A method for reducing fingerprint identification and forgery by using ORB image local features

Abstract

The application discloses a method for reducing fingerprint identification and forgery by using ORB image local features, comprising the following steps: S1, extracting minutia points of a to-be-matched fingerprint image; S2, marking a region around the minutia points of the to-be-matched fingerprint image, and extracting ORB key points of the marked region; S3, calculating minutia point pairs of the to-be-matched fingerprint image, and judging whether the calculated minutia point pairs are within a preset minutia point pair range; if not, the to-be-matched fingerprint image fails to match; if yes, step S4 is performed; S4, matching the ORB key points of the to-be-matched fingerprint image according to the calculated minutia point pairs, and judging whether the number of the matched ORB key points is greater than or equal to a preset ORB key point matching number; if not, the to-be-matched fingerprint image fails to match; if yes, step S5 is performed; and S5, the to-be-matched fingerprint image succeeds in matching.

Description

Technical Field

[0001] This invention relates to the field of fingerprint comparison technology, and in particular to a method for reducing fingerprint fraud by utilizing local features of ORB images. Background Technology

[0002] Currently, fingerprint recognition terminal devices on the market are employing various methods to reduce hardware costs and broaden their application range, with the most significant being the reduction of sensor size. The image size captured by a fingerprint sensor at the same DPI has shrunk from 256*360 to 160*160. The captured finger area can no longer cover the entire finger, and with the reduction in the capture area, the number of unique fingerprint detail points also decreases accordingly. Since different fingers often have similar local detail points, matching algorithms based solely on fingerprint detail points can lead to many false recognitions.

[0003] Patent CN115497125A discloses a fingerprint recognition method, system, computer device, and computer-readable storage medium, comprising: acquiring a fingerprint image of a fingerprint to be matched; extracting minutiae from the fingerprint image to obtain minutiae features; extracting and compressing the minutiae features into depth features to obtain vector descriptors of the minutiae in the fingerprint image to be matched; using the vector descriptors to perform pattern matching between the minutiae features of the fingerprint image to be matched and the minutiae features of a template fingerprint image; if the match is successful, the matching is complete; if the match fails, ORB feature matching verification is performed between the fingerprint image to be matched and the template fingerprint image. While the above patent can achieve accurate matching on relatively small fingerprint images, its verification method involves adjusting the minutiae feature matching score, which can still lead to false recognitions in fingerprint minutiae matching.

[0004] To address the aforementioned technical problems, this invention provides a method for reducing fingerprint fraud by utilizing local features of ORB images. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by providing a method for reducing fingerprint fraud by utilizing local features of ORB images.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] A method for reducing fingerprint forgery using local features of ORB images includes:

[0008] S1. Extract the details of the fingerprint image to be matched;

[0009] S2. Mark the area around the details of the fingerprint image to be matched, and extract the ORB key points of the marked area;

[0010] S3. Calculate the minutiae matching pairs of the fingerprint image to be matched, and determine whether the calculated minutiae matching pairs are within the preset minutiae pair range. If not, the fingerprint image to be matched fails to match; if so, proceed to step S4.

[0011] S4. Match the ORB keypoints of the fingerprint image to be matched based on the calculated minutiae matching points. Determine if the number of matched ORB keypoints is greater than or equal to the preset number of matched ORB keypoints. Otherwise, the fingerprint image to be matched fails to match. If it is, proceed to step S5.

[0012] S5. The fingerprint image to be matched has been successfully matched.

[0013] Furthermore, after extracting the minutiae of the fingerprint image to be matched in step S1, the method further includes: calculating the distance between all minutiae and the center point of the fingerprint image to be matched, and sorting the minutiae corresponding to the calculated distances.

[0014] Furthermore, in step S2, the area to be marked is: the original image of the fingerprint image to be matched is divided into blocks, and blocks around the minutiae that are not near the background area are selected, and the selected blocks are marked to obtain the marked area.

[0015] Furthermore, in step S2, the ORB key points in the marked region are extracted by removing ORB key points that are too close together within the marked region and selecting ORB key points that are close to the details of the fingerprint image to be matched.

[0016] Furthermore, in step S3, calculating the minutiae matching point pairs of the fingerprint image to be matched specifically involves: obtaining the minutiae features of the fingerprint image to be matched, and matching the minutiae features of the fingerprint image to be matched to obtain the matching result of the minutiae features.

