the problem, which is very inconvenient;

[0004] The identity of a person is authenticated through facial recognition, which is cumbersome. Repeated facial recognition increases the computing burden of the processor, which may cause the device to heat up and performance to degrade. Each recognition generates a large amount of image data and feature information. Repeated execution will quickly occupy the storage space. The pupil position is not determined, and iris feature comparison is performed directly, resulting in inaccurate division of the iris area, which in turn affects the integrity and accuracy of feature extraction.

[0005] Therefore, the present invention improves the existing equipment in view of the above problems. Summary of the invention

[0006] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an integrated information collection device for transaction supervision.

[0007] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: an integrated information collection device for transaction supervision, including an equipment box, a plurality of ventilation strips are provided on the back of the equipment box, a passage is provided on one side of the top surface of the equipment box, a control module is provided at the passage, the control module is provided with a detection component, a printing component is provided in the middle of the equipment box, and a collection component is provided on one side of the outer side of the equipment box.

[0008] The detection component includes an acquisition module, an analysis module, and a change module;

[0009] The acquisition module detects the height and weight data, the distance data between the pressure plate and the top of the head, and the facial image data of the person, and transmits the detected data to the analysis module;

[0010] The analysis module analyzes the distance data between the pressure plate and the top of the head to determine whether there is an abnormality in the detection of the height data. If it is determined that there is an abnormality, the facial recognition operation is stopped; the facial image data is analyzed to determine the exact position of the pupil, and then the iris feature is determined to confirm whether the identity of the person is consistent. After determining that the identity of the person is consistent, a change signal is generated and transmitted to the change module;

[0011] Change module, receives change signal, and unlocks the personnel information change interface.

[0012] Preferably, the detection component includes an input module, which is a plate-shaped screen. The input module is fixed in a mounting hole in the middle of the top surface of the equipment box through a fixing plate. A touch controller is installed under the input module. The touch controller is connected to a transcriber through a connecting wire, and the transcriber is installed and connected to the upper side of the control module by bolts.

[0013] Preferably, a verification module is provided below the side of the control module, and the verification module is fixed on the side of the control module through a mounting frame, and the rear of the verification module is connected to the rear end face of the control module through a wire.

[0014] Preferably, the printing assembly includes a printing module, which is composed of a document printer and an image printer therebelow. Two racks are provided on both sides of the bottom surface of the image printer, and the racks are fixed to the side walls of the equipment box by fastening bolts.

[0015] Preferably, the acquisition component comprises an acquisition module, and the acquisition module consists of a frame and a measurement structure on the frame, and the lower end of the front end surface of the frame is connected to the interface of the front end surface of the control module through a wire.

[0016] Preferably, the measuring structure includes a weight scale, which is installed in the middle of the flat plate below the frame, a slide groove is provided in the middle of the side surface of the frame, a motor is installed and fixed below the slide groove, a threaded rod is connected to the top surface of the motor, a threaded seat is provided on the outer side surface of the top end of the threaded rod, a pressure plate is fixed to the front end surface of the threaded seat, and a pressure sensor is provided at the bottom of the pressure plate.

[0017] Preferably, the analysis module performs the following steps to determine the height data:

[0018] S1: When the pressure data detected reaches the preset pressure threshold, it is determined that the pressure plate is in close contact with the top of the guide's head; then the distance sensors around the contact position of the pressure plate collect the distance data between the top of the head and the pressure plate, and spread it around with the contact point as the center, and sort the distance data in the order of outward diffusion;

[0019] S2: Arrange the collected distance data according to the sorting sequence number, then calculate the difference between the distance data of adjacent sequence numbers, and compare the difference with the preset difference threshold. If the difference between the adjacent distance data is greater than the preset difference threshold, it is determined that there is an abnormality in the collection of the distance data;

[0020] S3: Obtain the serial number of the distance data determined to be collected abnormally, and compare the distance data determined to be collected abnormally with the distance data of its adjacent serial number. If the difference between the abnormal distance data and the distance data of the adjacent serial number is less than a preset difference threshold, it is determined that the detection is wrong and the detection is performed again; otherwise, it is determined that there is an abnormality in the collection of the distance data.

