A fingerprint extraction and recognition system and method based on fluorescent materials

Abstract

The present invention discloses a fingerprint extraction and identification system and method based on fluorescent materials. The system includes a fingerprint library, a handheld terminal, a fingerprint extraction and analysis module; the handheld terminal includes a light source control board, an excitation light source module, a macro lens and a smart phone camera; the fingerprint analysis module has a built-in fingerprint feature extraction algorithm and a fingerprint feature comparison algorithm; the operator places the fingerprint in the sampling area of ​​the handheld terminal, and the fingerprint analysis module runs the fingerprint feature extraction algorithm to call the handheld terminal to extract fingerprint feature information, and then runs the fingerprint feature comparison algorithm to compare the extracted fingerprint feature information with the information in the fingerprint library to realize fingerprint recognition. The present invention integrates fluorescence excitation, fingerprint image acquisition, fingerprint extraction and identification functions, has the characteristics of easy carrying, high timeliness, simple operation and no need for multi-person collaboration, and is suitable for the field of on-site trace inspection technology.

Description

Technical Field

[0001] The invention belongs to the technical field of on-site trace inspection, and in particular relates to a fingerprint extraction and identification system and method based on fluorescent materials. Background Art

[0002] For a long time, fingerprint identification has been widely used in the field of criminal scene investigation as a relatively accurate technology that can identify the target person by comparing the characteristic point information of different fingerprints. On-site fingerprint identification technology usually requires two steps: fingerprint extraction and fingerprint recognition. Fingerprint extraction completes the imaging and extraction of fingerprint information, and fingerprint recognition compares the characteristic points of the fingerprint image and compares the fingerprint with the fingerprint database to confirm the suspect. At present, common fingerprint extraction methods include powder visualization method (Luke Maidment, Peter G. Schunemann, and Derryck T. Reid. White powder identification using broadband coherent light in the molecular fingerprint region, Optics Express, 2018, 26 (19): 25364-25369), fumigation method (J Almog, Y Sasson, A Anati. Chemical reagents for the development of latent fingerprints, 2-controlled addition of water vapor to iopine fumes-a solution to the aging problem, Journal of forensic sciences, 1979, 24 (2): 431-436), silver nitrate method (FM Kerr, AD Westland, F. Haque. Observations on the use of silver compounds for fingerprint visualization, Forensic Science International, 1981, 18 (2): 209-214), laser irradiation method (Eric Michiels, Renaat Gijbels. Fingerprint spectra in Laser Microprobe Mass Analysis of titanium oxides of different stoichiometry, Spectrochimica Acta Part B: Atomic Spectroscopy, 1983, 38 (10): 1347-1354) and photographic extraction methods. Among them, the combination of fluorescent powder development method and photographic method has the characteristics of simplicity, rapidity, long retention time and objective and true reflection of the surrounding environment of fingerprint receptors. It is particularly widely used in criminal investigation scene technology.

[0003] At present, when applying the fingerprint photography extraction technology based on fluorescent powder, it usually requires the cooperation of multiple people, and the fingerprint extraction is completed through the cooperation of the excitation light source and the camera. The open environment and the cooperation of multiple people not only lead to complex steps in the fingerprint extraction process, but also many influencing factors, such as different angles, light and shadow changes in the environment, the stability of the handheld device, etc., resulting in large differences in the clarity of the fingerprint extracted image, which seriously affects the accuracy of fingerprint recognition and identification. At the same time, the results of this fingerprint extraction need to be transmitted to the background before fingerprint recognition can be used, that is, ① fingerprint display ② photo ③ photo back ④ fingerprint recognition comparison (Meng Fanhua, Tian Hualin. Analysis of the application of fingerprint inspection in criminal investigation work, Chinese Science, 2016, 20). This method requires a lot of manpower and material resources when used, which puts a certain pressure on the on-site criminal investigation and hinders the improvement of case handling efficiency.

