A method, device and system for evaluating humidity of fingerprint images

Abstract

The present invention discloses a method, device and system for evaluating humidity of a fingerprint image. The method comprises: performing dynamic binarization processing on a fingerprint image to obtain a binarized image; performing connected domain analysis on the binarized image to obtain each connected domain and feature information of each connected domain; screening out abnormal connected domains from all connected domains according to each feature information; calculating the area ratio of the abnormal connected domain in all connected domains, and taking the area ratio as a humidity evaluation index. In the present invention, since the fingerprint image is binarized by dynamic binarization processing, it is not affected by the light and dark changes of the fingerprint itself, so that the obtained humidity evaluation index is more accurate, which is beneficial to improving the accuracy of humidity evaluation of the fingerprint image.

Description

Technical Field

[0001] The present invention relates to the technical field of fingerprint recognition, and in particular to a method, device and system for evaluating humidity of a fingerprint image. Background Art

[0002] With the development of science and technology, fingerprint recognition is increasingly widely used. Among them, wet fingers will affect the quality of fingerprint images and the accuracy of fingerprint recognition. Usually, the matching score of wet fingers is lower than that of normal fingers, and the preprocessing method and parameters for extracting local features of wet fingers should also be different from those of normal fingers. Therefore, it is necessary to accurately evaluate the humidity of fingerprint images.

[0003] In the prior art, the humidity of fingerprint images is usually evaluated based on the grayscale mean and variance. It is believed that the mean and variance of wet fingers are both smaller, while the mean of dry fingers is larger and the variance is smaller. However, in actual situations, fingerprint images are complex and changeable. The grayscale value is not only affected by humidity, but also by pressing force, foreign matter, scars, sensing mechanism and fingerprint collection environment, and the variance is affected by noise. Therefore, the method based on grayscale mean and variance to evaluate the humidity of fingerprint images has great limitations, and the evaluation accuracy needs to be improved.

[0004] In view of this, how to provide a fingerprint image humidity assessment method, device and system that solves the above technical problems has become a problem that needs to be solved by those skilled in the art. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method, device and system for evaluating humidity of a fingerprint image, which can make the obtained humidity evaluation index more accurate, thereby improving the accuracy of humidity evaluation of a fingerprint image.

[0006] To solve the above technical problems, an embodiment of the present invention provides a method for evaluating humidity of a fingerprint image, comprising:

[0007] Perform dynamic binarization processing on the fingerprint image to obtain a binary image;

[0008] Performing connected domain analysis on the binary image to obtain each connected domain and feature information of each connected domain;

[0009] Filtering out abnormal connected domains from all connected domains according to each of the characteristic information;

[0010] The area ratio of the abnormal connected domain in all connected domains is calculated, and the area ratio is used as a humidity evaluation index.

[0011] Optionally, the process of performing dynamic binarization processing on the fingerprint image to obtain a binarized image is:

[0012] For each pixel in the fingerprint image, obtain a neighborhood corresponding to the pixel;

[0013] Determine a dynamic grayscale threshold corresponding to the pixel point according to the grayscale mean of the neighborhood corresponding to the pixel point;

[0014] Binarize the grayscale value of the pixel point according to the dynamic grayscale threshold to obtain a binarization result;

[0015] A binary image is constructed based on the binarization results of all pixels.

[0016] Optionally, the process of determining the dynamic grayscale threshold corresponding to the pixel point according to the grayscale mean of the neighborhood is:

[0017] The grayscale mean of all pixels in the neighborhood corresponding to the pixel is calculated according to the first calculation formula, wherein the first calculation formula is: Among them, M is the grayscale mean, N is the side length of the neighborhood, and I(i,j) is the grayscale value of the pixel with relative coordinates (i,j) in the neighborhood;

[0018] According to the second calculation relationship and the grayscale mean, a dynamic grayscale threshold corresponding to the pixel point is obtained, wherein the second calculation relationship is: Thr=M+a, wherein Thr is the grayscale threshold and a is an adjustable constant.