[0017] Furthermore, in step S4, the ORB keypoints of the fingerprint image to be matched are matched based on the calculated minutiae matching points, specifically as follows:

[0018] A1. Obtain the ORB key point features of the fingerprint image to be matched;

[0019] A2. Convert the ORB key point features of the fingerprint image to be matched to a unified matching coordinate system for registration;

[0020] A3. Match the ORB key point features of the registered fingerprint images to be matched, and obtain the matching results.

[0021] Furthermore, the details feature includes the coordinate position of the details and the orientation of the details.

[0022] Furthermore, the ORB key point features include the coordinate position of the ORB feature point, the orientation of the ORB feature point, and the ORB feature point descriptor.

[0023] Furthermore, before step A2, the method further includes: calculating configuration parameters for ORB keypoint features.

[0024] Compared with existing technologies, this invention does not extract ORB features from all regions, but only from the regions surrounding the minutiae. It also provides an ORB feature filtering method that allows flexible control over the number of ORB feature points as needed, reducing computation time and fingerprint feature file size. Furthermore, by adding ORB features, this invention reduces the likelihood of false matching due to topological similarity at minutiae. Finally, the ORB feature matching algorithm of this invention fully utilizes minutiae matching pairs, simplifying the entire ORB feature matching process and reducing additional computation time. Attached Figure Description

[0025] Figure 1 This is a flowchart of a method for reducing fingerprint fraud detection using local features of ORB images, provided in Embodiment 1.

[0026] Figure 2 This is a schematic diagram of the number of ORB feature points extracted using the existing method provided in Example 1;

[0027] Figure 3 This is a schematic diagram of fingerprint minutiae provided in Embodiment 1;

[0028] Figure 4 This is a schematic diagram of the blocks selected for ORB feature extraction provided in Example 1;

[0029] Figure 5 This is a schematic diagram of the ORB features and fingerprint minutiae of the selected blocks provided in Example 1;

[0030] Figure 6 This is a schematic diagram of the matching of the same fingers provided in Embodiment 1;

[0031] Figure 7 This is a schematic diagram of different finger matching situations provided in Example 2. Detailed Implementation

[0032] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, unless otherwise specified, the following embodiments and features described therein can be combined with each other.

[0033] The purpose of this invention is to address the shortcomings of existing technologies by providing a method for reducing fingerprint fraud by utilizing local features of ORB images.

[0034] Example 1

[0035] This embodiment provides a method for reducing fingerprint fraud by utilizing local features of ORB images, such as... Figure 1 As shown, it includes:

[0036] S1. Extract the details of the fingerprint image to be matched;

[0037] S2. Mark the area around the details of the fingerprint image to be matched, and extract the ORB key points of the marked area;

[0038] S3. Calculate the minutiae matching pairs of the fingerprint image to be matched, and determine whether the calculated minutiae matching pairs are within the preset minutiae pair range. If not, the fingerprint image to be matched fails to match; if so, proceed to step S4.

[0039] S4. Match the ORB keypoints of the fingerprint image to be matched based on the calculated minutiae matching points. Determine if the number of matched ORB keypoints is greater than or equal to the preset number of matched ORB keypoints. Otherwise, the fingerprint image to be matched fails to match. If it is, proceed to step S5.

[0040] S5. The fingerprint image to be matched has been successfully matched.

[0041] This invention studies various methods for local image feature extraction, including SIFT, SURF, and ORB. ORB, in particular, has low computational cost and its binary descriptor reduces storage requirements, while also exhibiting rotation invariance. This makes it well-suited for low-resource fingerprint recognition embedded systems. However, a medium-sized (160*160) fingerprint image with rich textures requires a large number of extracted ORB local feature points, consuming significant storage space. Figure 2 The ORB feature points shown total 550. Storing all of them in the fingerprint template for comparison would be extremely unreasonable. Therefore, this embodiment proposes a method to reduce fingerprint spoofing by utilizing local features of the ORB image to solve the above problem.

[0042] In step S1, the details of the fingerprint image to be matched are extracted.

[0043] Obtain the fingerprint images to be matched and extract the minutiae (endpoints and forks) of the fingerprint images. The fingerprint images to be matched are the first fingerprint image and the second fingerprint image.

[0044] It should be noted that existing methods can be used to extract details from fingerprint images, and this embodiment will not elaborate on them.

