Infrared authentic identification device for paper money authentic identification

Abstract

The utility model belongs to the field of banknote authentication, particularly relates to an infrared authentication device for banknote authentication, and aims to solve the problems that an existing authentication device is uneven in infrared light band, easy to be interfered by dust and low in receiving sensitivity and affects the accuracy and reliability of banknote authentication. The device comprises an upper module and a lower module which are arranged in the currency counting machine, a currency counting channel is arranged between the upper module and the lower module, an infrared transmitting tube component and an infrared receiving tube component are respectively arranged in the currency counting channel, and the infrared transmitting tube component and the infrared receiving tube component are arranged in an up-and-down correlation mode. By optimizing the structural design of the infrared transmitting tube component and the infrared receiving tube component, an infrared light band is more uniform, a signal penetrating paper money is more stable, the accuracy of paper money identification is improved, the dustproof glass and the filter glass effectively prevent dust and stray light from interfering with the identification process, and the accuracy of paper money identification is improved. And the anti-interference capability of the device and the consistency of output signals are enhanced.

Description

Technical Field

[0001] The utility model relates to the technical field of banknote counterfeiting identification, in particular to an infrared counterfeiting identification device for banknote counterfeiting identification. Background Art

[0002] With the increasing frequency of modern financial transactions and the increasing volume of banknotes in circulation, banknote authenticity verification has become a critical component in various industries, including finance and retail. Traditional banknote authentication methods rely primarily on manual observation and feel, which is inefficient and prone to errors. In recent years, with the rapid development of optoelectronic technology, infrared counterfeit detection technology has been gradually applied to banknote authentication. Infrared counterfeit detection technology utilizes the penetrating properties of infrared light and its absorption by different substances to detect changes in the infrared light after it passes through the banknote to verify its authenticity.

[0003] However, existing infrared counterfeit detection devices still have some shortcomings in structural design and usage effects, such as uneven infrared light band, susceptibility to dust interference, low receiving sensitivity, and large output signal errors, which affect the accuracy and reliability of banknote identification.

[0004] In view of the above problems, this utility model document proposes an infrared counterfeit detection device for banknotes. Utility Model Content

[0005] The purpose of the utility model is to solve the shortcomings of the prior art, such as uneven infrared light band, susceptibility to dust interference, low receiving sensitivity, and large signal error, which affect the accuracy and reliability of banknote identification, and to propose an infrared counterfeit identification device for banknote identification.

[0006] In order to achieve the above purpose, the present invention adopts the following technical solutions:

[0007] An infrared counterfeit detection device for banknotes includes an upper module and a lower module disposed in a banknote counter, a banknote counting channel being provided between the upper and lower modules, an infrared emitting tube component and an infrared receiving tube component being respectively installed in the banknote counting channel, the infrared emitting tube component and the infrared receiving tube component being disposed in an up-down direction opposite to each other;

[0008] The infrared emitting tube component includes an infrared emitting tube housing, which is installed in the upper module. A support frame is fixedly connected to the infrared emitting tube housing. A first circuit board is installed above the support frame. The bottom of the first circuit board is electrically connected to a plurality of infrared emitting tubes. A light homogenizing plate is installed inside the infrared emitting tube housing to form a uniform infrared light band.

[0009] The infrared receiving tube component includes an infrared receiving tube shell, which is installed in the lower module. A receiving grid is installed in the infrared receiving tube shell. A second circuit board is provided at the bottom of the receiving grid, and several infrared receiving tubes are electrically connected to the top of the second circuit board.

[0010] In a possible design, a plurality of the infrared emitting tubes are arranged in a linear array.

[0011] In a possible design, a plurality of the infrared receiving tubes are arranged in a linear array to receive voltage signal data information generated when infrared light bands penetrate banknotes during identification.

[0012] In a possible design, dust-proof glass is installed at the bottom of the infrared emitting tube housing.

[0013] In a possible design, a filter glass is installed above the infrared receiving tube housing.

[0014] In a possible design, the infrared emitting tube component and the infrared receiving tube component are designed as independent modular components.

[0015] In a possible design, a plurality of legs are fixedly connected to the bottom of the banknote counter.

[0016] In the present application, when banknotes pass through the banknote counting channel, the infrared emitting tube in the infrared emitting tube component emits infrared rays to form a uniform infrared light band.

[0017] This infrared light band penetrates the banknote and is received by the infrared receiving tube in the infrared receiving tube component.

[0018] The voltage signal data information generated after the infrared light band received by the infrared receiving tube penetrates the banknote is used to identify the authenticity of the banknote.

[0019] The filter glass and dust-proof glass respectively improve the receiving sensitivity and prevent dust from entering, ensuring the accuracy of authentication and the reliability of the device.

[0020] Beneficial effects:

[0021] In the present invention, the infrared counterfeit detection device for banknotes optimizes the structural design of the infrared emitting tube component and the infrared receiving tube component, so that the infrared light band is more uniform and the signal after penetrating the banknote is more stable, thereby improving the accuracy of banknote identification.