[0019] Optionally, the process of binarizing the grayscale value of the pixel point according to the dynamic grayscale threshold is:

[0020] According to the third calculation relationship and the grayscale threshold, a binarization result corresponding to the pixel point is obtained, wherein the third calculation relationship is:

[0021]

[0022] Optionally, the process of performing connected domain analysis on the binary image is:

[0023] A seed filling algorithm is used to perform connected domain analysis on the binary image.

[0024] Optionally, the process of screening out abnormal connected domains from all connected domains according to each of the feature information is as follows:

[0025] For each of the connected domains, it is determined whether the ridges of the fingerprint are normal according to the feature information of the connected domain. If normal, the connected domain is a normal connected domain; if abnormal, the connected domain is an abnormal connected domain.

[0026] Optionally, the feature information includes area, perimeter, height, width, and the number of singular points on the edge of the connected domain.

[0027] Optionally, the process of judging whether the ridge of the fingerprint is normal according to the feature information of the connected domain is:

[0028] Preset multiple filtering conditions;

[0029] When the feature information corresponding to the connected domain satisfies at least one screening condition, the ridge line of the fingerprint is an abnormal ridge line; when the feature information corresponding to the connected domain does not satisfy each of the screening conditions, the ridge line of the fingerprint is a normal ridge line.

[0030] Optionally, the plurality of screening conditions are:

[0031] The first screening condition is: the area S is smaller than the first area;

[0032] The second screening condition is: the height H is less than the first height value, and the width W is less than the first width value;

[0033] The third screening condition is: the perimeter C is less than the preset perimeter;

[0034] The fourth screening condition is: the width W is less than the second width value, and the height H is greater than the second height value;

[0035] The fifth screening condition is: the width W is less than the third width value, and the height H is greater than the third height value, wherein;

[0036] The sixth screening condition is: the width W is less than the fourth width value, and the height H is greater than the fourth height value; wherein the second width value, the third width value, and the fourth width value increase in sequence, the second height value, the third height value, and the fourth height value increase in sequence, and the second height value is much greater than the second width value;

[0037] The seventh screening condition is: the ratio of the width W to the number of singular points Nodd is less than the first value, and the number of singular points Nodd is greater than the first number;

[0038] The eighth screening condition is: the ratio of the width W to the number of singular points Nodd is less than the second value, and the number of singular points is greater than the second number; wherein the first value, the first number, the second value, and the second number increase in order.

[0039] The embodiment of the present invention further provides a fingerprint image humidity assessment device, comprising:

[0040] A processing module, used for dynamically binarizing the fingerprint image to obtain a binary image;

[0041] An analysis module, used for performing connected domain analysis on the binary image to obtain each connected domain and feature information of each connected domain;

[0042] A screening module, used for screening out abnormal connected domains from all connected domains according to each of the characteristic information;

[0043] The calculation module is used to calculate the area ratio of the abnormal connected domain in all connected domains, and use the area ratio as a humidity evaluation index.

[0044] The embodiment of the present invention further provides a fingerprint image humidity assessment system, comprising:

[0045] Memory for storing computer programs;

[0046] A processor is used to implement the steps of the fingerprint image moisture assessment method as described above when executing the computer program.

[0047] The embodiment of the present invention provides a method, device, system and computer-readable storage medium for humidity assessment of a fingerprint image. The method includes: dynamically binarizing the fingerprint image to obtain a binary image; performing connected domain analysis on the binary image to obtain each connected domain and feature information of each connected domain; screening out abnormal connected domains from all connected domains based on each feature information; calculating the area ratio of the abnormal connected domain in all connected domains, and using the area ratio as a humidity assessment indicator.