[0004] In recent years, fingerprint analysis and recognition technology has developed rapidly as an important artificial intelligence algorithm technology that can provide security and public safety protection, and has been widely used in various occasions and a variety of mobile devices (Bang Wang, Qiuyun Chen, Laurence T. Yang, Han-Chieh Chao. Indoor smartphone localization via fingerprint crowdsourcing: challenges and approaches, IEEE Transactions on Multimedia, 2016, 23 (3): 82-89). The system and method proposed in the present invention integrate the fingerprint collection device and the fingerprint analysis and recognition system into one by designing a handheld optical terminal and integrating the fingerprint analysis and recognition algorithm into the smartphone, combined with the powerful image acquisition and processing capabilities of the smartphone, thereby simplifying the case handling process from evidence collection to fingerprint recognition and comparison, and improving the work efficiency of public security on-site criminal investigation personnel. Summary of the invention

[0005] In view of the problems that existing fingerprint extraction systems and methods are expensive, inconvenient to carry, complicated processes, poor detection timeliness, and do not support real-time analysis, the present invention provides a fingerprint extraction and identification system and method based on fluorescent materials.

[0006] The purpose of the present invention is achieved by at least one of the following technical solutions.

[0007] A fingerprint extraction and recognition system based on fluorescent materials, including a fingerprint library, a handheld terminal, and a fingerprint extraction and analysis module;

[0008] The handheld terminal includes a light source control board, an excitation light source module, a macro lens and a smartphone camera;

[0009] The fingerprint analysis module has built-in fingerprint feature extraction algorithm and fingerprint feature comparison algorithm;

[0010] The operator places the fingerprint in the sampling area of ​​the handheld terminal. The fingerprint analysis module runs the fingerprint feature extraction algorithm to call the handheld terminal to extract fingerprint feature information, and then runs the fingerprint feature comparison algorithm to compare the extracted fingerprint feature information with the information in the fingerprint library to achieve fingerprint recognition.

[0011] Furthermore, before fingerprint extraction, a fingerprint imaging magnetic powder made of fluorescent luminescent material should be applied on the fingerprint to absorb excess powder on the surface so that the fingerprint lines can be clearly displayed;

[0012] The fingerprint extraction and analysis module and fingerprint camera imaging are both implemented through a smart phone, wherein the fingerprint extraction and analysis module is carried out in an Android environment, and the camera is a camera in a smart phone, which cooperates with a macro lens to observe fingerprint imaging and then extract fingerprint features.

[0013] Furthermore, the excitation light source module includes a fluorescent excitation light source module and a white light excitation light source module, which are used to realize fingerprint imaging of fingerprint powder under different fingerprint extraction conditions. The fluorescent excitation light source module is an ultraviolet light source, and its function is to provide excitation light with a uniform illumination spot in the fingerprint collection area; the function of the white light excitation light source module is to provide white light with a uniform illumination spot of light intensity, and directly image the fingerprint under a light background.

[0014] Furthermore, when the fingerprint feature extraction algorithm is running, the smartphone camera is called to take pictures, the light source control board switches the excitation light source module under different fingerprint extraction conditions and controls the light intensity change to excite the fluorescent material, the macro lens in the handheld terminal is used to complete the clear image amplification, achieve clear fingerprint imaging, select the appropriate fingerprint collection area, perform image preprocessing, and extract fingerprint features;

[0015] The information in the fingerprint database is fingerprint feature information that is extracted in advance through a fingerprint feature extraction algorithm or directly imported and stored in the smartphone.

[0016] Furthermore, the image preprocessing is to remove the interference of uneven brightness and other noise in the fingerprint image through a series of processing of the original collected fingerprint image, and restore the real image line information through line refinement and repair, as follows:

[0017] The collected image is gray-processed, and the image gray-scale normalization processing is performed using the adaptive local binary image separation method; fingerprint image enhancement is performed; image background segmentation is performed to remove noise interference in the fingerprint as much as possible; the gray-scale maximum value is found in the image as the initial value according to the sequence; the direction value or ridge frequency is calculated for local Gabor filtering; the next point of ridge line tracking is determined; data is compared and determined according to a predetermined threshold to determine whether the termination condition is met. If so, the starting point is returned to for direction tracking. If the reverse tracking is completed, the gray-scale maximum value is re-searched for other point analysis until the entire fingerprint image is traversed.