[0045] like Figure 3 As shown, black dots are erroneous detail points caused by image breaks, and white dots are image detail points. In this embodiment, if the number of extracted detail points is greater than 30 (the number of detail points can be adjusted according to the maximum space that the actual template can store), ORB feature extraction is not performed on all detail points. Then, the distance between the extracted detail points and the center point of the image is calculated and sorted.

[0046] In this embodiment, ORB keypoint extraction is not performed on the minutiae region at the center of the image during subsequent operations; only ORB keypoints of minutiae far from the image center are extracted. This is because minutiae far from the image center are close to the image edges. During registration, the overlapping area of ​​the fingerprint image feature points to be matched will include the edge region. The smaller the overlapping area, the less central region is included, and the lower the chance of ORB pairing in the central region. The extraction area of ​​ORB feature points is controlled by controlling the number of minutiae.

[0047] In step S2, the area around the details of the fingerprint image to be matched is marked, and the ORB key points of the marked area are extracted.

[0048] The original fingerprint image to be matched is divided into 8x8 pixel blocks. The blocks are then checked for fingerprint texture areas. Blocks without texture areas are considered background areas, as blocks near background areas are prone to causing errors and are therefore excluded. The 5x5 area surrounding the selected minutiae, not near the background area, is the region from which ORB is finally extracted. Figure 4 As shown, white dots represent marked blocks, and black dots represent image detail points. Selected blocks are marked, and ORB keypoints are extracted from the marked areas. Because fingerprint images do not undergo scale changes, corner detection can be performed using the ORB keypoint detection method (FAST) only at the original image scale, reducing computational load.

[0049] In this embodiment, ORB keypoint calculation is performed on the selected region. If there are still too many keypoints causing the feature file to be too large, ORB keypoints that are too close together can be removed, ORB keypoints that are close to the fingerprint minutiae can be selected, and ORB keypoints with the best quality can be selected. For example... Figure 5 As shown, white dots represent ORB key feature points, black dots represent fingerprint minutiae, and black lines indicate the ORB direction; the number of feature points has been reduced from 550 to 75. Their directions and feature descriptors are calculated and stored in the feature template along with fingerprint minutiae information (endpoints, bifurcations).

[0050] Existing ORB keypoint matching algorithms generally involve first performing a 1:1 search on the descriptors of features A and B to find keypoint matching pairs with high similarity. Then, the RANSAC iterative method is used to estimate the matching relationship between features A and B. The RANSAC iterative method works as follows: based on the descriptor matching results, a series of possible ORB matching pairs for features A and B have been found. Some possible ORB matching pairs are randomly selected as initial inliers. A registration relationship model is then fitted using these inliers. All other possible ORB matching pairs are tested. If a possible ORB matching pair fits this registration relationship model, it is considered an inlier and the inliers are expanded. The algorithm calculates how many possible ORB matching pairs are used as RANSAC inliers and the error rate of estimating the inlier registration relationship model. The entire process is considered an iteration, which is repeated a fixed number of times (N>10). Each iteration generates a new registration relationship model. If the new model is inferior to the previous model due to too few inliers or a high error rate, it is discarded. If it is better than the existing models, it is selected. The best registration relationship model is chosen to remove erroneous ORB matching pairs. The ORB keypoint matching algorithm is complex and computationally intensive. Therefore, this embodiment redesigns a new ORB minutiae matching method, as shown in steps S3-S4.

[0051] In step S3, the minutiae matching point pairs of the fingerprint image to be matched are calculated, and it is determined whether the calculated minutiae matching point pairs are within the preset minutiae pair range. If not, the fingerprint image to be matched fails to match; if so, step S4 is executed.

[0052] The minutiae of the first fingerprint image and the second fingerprint image are compared to obtain matching pairs of minutiae features of the first fingerprint image and the second fingerprint image. Based on these pairs, the registration relationship of the features of the first fingerprint image and the second fingerprint image is calculated to obtain the relevant matching situation of ORB. This matching method is fast and has a small amount of computation. When there are more than or equal to 3 pairs of matching minutiae and less than 15 pairs, the finger is considered to be the same finger, and step S4 is executed.

[0053] like Figure 6 The image shows fingerprint images of two identical fingers. The white dots are ORB key feature points, the black dots are fingerprint minutiae, and the black lines represent the ORB direction. This embodiment uses feature point A of the first fingerprint image and feature point B of the second fingerprint image for illustration.

[0054] Based on the images, feature extraction is performed to obtain the minutiae feature information A of the first fingerprint image and the minutiae feature information B of the second fingerprint image. The minutiae feature information includes the coordinate position x, y of the minutiae and the direction ang of the minutiae.