[0022] In the present utility model, an infrared counterfeit detection device for banknotes is provided with dustproof glass, filter glass and light homogenizing plate in the infrared transmitting tube component and the infrared receiving tube component, respectively, which effectively prevents dust and stray light from interfering with the counterfeit detection process, and enhances the anti-interference ability of the device and the consistency of the output signal. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a schematic diagram of the internal cross-sectional structure of a banknote counter of an infrared counterfeit detection device for banknote counterfeiting proposed by the present invention;

[0024] Figure 2 This is a schematic diagram of the front opening structure of the upper and lower modules of an infrared counterfeit detection device for banknote counterfeiting proposed by the present invention;

[0025] Figure 3 This is a schematic diagram of the structure of the upper and lower modules of the infrared counterfeit detection device for banknote counterfeiting proposed by the present invention, with the side bevels opened;

[0026] Figure 4 This is a schematic diagram of the exploded structure of an infrared array transceiver tube of an infrared counterfeit detection device for banknotes proposed in the present invention;

[0027] Figure 5 The figure is a side view structural diagram of the upper and lower modules of the infrared array of an infrared counterfeit detection device for banknote counterfeiting proposed by the present invention.

[0028] In the figure: 1. Upper module; 2. Lower module; 3. Infrared emitting tube component; 4. Infrared receiving tube component; 5. First circuit board; 6. Infrared emitting tube; 7. Support frame; 8. Light homogenizer; 9. Infrared emitting tube housing; 10. Dust-proof glass; 11. Filter glass; 12. Infrared receiving tube housing; 13. Receiving grille; 14. Infrared receiving tube; 15. Second circuit board; 16. Money counting channel. DETAILED DESCRIPTION

[0029] 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.

[0030] Example 1

[0031] Reference Figure 1-Figure 5 An infrared counterfeit detection device includes: an upper module 1 and a lower module 2 are arranged in a banknote counter, and a banknote counting channel 16 is formed between the two modules.

[0032] In the banknote counting channel 16 , the upper module 1 is equipped with an infrared emitting tube component 3 , and the lower module 2 is equipped with an infrared receiving tube component 4 , and the infrared emitting tube component 3 and the infrared receiving tube component 4 are arranged in an up-and-down manner.

[0033] The infrared emitting tube component 3 includes an infrared emitting tube housing 9 , which is fixedly installed in the upper module 1 .

[0034] A support frame 7 is installed in the infrared emitting tube housing 9 , and the first circuit board 5 is fixedly connected to the top of the support frame 7 .

[0035] A plurality of infrared emitting tubes 6 are electrically connected to the bottom of the first circuit board 5 , and the infrared emitting tubes 6 are arranged in a linear array.

[0036] A light homogenizing plate 8 is installed at the bottom of the infrared emitting tube housing 9 to form the light emitted by the infrared emitting tube 6 into a uniform infrared light band.

[0037] A dustproof glass 10 is also installed at the bottom of the infrared emitting tube housing 9 to prevent dust from entering.

[0038] The infrared receiving tube component 4 includes an infrared receiving tube housing 12 , which is fixedly installed in the lower module 2 .

[0039] A receiving grid 13 is installed in the infrared receiving tube housing 12 , and a second circuit board 15 is provided at the bottom of the receiving grid 13 .

[0040] A plurality of infrared receiving tubes 14 are electrically connected above the second circuit board 15 , and the infrared receiving tubes 14 are arranged in a linear array.

[0041] A filter glass 11 is installed above the infrared receiving tube housing 12 to filter non-infrared light and improve receiving sensitivity.

[0042] The present application can be used in the field of banknote counterfeiting detection, and can also be used in other fields applicable to the present application.

[0043] Example 2

[0044] refer to Figure 1-Figure 5 , improved on the basis of Example 1:

[0045] An infrared counterfeit detection device for banknotes, which is applied to the field of banknotes counterfeit detection;

[0046] The method for identifying banknotes by an infrared counterfeit detection device includes: collecting, processing, analyzing, identifying and judging, and outputting results.

[0047] Collection method: Through effective circuit design and control, when the banknote counting is turned on, the infrared lamp beads in the infrared emitting tube component will be turned on to emit infrared light bands. When the banknote passes through the infrared receiving tube component, the circuit controls the infrared receiving tubes in the infrared receiving tube component to output voltage signals in sequence, thereby collecting and forming a row of data information. The process controls the cycle of collecting input data information at a certain time interval and continuously stores the obtained data information in the chip memory until the banknote leaves the infrared receiving tube component, and the collection of a banknote is completed. By splicing the stored data information, an infrared transmission characteristic image consisting of rows and columns is generated;

[0048] Processing method: The collected image includes the favorable infrared transmission characteristic image of the banknote and the useless blank portion outside the banknote edge. The collected voltage information value is converted through an image algorithm and a threshold reference judgment. After processing, a binary image is formed. This can be used to crop and eliminate the useless portion of the original image, thereby obtaining a complete infrared transmission characteristic image of the banknote for counterfeit detection and recognition;

[0049] Analysis method: The binarized image can quickly determine the edge position of the banknote, making it easier to calculate information such as the banknote's tilt angle, outline, and size.