[0018] Furthermore, the image grayscale normalization process is performed by using the local mean method in the adaptive local binarization method to process the image, by dividing the fingerprint image into non-overlapping, uniformly sized image blocks, and calculating the variance of each block based on the grayscale of the image block: the grayscale of the image block is obtained by calculating the average grayscale value in the block; the grayscale value variance of the image block is obtained by the average grayscale value of the pixels in the block and the average grayscale value; a threshold is set for the variance, and the variance is compared with the threshold to separate the background and fingerprint line area. This method is based on the fact that the variance of the background area is small, while the variance of the fingerprint area is large due to the ridge and valley structure. If the variance of a certain image block is not zero or is far from the threshold, the area is further segmented by threshold; the mean variance algorithm is as follows:

[0019] The size of the fingerprint image is m×m, which is divided into non-overlapping, uniformly sized image blocks, with a block size of n×n; in the fingerprint image, (i, j) indicates the horizontal and vertical coordinate positions of a certain image block in the fingerprint image block, and (u, v) indicates the coordinate position of the pixel in the image block;

[0020] The sum of the grayscale values ​​of each point in the image block is calculated according to the following formula:

[0021]

[0022] Wherein, L(u,v) is the gray value of the pixel in the image block, M(i,j) is the total gray value of the (i,j)th image block, i=1, 2…k, j=1, 2…k, k=m / n;

[0023] The grayscale variance of the image block is:

[0024]

[0025] A(i,j) is the mean gray value in the (i,j)th image block. By setting the threshold of V(i,j), the valid fingerprint area and background area can be determined.

[0026] Select the threshold value T d , if V(i,j)>Td , then the value of the corresponding image block in the image block (i, j) area is set to F(i, j) = 1, and the area where the image block is located is a valid fingerprint area block; otherwise, the value of the image block is set to F(i, j) = 0, and the image block is a background area block.

[0027] Furthermore, the light source control panel includes a light source switch, light intensity control, light source switching and charging functions, which can realize the switching of ultraviolet light sources and white light sources in different environments, and is convenient for the use of equipment in different environments. The built-in battery can realize the charging function to facilitate the use of the equipment at any time, and the power status light is always on when turned on.

[0028] Furthermore, the macro lens and the smartphone camera are arranged in sequence just above the fingerprint collection area; the fluorescent excitation light source module and the white light excitation light source module are distributed symmetrically on both sides of the macro lens and have the same height, and are closely arranged in sequence; the optical axes of the macro lens and the smartphone camera are at an angle of 45 degrees to the central optical axes of the fluorescent excitation light source module and the white light excitation light source module.

[0029] Furthermore, for on-site fingerprints, fingerprint imaging and collection can be performed using either a white light source module or a fluorescent excitation light source module as needed; under complex backgrounds, the fluorescent material can be excited by the fluorescent excitation light source module to highlight the fingerprint, and fingerprint collection can be achieved through handheld terminals and smart phones; for fingerprints that are clearly visible under light backgrounds such as paper and walls, the white light source module of the handheld terminal is used to illuminate and collect the image. The collected fingerprints are compared with the fingerprint library information stored in the smart phone through the fingerprint feature extraction algorithm and fingerprint feature comparison algorithm in the fingerprint analysis module. At the same time, the collected fingerprint image can be shared with other users through a wireless network to achieve cloud comparison.

[0030] A fingerprint extraction and identification method based on fluorescent materials comprises the following steps;

[0031] S1. Fingerprint imaging: Apply fluorescent magnetic fingerprint imaging powder on the fingerprint to absorb excess powder on the surface, so that the fingerprint lines can be clearly displayed;

[0032] S2, fingerprint imaging and fingerprint extraction: Cover the handheld terminal in the fingerprint collection area, place the macro lens directly above the fingerprint, switch the light source module and control the light intensity change through the light source control board, run the fingerprint extraction and analysis module in the smartphone, run the fingerprint feature extraction algorithm, call the smartphone camera to achieve clear fingerprint imaging, perform image preprocessing, and extract fingerprint feature information;

[0033] S3, fingerprint identification: run the fingerprint feature comparison algorithm, compare the fingerprint feature information extracted in step S2 with the fingerprint feature information extracted in advance by the fingerprint feature extraction algorithm or directly imported into the fingerprint library, and complete the fingerprint identification;

[0034] S4. Result display: The fingerprint extraction and analysis module displays the fingerprint recognition result on the smartphone.