[0021] Preferably, the analysis module performs the following steps to analyze facial data:

[0022] K1: grayscale the collected facial image data, divide the grayscale processed image data into image blocks of the same size according to the size of the pixel block, and then calculate the pixel value of each image block;

[0023] K2: Then compare the grayscale value of the image block with the grayscale value of the adjacent image block. If the ratio of the grayscale value of the selected image block to the grayscale value of the adjacent image block on one side is less than the preset ratio threshold, and the ratio of the grayscale value of the selected image block to the grayscale value of the adjacent image block on the other side is greater than the preset ratio threshold, then the selected image block is determined to be a facial contour image block;

[0024] K3: Take the image block at the center of the facial image after grayscale processing as the center image block, mark the facial contour image block farthest from the center image block as mark one, calculate the maximum spacing data between facial contour image blocks in the same row and column, and record the maximum spacing data as facial width data and facial height data.

[0025] Preferably, the analysis module performs the following steps to determine the pupil position:

[0026] M1: according to the number of rows and columns in the facial image data where the image block is located, the image block is marked with the corresponding row number and column number, which is recorded as the serial number mark;

[0027] M2: Divide the facial image data into four regions with half the value of the facial height data and the facial width data. The two upper regions are recorded as region 1 and region 2 in a clockwise direction, and the two lower regions are recorded as region 3 and region 4. In region 1 and region 2, locate the facial contour image block, and then assign the row number of the located facial contour image block to the image block. and grayscale value Record and number the rows Gray value of the image block at position Perform detection, row number The following relations are satisfied: , is the total number of columns of facial image data; if the comparison ratio is preset , then determine the row number and The grayscale values ​​of the image blocks at the two positions are similar, and the two image blocks are axially symmetric;

[0028] M3: Taking the facial contour image blocks selected in area 1 and area 2 as the starting point, compare the grayscale values ​​of the adjacent image blocks of the image block. If the ratio of the grayscale value of the adjacent image block to the grayscale value of the image block is less than the preset comparison ratio , then the grayscale values ​​of the two image blocks to be compared are determined to be similar, and the adjacent image blocks are marked as Mark 2. Then, starting from the adjacent image blocks, the grayscale values ​​of the adjacent image blocks are compared again until, starting from any image block containing Mark 2, there is no image block without Mark 2 at the adjacent position that satisfies the grayscale value of "the ratio of the grayscale values ​​of the two adjacent image blocks is less than the preset comparison ratio" ”;

[0029] M4: row number of the image block containing label 2 and column number Retrieve and take the image block with the largest row and column number. If , then the image block containing the second label is recorded as the eye image block; the row number and column number The corresponding position is the center of the eye socket. Taking the center of the eye socket as the base point, extend to both sides, compare the grayscale values, and determine the position distribution of the pupil and the white of the eye; then focus on the pupil position, collect the pupil data of the guide, and compare it with the iris data in the iris feature template database of legal persons pre-entered in the device, and compare the currently collected and generated iris feature codes with the templates in the database one by one. By calculating the similarity between the two, if the similarity between the two reaches the preset threshold, it is determined to be a successful match, confirming that the identity of the person is consistent with the corresponding identity in the database, generating a change signal, and passing the change signal to the change module; otherwise, it is determined that the identity does not match and needs to be re-detected.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] 1. Through the cooperation of the control module and the detection component, it is convenient to collect or verify the identity information of the personnel, improve the practicality, and realize the ability to collect and modify the identity information of the personnel. Through the cooperation of the control module and the printing module, it is convenient to print paper vouchers or forms, improve the practicality, and realize the ability to complete the verification process automatically in real time. Through the cooperation of the control module and the collection component, it is convenient to collect the physical information of the personnel, improve the practicality, and realize the comprehensive information collection ability, and finally solve the problem that the existing equipment does not have the ability to verify and change information;

[0032] 2. Perform height verification first through the analysis module. If the height data is detected to be abnormal, the facial recognition operation is stopped, avoiding unnecessary facial recognition processes and reducing the number of facial recognition executions, thereby reducing the computing burden of the processor, effectively preventing the device from heating up due to excessive computing, ensuring stable device performance, and not declining due to high-load computing caused by multiple facial recognitions; saving a lot of storage space, so that the storage resources of the device can be used more efficiently, without the need to frequently clean up or expand the storage space to cope with a large amount of recognition data; collecting and comparing iris features after accurately determining the pupil position can ensure that the iris area division is accurate, greatly improving the integrity and accuracy of iris feature extraction, and effectively avoiding identity authentication errors caused by inaccurate iris area division. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0034] Figure 1 This is a three-dimensional schematic diagram of the overall appearance of the device proposed by the present invention;