[0048] It can be seen that the embodiment of the present invention performs dynamic binarization processing on the fingerprint image to obtain the binarized image, then performs connected domain analysis on the binarized image to obtain feature information of each connected domain, and then screens each connected domain according to the feature information of each connected domain to screen out abnormal connected domains, and further determines the humidity assessment index of the fingerprint image according to the area ratio of the abnormal connected domain in all connected domains. In the present invention, since the fingerprint image is binarized by dynamic binarization processing, it is not affected by the light and dark changes of the fingerprint itself, so that the humidity assessment index finally obtained is more accurate, which is beneficial to improving the accuracy of the humidity assessment of the fingerprint image. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the prior art and the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1A schematic diagram of a flow chart of a method for evaluating humidity of a fingerprint image provided by an embodiment of the present invention;

[0051] Figure 2 A schematic diagram of a fingerprint image before and after dynamic binarization provided in an embodiment of the present invention;

[0052] Figure 3 A schematic diagram of a neighborhood of a pixel point provided in an embodiment of the present invention;

[0053] Figure 4 A schematic diagram of a singular point provided in an embodiment of the present invention;

[0054] Figure 5 A schematic diagram of a fingerprint image with high humidity provided in an embodiment of the present invention;

[0055] Figure 6 A schematic diagram of a normal fingerprint image provided in an embodiment of the present invention;

[0056] Figure 7 A schematic diagram of the structure of a humidity assessment device for a fingerprint image provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] The embodiments of the present invention provide a method, device, system and computer-readable storage medium for evaluating humidity of a fingerprint image, which can make the humidity evaluation index finally obtained more accurate during use, thereby improving the accuracy of humidity evaluation of a fingerprint image.

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0059] Please refer to Figure 1 , Figure 1 A schematic flow chart of a method for evaluating humidity of a fingerprint image provided by an embodiment of the present invention. The method comprises:

[0060] S110: Perform dynamic binarization processing on the fingerprint image to obtain a binary image;

[0061] It should be noted that in order to reduce the influence of the light and dark changes of the fingerprint itself on the humidity assessment of the fingerprint image in the embodiment of the present invention, a dynamic binarization method is used to perform dynamic binarization on the fingerprint image when binarizing the fingerprint image to obtain a corresponding binary image.

[0062] The specific process is as follows:

[0063] For each pixel in the fingerprint image, obtain the neighborhood corresponding to the pixel;

[0064] Determine the dynamic grayscale threshold corresponding to the pixel point according to the grayscale mean of the neighborhood;

[0065] Binarization is performed on the grayscale value of the pixel point according to the dynamic grayscale threshold to obtain a binarization result;

[0066] A binary image is constructed based on the binarization results of all pixels.

[0067] It is understandable that the grayscale threshold in the embodiment of the present invention is not a fixed threshold, but is determined for different pixels by the grayscale mean of the neighborhood corresponding to the pixel. The neighborhood size can be preset, for example, the neighborhood side length is preset to N, and then the grayscale value of each pixel in the neighborhood is obtained, and the grayscale mean is obtained by averaging, and then the dynamic grayscale threshold of the pixel is obtained according to the grayscale mean of the neighborhood, and each pixel of the fingerprint image is binarized according to the dynamic grayscale threshold.

[0068] Specifically, the grayscale mean of all pixels in the neighborhood can be calculated according to the first calculation formula, where the first calculation formula is: Among them, M is the grayscale mean, N is the side length of the neighborhood, and I(i,j) is the grayscale value of the pixel with relative coordinates (i,j) in the neighborhood;

[0069] According to the second calculation relationship and the grayscale mean, the dynamic grayscale threshold corresponding to the pixel point is obtained, wherein the second calculation relationship is: Thr=M+a, wherein Thr is the dynamic grayscale threshold and a is a constant.