[0035] Compared with the prior art, the advantages of the present invention are:

[0036] The present invention combines the image acquisition and data processing functions of a smart phone with optoelectronic technology to develop a portable, single-operable, miniaturized portable fingerprint extraction and recognition system and method. Compared with the prior art, it has the following advantages:

[0037] (1) The optical system is embedded in a handheld terminal and combined with a smartphone, which is easy to carry and can be realized without the need for multiple people to operate;

[0038] (2) Different light sources can be provided in different environments, and the adaptive local threshold method is used to process the light sources, so as to avoid the influence of different clarity on the recognition effect in different environments;

[0039] (3) The integration of multiple technologies can avoid problems such as different clarity in different places and people;

[0040] (4) By combining fingerprint imaging and fingerprint recognition, rapid fingerprint identification can be achieved through the built-in fingerprint library and cloud comparison, with high timeliness. The present invention is suitable for rapid fingerprint extraction and comparison at the crime scene, and can also be widely used in other types of on-site trace analysis, such as palm prints, footprints, etc., and has broad application and market prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Schematic diagram of the isometric structure of the handheld terminal in an embodiment of the present invention.

[0042] Figure 2 FIG. 4 is a top view of a handheld terminal in an embodiment of the present invention.

[0043] Figure 3 for Figure 2 Cross-sectional view along the AA direction.

[0044] Figure 4 It is a functional flow chart of the present invention.

[0045] Figure 5 The present invention is a flow chart of a fingerprint extraction and recognition method based on fluorescent materials. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solutions and features of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0047] Example:

[0048] A fingerprint extraction and recognition system based on fluorescent materials, such as Figure 4 As shown, it includes a fingerprint library, a handheld terminal, and a fingerprint extraction and analysis module;

[0049] In this embodiment, the handheld terminal includes a light source control board 5, an excitation light source module, a macro lens 6 and a smartphone camera;

[0050] The fingerprint analysis module has built-in fingerprint feature extraction algorithm and fingerprint feature comparison algorithm;

[0051] The operator places the fingerprint in the handheld terminal, and the fingerprint analysis module runs the fingerprint feature extraction algorithm to call the handheld terminal to extract fingerprint feature information, and then runs the fingerprint feature comparison algorithm to compare the extracted fingerprint feature information with the information in the fingerprint library in the cloud to achieve fingerprint recognition.

[0052] Before fingerprint extraction, the fingerprint imaging magnetic powder made of fluorescent material should be applied on the fingerprint to absorb the excess powder on the surface so that the fingerprint lines can be clearly seen;

[0053] In this embodiment, the fingerprint extraction and analysis module and the smart phone camera are both implemented by the smart phone 1, wherein the fingerprint extraction and analysis module is carried out in an Android environment, and the smart phone camera is a camera in the smart phone 1, which cooperates with the macro lens 6 to observe the fingerprint imaging and then extract the fingerprint features;

[0054] The excitation light source module includes a fluorescent excitation light source module 7 and a white light excitation light source module 8, which are used to realize fingerprint imaging of fingerprint powder under different fingerprint extraction conditions. The fluorescent excitation light source module 7 is an ultraviolet light source, and its function is to provide excitation light with a uniform illumination spot in the fingerprint collection area; the function of the white light excitation light source module 8 is to provide white light with a uniform illumination spot, and the fingerprint is directly imaged under a light background.

[0055] In this embodiment, the fluorescence excitation light source module 7 includes an ultraviolet lamp 7-1, an ultraviolet light homogenizing lens 7-2 and an ultraviolet filter 7-3, and the white light source module 8 includes a white light lamp 8-1, a white light homogenizing lens 8-2 and a white light homogenizing sheet 8-3.

[0056] When the fingerprint feature extraction algorithm is running, the smartphone camera is called to take pictures, the light source control board 5 switches the excitation light source module under different fingerprint extraction conditions and controls the light intensity change to excite the fluorescent material, the macro lens 6 in the handheld terminal is used to complete the image clear magnification, realize the clear imaging of the fingerprint, select the appropriate fingerprint collection area, perform image preprocessing, and extract the fingerprint features;

[0057] The information in the fingerprint database is fingerprint feature information that is extracted in advance by a fingerprint feature extraction algorithm or directly imported and stored in the smart phone 1 .

[0058] The image preprocessing is to remove the interference of uneven brightness and other noise in the fingerprint image through a series of processing of the original collected fingerprint image, and restore the real image line information through line refinement and repair, as follows:

[0059] The collected image is gray-processed, and the image gray-scale normalization processing is performed using the adaptive local binary image separation method; fingerprint image enhancement is performed; image background segmentation is performed to remove noise interference in the fingerprint as much as possible; the gray-scale maximum value is found in the image as the initial value according to the sequence; the direction value or ridge frequency is calculated for local Gabor filtering; the next point of ridge line tracking is determined; data is compared and determined according to a predetermined threshold to determine whether the termination condition is met. If so, the starting point is returned to for direction tracking. If the reverse tracking is completed, the gray-scale maximum value is re-searched for other point analysis until the entire fingerprint image is traversed.