[0035] Figure 2This is a schematic front view of the overall appearance of the device proposed by the present invention;

[0036] Figure 3 This is a three-dimensional schematic diagram of the detection component structure proposed by the present invention;

[0037] Figure 4 A three-dimensional schematic diagram of the printing assembly structure proposed by the present invention;

[0038] Figure 5 This is a three-dimensional schematic diagram of the structure of the collection component proposed by the present invention;

[0039] Figure 6 This is a system flow chart proposed by the present invention.

[0040] Serial numbers in the figure: 1. Equipment box; 2. Control module; 3. Printing module; 4. Input module; 5. Acquisition module; 6. Verification module; 7. Mounting bracket; 8. Transcriber; 9. Touch controller; 10. Fixing plate; 11. Storage rack; 12. Fastening bolts; 13. Motor; 14. Threaded rod; 15. Press plate. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0042] Example: See Figure 1-6 The present invention provides an integrated information collection device for transaction supervision, including an equipment box 1, a plurality of ventilation strips are provided on the back of the equipment box 1, a through opening is provided on one side of the top surface of the equipment box 1, a control module 2 is provided at the through opening, the control module 2 is provided with a detection component, a printing component is provided in the middle of the equipment box 1, and a collection component is provided on one side of the outer side of the equipment box 1. The modular design facilitates the maintenance and upgrading of the device and improves the practicality; the detection component includes an input module 4, the input module 4 is a plate-shaped screen, the input module 4 is fixed in the installation opening in the middle of the top surface of the equipment box 1 through a fixing plate 10, and a A touch controller 9 is connected to a transcriber 8 through a connecting wire, and the transcriber 8 is installed and connected to the upper side of the control module 2 through bolts. Through the cooperation of the input module 4, the transcriber 8 and the touch controller 9, it is convenient to display information and guide personnel to touch and input information, thereby improving practicality. A verification module 6 is provided at the lower side of the control module 2, and the verification module 6 is installed and fixed on the side of the control module 2 through a mounting frame 7. The rear of the verification module 6 is connected to the rear end face of the control module 2 through a wire. Through the cooperation of the control module 2 and the verification module 6, it is convenient to call up personnel information and complete information verification changes as quickly as possible, thereby improving practicality.

[0043] In the present invention, the printing component includes a printing module 3, which is composed of a document printer and an image printer below it. Two racks 11 are provided on both sides of the bottom surface of the image printer. The racks 11 are fixed to the side walls of the equipment box 1 by fastening bolts 12. Through the cooperation of the document printer and the image printer, it is convenient to output paper documents and photo materials, thereby improving practicality; the collection component includes a collection module 5, which is composed of a frame and a measuring structure on the frame. The lower end of the front end surface of the frame is connected to the interface of the front end surface of the control module 2 through a wire. The measuring structure includes a weighing scale, which is installed in the middle of the flat plate below the frame, and a slide groove is provided in the middle of the side surface of the frame. A motor 13 is fixedly installed under the slide groove, and a threaded rod 14 is connected to the top surface of the motor 13. A threaded seat is sleeved on the outer side of the top of the threaded rod 14, and a pressing plate 15 is fixedly connected to the front end surface of the threaded seat. A pressure sensor is arranged at the bottom of the pressing plate 15. Through the setting of the powder discharge sensor, when the pressing plate 15 touches the user's head, a signal can be sent to the control module 2 inside the equipment box 1. The control module 2 stops driving the motor 13, and controls the cooperation between the motor 13 and the threaded rod 14 to drive the pressing plate 15 to rise and reset. Through the cooperation of the weighing device, the motor 13 and the pressing plate 15, it is convenient to collect the height and weight information of different people, thereby improving the practicality of the device.