[0055] Minute points a1, a2, and a3 are points matched by minute point A obtained using the minute point matching algorithm; minute points b1, b2, and b3 are points matched by minute point B obtained using the minute point matching algorithm.

[0056] Therefore, we can see that a1(x=76,y=141,ang=240) and b1(x=27,y=120,ang=231), a2(x=94,y=77,ang=270) and b2(x=39,y=54,ang=265), and a3(x=115,y=56,ang=310) and b3(x=58,y=30,ang=305) are a match.

[0057] It should be noted that the minutiae matching algorithm can adopt existing schemes, which will not be described in detail in this embodiment.

[0058] Based on the minutiae matching results, calculate the translation and rotation factors. Using minutiae A as the reference, rotate and translate feature B to the coordinate system of feature A for comparison, based on the minutiae matching results. a1 and b1 are the matched reference pairs, with registration parameters TransParaB(baseX, baseY, deltaX, deltaY, deltaTheta), where baseX is the x-coordinate of the reference point, baseY is the y-coordinate of the reference point, deltaX is the x-coordinate offset, deltaY is the y-coordinate offset, and deltaTheta is the angular offset. Taking the minutiae reference pair b1 in feature B as the reference point, calculate the configuration parameter TransParaB, specifically:

[0059]

[0060] According to the above calculation method, TransParaB(baseX=27, baseY=120, deltaX=49, deltaY=21, deltaTheta=351) can be obtained.

[0061] In step S4, the ORB keypoints of the fingerprint image to be matched are matched based on the calculated minutiae matching points. It is determined that the number of matched ORB keypoints is greater than or equal to the preset number of matched ORB keypoints; otherwise, the fingerprint image matching fails. If so, step S5 is executed. Specifically, this includes:

[0062] A1. Obtain the ORB key point features of the fingerprint image to be matched.

[0063] Based on the images, feature extraction is performed to obtain ORB features A of the first fingerprint image and ORB features B of the second fingerprint image. The ORB features include the coordinate positions x and y of the ORB feature points, the orientation ang of the ORB feature points, and the ORB feature descriptor binary.

[0064] When entering the ORB keypoint matching stage, the ORB keypoints in the minutiae region that have matched in position are subjected to orientation and descriptor matching. If there are 5 or more keypoints matching in the ORB, the minutiae and keypoint matching is considered successful, and the probability of false recognition is extremely low. If the two finger images are of the same finger, the match is successful; otherwise, the two fingers are considered to be different fingers, and the match fails.

[0065] A2. Convert the ORB key point features of the fingerprint image to be matched to a unified matching coordinate system for registration.

[0066] After obtaining the configuration parameter TransParaB in the minutiae calculation in step S3, the ORB features (d1, d2, d3...) in feature B are rotated and translated to the coordinate system of feature A based on the calculated registration parameters. The new x-coordinate, new y-coordinate, and new angle of the ORB features are then Newdx, Newdy, and Newdang. The binarized descriptor is rotation and translation invariant and does not need to be modified. The specific implementation method is as follows:

[0067]

[0068] The ORB feature point d1 (x = 102, y = 116, ang = 351, binary = 1001111101000001 10110111) in feature B is translated and rotated into the coordinate system of feature A according to the calculated TransParaB (baseX = 27, baseY = 120, deltaX = 49, deltaY = 21, deltaTheta = 351) configuration parameters to obtain d11. Specific calculation details are as follows:

[0069] SinTheta = sin(351) = -0.156

[0070] CosTheta = cos(351) = 0.99

[0071] d11(x)=(int)((27+49)+(116-120)*(-0.156)+(102-27)*0.99+0.5)=151;

[0072] d11(y)=(int)((120+21)+(116-120)*0.99-(102-27)*(-0.156)+0.5)=149;

[0073] d11(ang)=351+351-360=342

[0074] d11(binary)=d1(binary)=10011111 01000001 10110111;

[0075] The calculation yields d11(x=151,y=149,ang=342,binary=10011111 0100000110110111).

[0076] A3. Match the ORB key point features of the registered fingerprint images to be matched, and obtain the matching results.

[0077] Based on the coordinates of d11, point c1 in feature A is found to be a matching point, with the error range within the allowable threshold. Δx is between -5 and +5, Δy is between -5 and +5, Δang is between -15 and +15, and Δbinary has a maximum of 5 dimensions of inconsistency in 24-dimensional binary data. The error values ​​of c1 and d11 are as follows, and none exceed the error range, therefore a match can be found.