[0060] The image grayscale normalization process is to perform image processing by using the local mean method in the adaptive local binarization method, by dividing the fingerprint image into non-overlapping, uniformly sized image blocks, and calculating the variance of each block according to the grayscale of the image block: the grayscale of the image block is obtained by calculating the average grayscale value in the block; the grayscale value variance of the image block is obtained by calculating the average grayscale value of the pixels in the block and the average grayscale value; a threshold is set for the variance, and the size of the variance and the threshold are compared to separate the background and fingerprint line areas. This method is based on the fact that the variance of the background area is small, while the variance of the fingerprint area is large due to the ridge and valley structure. If the variance of a certain image block is not zero or is far from the threshold, the area is further subjected to threshold segmentation processing, as follows:

[0061] The size of the fingerprint image is m×m, which is divided into non-overlapping, uniformly sized image blocks, with a block size of n×n. In the fingerprint image, (i,j) indicates the horizontal and vertical coordinates of a certain image block in the fingerprint image block, and (u,v) indicates the coordinate position of the pixel in the image block;

[0062] The sum of the grayscale values ​​of each point in the image block is calculated according to the following formula:

[0063]

[0064] Wherein, L(u,v) is the gray value of the pixel in the image block, M(i,j) is the total gray value of the (i,j)th image block, i=1, 2…k, j=1, 2…k, k=m / n;

[0065] The grayscale variance of the image block is:

[0066]

[0067] A(i,j) is the mean gray value in the (i,j)th image block. By setting the threshold of V(i,j), the valid fingerprint area and background area can be determined.

[0068] Select the threshold value T d , if V(i,j)>T d , then the value of the corresponding image block in the image block (i, j) area is set to F(i, j) = 1, and the area where the image block is located is a valid fingerprint area block; otherwise, the value of the image block is set to F(i, j) = 0, and the image block is a background area block.

[0069] The light source control panel 5 includes a light source switch, light intensity control, light source switching and charging functions, which can realize the switching of ultraviolet light source and white light source in different environments, and is convenient for the use of equipment in different environments. The built-in battery can realize the charging function to facilitate the use of the equipment at any time. When turned on, the power status light is always on.

[0070] like Figure 1 As shown, in this embodiment, the light source control panel 5 includes a light source switch 5-1, a brightness increase key 5-2, a brightness decrease key 5-3, a power indicator light 5-4, and a charging port 5-5; pressing the brightness increase key 5-2 and the brightness decrease key 5-3 at the same time can realize light source switching.

[0071] In this embodiment, Figure 2 As shown, the macro lens 6 and the smart phone camera are arranged in sequence just above the fingerprint collection area; the fluorescent excitation light source module 7 and the white light excitation light source module 8 are symmetrically distributed on both sides of the macro lens 6 and have the same height, and are closely arranged in sequence; the optical axes of the macro lens 6 and the smart phone camera form an angle of 45% with the central optical axes of the fluorescent excitation light source module 7 and the white light excitation light source module 8.

[0072] For on-site fingerprints, fingerprint imaging and collection can be performed using white light source module 8 or fluorescent excitation light source module 7 as needed; under complex backgrounds, fluorescent material excitation is achieved through fluorescent excitation light source module 7 to highlight fingerprints, and fingerprint collection is achieved through a handheld terminal; for clearly visible fingerprints under light backgrounds such as paper, walls, etc., the white light source module 8 of the handheld terminal is used to illuminate and collect the image, and the collected fingerprints are compared with the fingerprint library stored in the smart phone 1 through the fingerprint feature extraction algorithm and fingerprint feature comparison algorithm in the fingerprint analysis module. At the same time, the collected fingerprint image can be shared with other users through a wireless network to achieve cloud comparison.