[0044] The detection component includes an acquisition module, an analysis module, and a change module;

[0045] When the pressure plate 15 descends to contact the top of the guide's head, the pressure data between the two is detected. When the detected pressure data reaches the preset pressure threshold, it is determined that the pressure plate 15 is in close contact with the top of the guide's head; then the distance sensors around the contact position of the pressure plate 15 collect the distance data between the top of the head and the pressure plate 15, and spread it around with the contact point as the center, and sort the distance data in the order of outward diffusion;

[0046] Arrange the collected distance data according to the sorting sequence number, then calculate the difference between the distance data of adjacent sequence numbers, and compare the difference with the preset difference threshold. If the difference between the adjacent distance data is greater than the preset difference threshold, it is determined that there is an abnormality in the collection of the distance data;

[0047] Obtain the serial number of the distance data that is judged to be collected abnormally, and compare the distance data that is judged to be collected abnormally with the distance data of its adjacent serial number. If the difference between the abnormal distance data and the distance data of the adjacent serial number is less than the preset difference threshold, it is judged that the detection is wrong and the detection is performed again; otherwise, it is determined that there is an abnormality in the collection of the distance data.

[0048] When the guide is testing the weight and height data on the weighing machine, the camera device on the acquisition module 5 can collect the facial image data of the guide, and the analysis module grayscales the collected facial image data, divides the grayscale processed image data according to the size of the pixel block, and divides it into image blocks of the same size, and then calculates the pixel value of each image block; then compares the grayscale value of the image block with the grayscale value of the adjacent image block, if the ratio of the grayscale value of the selected image block to the grayscale value of the adjacent image block on one side is less than the preset ratio threshold, and the ratio of the grayscale value of the adjacent image block on the other side is greater than the preset ratio threshold, then the selected image block is determined to be a facial contour image block; the image block at the center position of the facial image after grayscale processing is taken as the central image block, the facial contour image block farthest from the central image block is marked as mark one, and the maximum spacing data between the facial contour image blocks in the same row and column is calculated, and the maximum spacing data is recorded as facial width data and facial height data;

[0049] According to the number of rows and columns in the facial image data where the image block is located, the image block is marked with a corresponding row number and column number, recorded as a serial number mark;

[0050] The facial image data is divided into four regions with half the value of the facial height data and the facial width data. The two regions of the upper layer are respectively recorded as region 1 and region 2 in the clockwise direction, and the two regions of the lower layer are respectively recorded as region 3 and region 4. In region 1 and region 2, the facial contour image block is located, and then the row number of the facial contour image block obtained by the location is and grayscale value Record and number the rows Gray value of the image block at position Perform detection, row number The following relations are satisfied: , is the total number of columns of facial image data; if the comparison ratio is preset , then determine the row number and The grayscale values ​​of the image blocks at the two positions are similar, and the two image blocks are axially symmetric;

[0051] Then, the facial contour image blocks selected in area 1 and area 2 are used as the starting point to compare the grayscale values ​​of the adjacent image blocks of the image block. If the ratio of the grayscale value of the adjacent image block to the grayscale value of the image block is less than the preset comparison ratio , then the grayscale values ​​of the two image blocks to be compared are determined to be similar, and the adjacent image blocks are marked as Mark 2. Then, starting from the adjacent image blocks, the grayscale values ​​of the adjacent image blocks are compared again until, starting from any image block containing Mark 2, there is no image block without Mark 2 at the adjacent position that satisfies the grayscale value of "the ratio of the grayscale values ​​of the two adjacent image blocks is less than the preset comparison ratio" ”;

[0052] The row number of the image block containing label 2 and column number Retrieve and take the image block with the largest row and column number. If , then the image block containing the second label is recorded as the eye image block; the row number and column number The corresponding position is the center of the eye socket. Taking the center of the eye socket as the base point, extend to both sides, compare the grayscale values, and determine the position distribution of the pupil and the white of the eye; then focus on the pupil position, collect the pupil data of the guide, and compare it with the iris data in the iris feature template database of legal persons pre-entered in the device, and compare the currently collected and generated iris feature codes with the templates in the database one by one. By calculating the similarity between the two, if the similarity between the two reaches the preset threshold, it is determined to be a successful match, confirming that the identity of the person is consistent with the corresponding identity in the database, generating a change signal, and passing the change signal to the change module; otherwise, it is determined that the identity does not match and needs to be re-detected.