[0078] Δx=d11(x)-c1(x)=151-153=-2;

[0079] Δy=d11(y)-c1(y)=149-146=3;

[0080] Δang=d11(ang)-c1(ang)=342-350=-8;

[0081] Δbinary=d11(10011111 01000001 10110111)-c1(101111111100101110110111)=3

[0082] Similarly, by rotating and translating all other ORB features in B to the coordinate system of feature A in the same way, we can calculate that ten pairs of points are matched, with the error within the allowable range. These are c1 and d1, c2 and d2, c3 and d3, c4 and d4, c5 and d5, c6 and d6, c7 and d7, c8 and d8, c9 and d9, and c10 and d10. The specific feature values ​​of the matched ORB minutiae are shown below:

[0083] c1(x=153,y=146,ang=350,binary=10111111 11001011 10110111)

[0084] d1(x=102,y=116,ang=351,binary=10011111 01000001 10110111)

[0085] c2(x=134,y=97,ang=253,binary=00110111 00100001 10101011)

[0086] d2(x=80,y=68,ang=233,binary=01110111 00100001 00110011)

[0087] c3(x=82,y=122,ang=298,binary=00111110 00100000 10100101)

[0088] d3(x=30,y=99,ang=276,binary=00111110 10000100 11100100)

[0089] c4(x=93,y=58,ang=305,binary=00011111 11000001 01110111)

[0090] d4(x=36,y=34,ang=306,binary=00011101 11000000 01110101)

[0091] c5(x=80,y=145,ang=36,binary=00100000 10110100 11000100)

[0092] d5(x=31,y=123,ang=35,binary=00101110 10111110 11100100)

[0093] c6(x=93,y=150,ang=186,binary=11000100 00000000 101000)

[0094] d6(x=44,y=125,ang=186,binary=00000100 00000000 101000)

[0095] c7(x=71,y=158,ang=46,binary=01001000 10010000 01000010)

[0096] d7(x=25,y=138,ang=29,binary=00001000 10011010 11111010)

[0097] c8(x=82,y=83,ang=132,binary=01000001 01011011 11000001)

[0098] d8(x=27,y=57,ang=133,binary=01000001 10011010 11100000)

[0099] c9(x=98,y=85,ang=211,binary=01000001 01011011 01100000)

[0100] d9(x=43,y=61,ang=196,binary=01000101 01011011 01101000)

[0101] c10(x=85,y=114,ang=292,binary=00011111 01000001 11110111)

[0102] d10(x=32,y=91,ang=271,binary=01011111 00000000 11110100)

[0103] Based on the above, it can be seen that all feature A and feature B details are successfully matched, and the ORB feature is also successfully matched, indicating that it is the same finger.

[0104] This embodiment uses image detail feature points as the center point to retain the required local ORB feature points. This method occupies very little feature template storage space. At the same time, it reduces the false acceptance rate of the mid-area fingerprint detail point comparison algorithm by comparing local ORB features.

[0105] Example 2

[0106] The method for reducing fingerprint fraud using local features of ORB images provided in this embodiment differs from Embodiment 1 in that:

[0107] In this embodiment, feature A of the first fingerprint image and feature C of the second fingerprint image are compared.

[0108] like Figure 7 As shown, white dots represent ORB key feature points, black dots represent fingerprint minutiae, and black lines indicate the direction of the ORB; features A and C represent different fingers. However, existing minutiae matching algorithms can successfully match them, thus resulting in a false positive.

[0109] According to this scheme, the minutiae of feature A are e1, e2, and e3, and the minutiae of feature C are f1, f2, and f3. Therefore:

[0110] e1(x=136,y=89,ang=268) and f1(x=93,y=79,ang=270), e2(x=150,y=143,ang=175) and f2(x=97,y=128,ang=177), e3(x=80,y=73,ang=267) and f3(x=41,y=58,ang=268) are matching pairs on minutiae matching.