[0073] A fingerprint extraction and recognition method based on fluorescent materials, such as Figure 5 As shown, the following steps are included;

[0074] S1. Fingerprint imaging: Apply fluorescent magnetic fingerprint imaging powder on the fingerprint to absorb excess powder on the surface, so that the fingerprint lines can be clearly displayed;

[0075] S2, fingerprint imaging and fingerprint extraction: Cover the handheld terminal in the fingerprint collection area, place the macro lens 6 directly above the fingerprint, switch the excitation light source module and control the light intensity change through the light source control board 5, run the fingerprint extraction and analysis module in the smart phone 1, run the fingerprint feature extraction algorithm, call the smart phone camera to achieve clear fingerprint imaging, perform image preprocessing, and extract fingerprint feature information;

[0076] S3, fingerprint identification: run the fingerprint feature comparison algorithm, compare the fingerprint feature information extracted in step S2 with the fingerprint feature information extracted in advance by the fingerprint feature extraction algorithm or directly imported into the fingerprint library, and complete the fingerprint identification;

[0077] S4, result display: the fingerprint extraction and analysis module displays the result of fingerprint recognition on the smart phone 1.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A fingerprint extraction and recognition system based on fluorescent materials, characterized in that: Including fingerprint database, handheld terminal, fingerprint extraction and analysis software; The handheld terminal includes a light source control board, an excitation light source module, a macro lens and a smartphone camera; The excitation light source module includes a fluorescent excitation light source module and a white light excitation light source module, which are used to realize fingerprint imaging of fingerprint powder under different fingerprint extraction conditions. The fluorescent excitation light source module is an ultraviolet light source, which provides excitation light with uniform illumination spot in the fingerprint collection area; the white light excitation light source module provides white light with uniform illumination spot, and directly images the fingerprint under a light background; The fluorescent excitation light source module includes an ultraviolet lamp, an ultraviolet light homogenizing lens and an ultraviolet filter, and the white light source module includes a white light lamp, a white light homogenizing lens and a white light homogenizing sheet; The macro lens and the smartphone camera are arranged in sequence just above the fingerprint collection area; the fluorescent excitation light source module and the white light excitation light source module are symmetrically distributed on both sides of the macro lens and have the same height, and are closely arranged in sequence; the optical axes of the macro lens and the smartphone camera are at a 45-degree angle to the central optical axes of the fluorescent excitation light source module and the white light excitation light source module; The fingerprint extraction and analysis software has built-in fingerprint feature extraction algorithm and fingerprint feature comparison algorithm; The operator places the fingerprint in the sampling area of ​​the handheld terminal. The fingerprint analysis software runs the fingerprint feature extraction algorithm to call the handheld terminal to extract fingerprint feature information, and then runs the fingerprint feature comparison algorithm to compare the extracted fingerprint feature information with the information in the fingerprint library to achieve fingerprint recognition; Before fingerprint extraction, the fingerprint imaging magnetic powder made of fluorescent material should be applied on the fingerprint to absorb the excess powder on the surface so that the fingerprint lines can be clearly seen; The fingerprint extraction and analysis software and fingerprint camera imaging are both implemented through a smart phone, wherein the fingerprint extraction and analysis software is installed and run in an Android environment, the camera is a camera in a smart phone, and a macro lens is used to observe fingerprint imaging, and then the fingerprint features are extracted; when the fingerprint feature extraction algorithm is running, the smart phone camera is called to shoot, and the light source control board is used to switch the excitation light source module and control the light intensity change under different fingerprint extraction conditions to excite the fluorescent material, and the macro lens in the handheld terminal is used to complete the clear image magnification, realize the clear fingerprint imaging, select the appropriate fingerprint collection area, perform image preprocessing, and extract the fingerprint features.

2. According to the fingerprint extraction and recognition system based on fluorescent materials according to claim 1, it is characterized in that: The information in the fingerprint database is fingerprint feature information that is extracted in advance through a fingerprint feature extraction algorithm or directly imported and stored in the smartphone.

3. According to claim 1, a fingerprint extraction and recognition system based on fluorescent materials is characterized in that: The image preprocessing is to remove the interference of uneven brightness and other noise in the fingerprint image through a series of processing of the original collected fingerprint image, and restore the real image line information through line refinement and repair, as follows: The collected image is gray-scale processed, and the image gray-scale normalization processing is performed using the adaptive local binary image separation method; fingerprint image enhancement is performed; image background segmentation is performed to remove noise interference in the fingerprint; Find the maximum gray value in the image according to the sequence as the initial value; Calculate the direction value or ridge frequency to perform local Gabor filtering; determine the next point for ridge tracing; Compare the data and determine whether the termination conditions are met based on the predetermined threshold. If so, return to the starting point for direction tracking. If the reverse tracking is completed, re-search for the grayscale maximum value to analyze other points until the entire fingerprint image is traversed.