[0053] Working principle: When the present invention is used, firstly, power is supplied to all electrical devices, then all electrical devices are started, and then the personnel are guided to stand in front of the equipment box 1, and the basic identity information of the personnel is input by touching the input module 4. The electrical signal of the touch input module 4 is translated into a digital signal by the transcriber 8, and then enters the control module 2, and then is stored in the database. After the identity information is input, the personnel are guided to stand on the weighing device on the collection module 5, and then the personnel are guided to stand straight, and then the collection module 5 is started, the weighing device will collect the weight information of the personnel, and the motor 13 is started at the same time, thereby driving the pressing plate 15 to descend through the threaded rod 14 until the pressing plate 15 touches the top of the person's head, and then collects the person's height information. The electrical signal of the collection module 5 will enter the control module 2 through the wire and then be stored in the database. Moreover, when the pressure plate 15 touches the user's head, it can send a signal to the control module 2 inside the equipment box 1, and the control module 2 stops driving the motor 13, and controls the cooperation between the motor 13 and the threaded rod 14 to drive the pressure plate 15 to rise and reset. When a person needs to change the information, the person is guided to input the verification information by touching the input module 4. The verification module 6 quickly calls the information in the database for identity authentication, and then re-enters the information to complete the information change.

[0054] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An integrated information collection device for transaction supervision, comprising a device box (1), characterized in that: The back of the equipment box (1) is provided with a plurality of ventilation strips, a top side of the equipment box (1) is provided with a through opening, a control module (2) is provided at the through opening, the control module (2) is provided with a detection component, a printing component is provided in the middle of the equipment box (1), and a collection component is provided on one side of the outer side of the equipment box (1); The detection component includes an acquisition module, an analysis module, and a change module; A collection module detects height and weight data, detects distance data between the pressure plate (15) and the top of the head, detects facial image data of the person, and transmits the detected data to the analysis module; An analysis module analyzes the distance data between the pressure plate (15) and the top of the head to determine whether there is an abnormality in the detection of the height data, and if it is determined that there is an abnormality, stops the facial recognition operation; Analyze the facial image data to determine the exact position of the pupil, then determine the iris features to confirm whether the person's identity is consistent. After determining that the person's identity is consistent, generate a change signal and pass the change signal to the change module; Change module, receives change signal, and unlocks the personnel information change interface.

2. The integrated information collection device for transaction supervision according to claim 1, characterized in that: The detection component comprises an input module (4), the input module (4) being a plate-shaped screen, the input module (4) being fixed in a mounting opening in the middle of the top surface of the equipment box (1) via a fixing plate (10), a touch controller (9) being installed below the input module (4), the touch controller (9) being connected to a transcriber (8) via a connecting wire, and the transcriber (8) being installed and connected to the upper side of the control module (2) via bolts.

3. The integrated information collection device for transaction supervision according to claim 1, characterized in that: A verification module (6) is provided below the side of the control module (2); the verification module (6) is mounted and fixed on the side of the control module (2) via a mounting frame (7); the rear of the verification module (6) is connected to the rear end face of the control module (2) via a wire.

4. The integrated information collection device for transaction supervision according to claim 1, characterized in that: The printing assembly comprises a printing module (3), the printing module (3) being composed of a document printer and an image printer below the printing module (3), two storage racks (11) being provided on both sides of the bottom surface of the image printer, the storage racks (11) being mounted and fixed on the side walls of the equipment box (1) by means of fastening bolts (12).

5. The integrated information collection device for transaction supervision according to claim 1, characterized in that: The acquisition component comprises an acquisition module (5), the acquisition module (5) consisting of a frame and a measurement structure on the frame, the lower end of the front end surface of the frame being connected to an interface of the front end surface of the control module (2) via a wire.

6. The integrated information collection device for transaction supervision according to claim 5, characterized in that: The measuring structure comprises a weight scale, which is mounted in the middle of a flat plate below a frame, a slide groove is provided in the middle of a side surface of the frame, a motor (13) is fixedly mounted below the slide groove, a threaded rod (14) is connected to the top surface of the motor (13), a threaded seat is sleeved on the outer side surface of the top end of the threaded rod (14), a pressure plate (15) is fixedly connected to the front end surface of the threaded seat, and a pressure sensor is provided inside the bottom of the pressure plate (15).