[0050] Identification and judgment method: The image is tilt-corrected and rotated to generate a set frontal image. The image is downsampled to 64*64 size. The improved MobileNet network structure is used to extract features from the image. The features extracted by the convolutional network are processed to generate input suitable for the Transformer. The Transformer classification model outputs the authenticity probability for authenticity judgment. The specific steps are as follows:

[0051] 1. Image preprocessing

[0052] 1) Tilt Correction and Orientation: Tilt the collected currency images to ensure they are facing up and maintain a consistent orientation. This stabilizes feature positions, reduces rotation interference, and provides accurate input for position encoding in the subsequent Transformer model.

[0053] 2) Image downsampling: Perform Gaussian downsampling on the image, scaling it to 64x64. Compared to traditional downsampling methods, Gaussian downsampling can better preserve high-frequency information in the image, such as watermarks, black watermarks, security lines, zebra stripes, and other important authentication features;

[0054] 3) Image Normalization: Normalize the sampled image data to the range [-1, 1]. By performing variance scaling on the original data and subtracting the mean (the mean and variance are statistically derived from the training samples), the network’s robustness is improved and more efficient network training is facilitated.

[0055] 2. Feature Extraction

[0056] 1) Feature Extraction: To conserve computational resources, we use a modified MobileNet lightweight network to extract features from images. The network outputs feature maps of size 24x16x16, which helps reduce computational overhead while preserving key image information.

[0057] 3. Feature processing and classification

[0058] 1) Face value, face orientation, and version identification: The feature map is subjected to two 3x3 convolutions and then connected to a fully connected layer to identify the currency type, face value, face orientation, and version.

[0059] 2) Feature map processing: The extracted feature maps are subjected to 2x2 mean pooling and fused into a 64x24 feature vector. Subsequently, the position encoding is added to the feature vector so that the Transformer model can accurately process the position information.

[0060] 3) Transformer authenticity discrimination: The processed feature vector is input into the improved Transformer model. The attention mechanism in the Transformer can focus on the key features in the image, thereby improving the identification ability.

[0061] 4. Loss calculation

[0062] 1) Cross-entropy loss: Use the cross-entropy loss function to calculate the class probability. The loss function is calculated as follows:

[0063]

[0064] Where N is the number of samples, y i is the actual label, p i is the predicted probability.

[0065] Output

[0066] If the image algorithm successfully determines all the features of the banknote being counted and the comprehensive statistical analysis meets the preset template standard of the banknote detector software algorithm, the output is a real banknote and the currency, denomination, version and other information of the banknote are obtained. Otherwise, the output is a counterfeit banknote.

[0067] The above is only a preferred specific implementation method of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with the technical field within the technical scope disclosed by the present invention can make equivalent replacements or changes based on the technical solution and utility model concept of the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An infrared counterfeit detection device for banknotes, characterized in that: include: An upper module (1) and a lower module (2) are arranged in a banknote counting machine, a banknote counting channel (16) is provided between the upper module (1) and the lower module (2), an infrared emitting tube component (3) and an infrared receiving tube component (4) are respectively installed in the banknote counting channel (16), and the infrared emitting tube component (3) and the infrared receiving tube component (4) are arranged in an up-down direction; The infrared emitting tube component (3) includes an infrared emitting tube housing (9), the infrared emitting tube housing (9) is installed in the upper module (1), a support frame (7) is fixedly connected to the infrared emitting tube housing (9), a first circuit board (5) is installed above the support frame (7), a plurality of infrared emitting tubes (6) are electrically connected to the bottom of the first circuit board (5), and a light homogenizing plate (8) is installed inside the infrared emitting tube housing (9) for forming the light emitted by the infrared emitting tube (6) into a uniform infrared light band; The infrared receiving tube component (4) comprises an infrared receiving tube housing (12), the infrared receiving tube housing (12) being installed in the lower module (2), a receiving grid (13) being installed in the infrared receiving tube housing (12), a second circuit board (15) being provided at the bottom of the receiving grid (13), and a plurality of infrared receiving tubes (14) being electrically connected above the second circuit board (15).

2. The infrared counterfeit detection device for banknotes according to claim 1, characterized in that: A plurality of infrared emitting tubes (6) are arranged in a line to form a linear array.

3. The infrared counterfeit detection device for banknotes according to claim 1, characterized in that: A plurality of infrared receiving tubes (14) are arranged in a line array to receive voltage signal data information generated when infrared light bands penetrate banknotes during identification.

4. The infrared counterfeit detection device for banknotes according to claim 1, characterized in that: A dustproof glass (10) is installed at the bottom of the infrared emitting tube housing (9).

5. The infrared counterfeit detection device for banknotes according to claim 1, characterized in that: A filter glass (11) is installed above the infrared receiving tube housing (12).

6. The infrared counterfeit detection device for banknotes according to claim 1, characterized in that: The infrared emitting tube component and the infrared receiving tube component are designed as independent modular components.

7. The infrared counterfeit detection device for banknotes according to claim 1, characterized in that: A plurality of supporting legs are fixedly connected to the bottom of the money counter.

Images