4. The fingerprint extraction and recognition system based on fluorescent materials according to claim 3 is characterized in that: The image grayscale normalization process is to perform image processing by using the local mean method in the adaptive local binarization method, by dividing the fingerprint image into non-overlapping image blocks of uniform size, and calculating the variance of each block according to the grayscale of the image block: the grayscale of the image block is obtained by calculating the average grayscale value in the block; The gray value variance of the image block is obtained by the average gray value of the pixels in the block and the average gray value. A threshold is set for the variance, and the variance and the threshold are compared to separate the background and fingerprint line areas. If the variance of an image block is not zero or is far from the threshold, the area is further segmented by threshold. The mean variance algorithm is as follows: The size of the fingerprint image is m×m, which is divided into non-overlapping, uniformly sized image blocks, with a block size of n×n; in the fingerprint image, (i, j) indicates the horizontal and vertical coordinate positions of a certain image block in the fingerprint image block, and (u, v) indicates the coordinate position of the pixel in the image block; The sum of the grayscale values ​​of each point in the image block is calculated according to the following formula: Wherein, L(u,v) is the gray value of the pixel in the image block, M(i,j) is the total gray value of the (i,j)th image block, i=1, 2…k, j=1, 2…k, k=m / n; The grayscale variance of the image block is: A(i,j) is the mean gray value in the (i,j)th image block. By setting the threshold of V(i,j), the valid fingerprint area and background area can be determined. Select the threshold value T d , if V(i,j)>T d , then the value of the corresponding image block in the image block (i, j) area is set to F(i, j) = 1, and the area where the image block is located is a valid fingerprint area block; otherwise, the value of the image block is set to F(i, j) = 0, and the image block is a background area block.

5. The fingerprint extraction and recognition system based on fluorescent materials according to claim 1 is characterized in that: The light source control panel includes a light source switch, light intensity control, light source switching and charging functions, which can realize the switching of ultraviolet light sources and white light sources in different environments, making it convenient to use the equipment in different environments. The built-in battery can realize the charging function, making it convenient to use the equipment at any time. When turned on, the power status light is always on.

6. A fingerprint extraction and recognition system based on fluorescent materials according to any one of claims 1 to 5, characterized in that: For on-site fingerprints, fingerprint imaging and collection can be performed using either white light source modules or fluorescent excitation light source modules as needed. Under complex backgrounds, fluorescent material excitation is achieved through the fluorescent excitation light source module to highlight the fingerprint, and fingerprint collection is achieved through handheld terminals and smartphones. For clearly visible fingerprints under light backgrounds, the white light source module of the handheld terminal is used to illuminate and collect the image. The collected fingerprints are compared with the fingerprint library information stored in the smartphone through the fingerprint feature extraction algorithm and fingerprint feature comparison algorithm in the fingerprint analysis software. At the same time, the collected fingerprint images can be shared with other users through wireless networks to achieve cloud comparison.

7. A fingerprint extraction and identification method based on fluorescent materials based on the fingerprint extraction and identification system based on fluorescent materials according to claim 6, characterized in that: The steps include: S1. Fingerprint imaging: Apply fluorescent magnetic fingerprint imaging powder on the fingerprint to absorb excess powder on the surface, so that the fingerprint lines can be clearly displayed; S2, fingerprint imaging and fingerprint extraction: Cover the handheld terminal in the fingerprint collection area, place the macro lens directly above the fingerprint, switch the excitation light source module and control the light intensity change through the light source control board, run the fingerprint extraction and analysis software in the smartphone, run the fingerprint feature extraction algorithm, call the smartphone camera to achieve clear fingerprint imaging, perform image preprocessing, and extract fingerprint feature information; S3, fingerprint identification: run the fingerprint feature comparison algorithm, compare the fingerprint feature information extracted in step S2 with the fingerprint feature information extracted in advance by the fingerprint feature extraction algorithm or directly imported into the fingerprint library, and complete the fingerprint identification; S4. Result display: The fingerprint extraction and analysis software displays the fingerprint recognition results on the smartphone.

Images