7. The integrated information collection device for transaction supervision according to claim 1, characterized in that: The analysis module performs the following steps to identify height data: S1: When the detected pressure data reaches a preset pressure threshold, it is determined that the pressure plate (15) is in close contact with the top of the guide's head; then the distance sensors around the contact position of the pressure plate (15) collect the distance data between the top of the head and the pressure plate (15), and spread the data around the contact point, and sort the distance data in the order of spreading outwards; S2: Arrange the collected distance data according to the sorting sequence number, then calculate the difference between the distance data of adjacent sequence numbers, and compare the difference with the preset difference threshold. If the difference between the adjacent distance data is greater than the preset difference threshold, it is determined that there is an abnormality in the collection of the distance data; S3: Obtain the serial number of the distance data determined to be collected abnormally, and compare the distance data determined to be collected abnormally with the distance data of its adjacent serial number. If the difference between the abnormal distance data and the distance data of the adjacent serial number is less than a preset difference threshold, it is determined that the detection is wrong and the detection is performed again; otherwise, it is determined that there is an abnormality in the collection of the distance data.

8. The integrated information collection device for transaction supervision according to claim 7, characterized in that: The analysis module performs facial data analysis steps as follows: K1: grayscale the collected facial image data, divide the grayscale processed image data into image blocks of the same size according to the size of the pixel block, and then calculate the pixel value of each image block; K2: Then compare the grayscale value of the image block with the grayscale value of the adjacent image block. If the ratio of the grayscale value of the selected image block to the grayscale value of the adjacent image block on one side is less than the preset ratio threshold, and the ratio of the grayscale value of the selected image block to the grayscale value of the adjacent image block on the other side is greater than the preset ratio threshold, then the selected image block is determined to be a facial contour image block; K3: Take the image block at the center of the facial image after grayscale processing as the center image block, mark the facial contour image block farthest from the center image block as mark one, calculate the maximum spacing data between facial contour image blocks in the same row and column, and record the maximum spacing data as facial width data and facial height data.

9. The integrated information collection device for transaction supervision according to claim 8, characterized in that: The analysis module determines the pupil position in the following steps: M1: according to the number of rows and columns in the facial image data where the image block is located, the image block is marked with the corresponding row number and column number, which is recorded as the serial number mark; M2: Divide the facial image data into four regions with half the value of the facial height data and the facial width data. The two upper regions are recorded as region 1 and region 2 in a clockwise direction, and the two lower regions are recorded as region 3 and region 4. In region 1 and region 2, locate the facial contour image block, and then assign the row number of the located facial contour image block to the image block. and grayscale value Record and number the rows Gray value of the image block at position Perform detection, row number The following relations are satisfied: , is the total number of columns of facial image data; if the comparison ratio is preset , then determine the row number and The grayscale values ​​of the image blocks at the two positions are similar, and the two image blocks are axially symmetric; M3: Taking the facial contour image blocks selected in area 1 and area 2 as the starting point, compare the grayscale values ​​of the adjacent image blocks of the image block. If the ratio of the grayscale value of the adjacent image block to the grayscale value of the image block is less than the preset comparison ratio , then the grayscale values ​​of the two image blocks to be compared are determined to be similar, and the adjacent image blocks are marked as Mark 2. Then, starting from the adjacent image blocks, the grayscale values ​​of the adjacent image blocks are compared again until, starting from any image block containing Mark 2, there is no grayscale value of the image block not containing Mark 2 at the adjacent position that satisfies the condition "the ratio of the grayscale values ​​of the two adjacent image blocks is less than the preset comparison ratio" ”; M4: row number of the image block containing label 2 and column number Retrieve and take the image block with the largest row and column number. If , then the image block containing the second label is recorded as the eye image block; the row number and column number The corresponding position is the center of the eye socket. Taking the center of the eye socket as the base point, extend to both sides to compare the grayscale values ​​and determine the position distribution of the pupil and the white of the eye. Then focus on the pupil position, collect the pupil data of the guide, and compare it with the iris data in the iris feature template database of legal persons pre-entered in the device. The currently collected and generated iris feature code is compared with the template in the database one by one, and the similarity between the two is calculated. If the similarity between the two reaches the preset threshold, it is determined to be a successful match, confirming that the identity of the person is consistent with the corresponding identity in the database, generating a change signal, and passing the change signal to the change module; otherwise, it is determined that the identity does not match and re-detection is required.

Images