[0111] However, ORB pairing failed, specifically:

[0112] Following the method in step S4, e1 and f1 are used as the reference pair to obtain the registration parameters TransParaC (baseX=93, baseY=79, deltaX=43, deltaY=10, deltaTheta=2). Based on the registration parameters TransParaC, the ORB features of feature C are registered to the coordinate system of feature A. No ORB feature is registered with any ORB feature in feature A. For example:

[0113] g1(x=129,y=95,ang=344,binary=01001001 01000001 10101001), g2(x=80,y=145,ang=36,binary=00100000 10110100 11000000), g3(x=71,y=158,ang=46,binary=01001000 10010000 1000010) are ORB feature points of feature A. h1(x=86,y=85,ang=354,binary=00001000 00010000 10000100) and h2(x=32,y=133,ang=45,binary=11110101 01110001) are ORB feature points of feature A. 00011001), h3(x=35,y=161,ang=295,binary=1011111011100101 11111100) are ORB feature points of feature C. The translation and rotation of f1, f2, and f3 to the A feature coordinate system are calculated according to the registration parameter TransParaC, resulting in g11(x=129,y=95,ang=356,binary=0000100000010000 10000100), g22(x=76,y=145,ang=47,binary=11110101 0111000100011001), and g33(x=80,y=172,ang=297,binary=10111110 11100101 11111100).

[0114] The coordinate positions and angles of g1(x=129,y=95,ang=344,binary=01001001 01000001 10101001) and g11(x=129,y=95,ang=356,binary=00001000 00010000 10000100) are within the error range, but the binary descriptors are 9 different, which exceeds the allowable error range.

[0115] The coordinate positions and angles of g2(x=80,y=145,ang=36,binary=00100000 10110100 11000000) and g22(x=76,y=145,ang=47,binary=11110101 01110001 00011001) are within the error range, but the binarized descriptors have 14 different dimensions, which exceeds the allowable error range.

[0116] The binary descriptors for coordinate position and angle of g3(x=71,y=158,ang=46,binary=01001000 10010000 1000010) and g33(x=80,y=172,ang=297,binary=10111110 11100101 11111100) are significantly outside the error range.

[0117] Therefore, the ORB keypoint feature matching of features A and C is unsuccessful, as features A and C are not the same finger, and the comparison fails.

[0118] Compared to algorithms that rely solely on minutiae, the ORB feature designed in this embodiment can effectively reduce the false acceptance rate of fingerprint recognition algorithms.

[0119] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for reducing fingerprint forgery using local features of ORB images, characterized in that, include: S1. Extract the minutiae of the fingerprint image to be matched, calculate the distance between all minutiae and the center point of the fingerprint image to be matched, and sort the minutiae corresponding to the calculated distances; S2. Mark the area around the details of the fingerprint image to be matched, and extract the ORB key points of the marked area; The marking area is as follows: the original image of the fingerprint image to be matched is divided into blocks, and blocks around the minutiae that are not near the background are selected and marked to obtain the marked area; the ORB key points of the marked area are extracted by removing ORB key points that are too close in the marked area and selecting ORB key points that are close to the minutiae of the fingerprint image to be matched. S3. Calculate the minutiae matching pairs of the fingerprint image to be matched, and determine whether the calculated minutiae matching pairs are within the preset minutiae pair range. If not, the fingerprint image to be matched fails to match. If so, proceed to step S4; S4. Match the ORB keypoints of the fingerprint image to be matched based on the calculated minutiae matching points. Determine if the number of matched ORB keypoints is greater than or equal to the preset number of matched ORB keypoints. If not, the fingerprint image to be matched fails to match; if so, proceed to step S5. Specifically, matching the ORB keypoints of the fingerprint image to be matched based on the calculated minutiae matching points involves: A1. Obtain the ORB key point features of the fingerprint image to be matched; A2. Calculate the configuration parameters of ORB key point features, and transform the ORB key point features of the fingerprint image to be matched to a unified matching coordinate system for registration. A3. Match the ORB key point features of the registered fingerprint images to be matched, and obtain the matching results; S5. The fingerprint image to be matched has been successfully matched.

2. The method for reducing fingerprint forgery using local features of ORB images according to claim 1, characterized in that, In step S3, calculating the minutiae matching point pairs of the fingerprint image to be matched specifically involves: obtaining the minutiae features of the fingerprint image to be matched, and matching the minutiae features of the fingerprint image to be matched to obtain the matching result of the minutiae features.

3. The method for reducing fingerprint forgery using local features of ORB images according to claim 2, characterized in that, The features of the detail points include the coordinate position and orientation of the detail points.

4. The method for reducing fingerprint forgery using local features of ORB images according to claim 3, characterized in that, The ORB keypoint features include the coordinate position of the ORB feature point, the orientation of the ORB feature point, and the ORB feature point descriptor.

Images