[0070] For example, for a pixel in a fingerprint image, its gray value is 1, and the process of binarization according to the dynamic gray threshold is:

[0071]

[0072] The dynamic grayscale threshold corresponding to each pixel is determined respectively, and then the pixel is binarized. When all the pixels are binarized, the dynamic binarization of the fingerprint image is completed. Figure 2 The images before and after dynamic binarization are shown, where the left side is the original fingerprint image and the right side is the binarized image after dynamic binarization.

[0073] S120: Performing connected domain analysis on the binary image to obtain each connected domain and feature information of each connected domain;

[0074] It should be noted that, in the embodiment of the present invention, a seed filling algorithm can be used to perform connected domain analysis on the binary image. Specifically, as long as the white pixels are connected up, down, left, and right, they belong to the same connected domain. Figure 2 The binary image on the right side contains multiple connected domains, and the connected domains correspond to the ridges of the fingerprint. After determining each connected domain, the characteristic information of each connected domain is further counted, which may include the area S, perimeter C, height H, width W, and the number of singular points Nodd on the edge of the connected domain, etc. It may also include the aspect ratio, the ratio of the perimeter to the number of singular points, and other information.

[0075] The area S represents the number of pixels in the connected domain; the perimeter C represents the number of pixels at the edge of the connected domain; the height H represents the difference between the maximum and minimum ordinates of the connected domain, that is, H = y max -y min ; The width W represents the difference between the maximum and minimum horizontal coordinates of the connected domain, W = x max -x min ; Aspect ratio lw = H / W; The number of singular points Nodd represents the number of all singular points on the edge of the connected domain.

[0076] like Figure 3 As shown in the figure, for a point in the center, the four points above, below, left and right are its four neighborhoods. For a point on the edge, if there is only one pixel in its four neighborhoods that belongs to the same connected domain as it, then it must be a singular point; if there are two pixels in its four neighborhoods that belong to the same connected domain as it, then it depends on the situation. When these two pixels are in the upper and lower positions or the left and right positions, they are considered singular points, while the upper left, lower left, upper right, and lower right are not considered singular points. Figure 4 In the connected domain, the five circled points are all singular points.

[0077] S130: Filtering out abnormal connected domains from all connected domains according to various feature information;

[0078] Specifically, after obtaining the characteristic information of each connected domain, in the embodiment of the present invention, the abnormal connected domains can be screened out from all the connected domains according to the respective characteristic information.

[0079] The process of selecting abnormal connected domains from all connected domains according to each feature information in S130 may specifically be:

[0080] For each connected domain, whether the ridge of the fingerprint is normal is determined based on the characteristic information of the connected domain. If normal, the connected domain is a normal connected domain; if abnormal, the connected domain is an abnormal connected domain.

[0081] It should be noted that the connected domain corresponding to a normal ridge line is usually a whole root with a large area, and the edge of the connected domain is relatively smooth and free of burrs. The connected domain corresponding to the ridge line of a wetter finger is often disconnected, resulting in a smaller area, and sometimes also causing the ridge line to deform or even disappear, and the number of singular points on the edge of the corresponding connected domain increases. Therefore, in the embodiment of the present invention, it is possible to further determine whether the ridge line corresponding to the connected domain is normal based on the characteristic information of the connected domain. When the connected domain is normal, it means that the corresponding ridge line is a normal ridge line. When the connected domain is abnormal, it means that the corresponding ridge line is an abnormal ridge line.

[0082] Furthermore, judging whether the ridges of the fingerprint are normal based on the feature information of the connected domain may specifically be:

[0083] Preset multiple filtering conditions;

[0084] When the feature information corresponding to the connected domain meets at least one screening condition, the ridge line of the fingerprint is an abnormal ridge line; when the feature information corresponding to the connected domain does not meet each screening condition, the ridge line of the fingerprint is a normal ridge line.

[0085] It can be understood that in the embodiment of the present invention, multiple filtering conditions can be pre-set in the process of determining whether the ridges of the fingerprint are normal, and then the feature information of each connected domain is filtered according to these filtering conditions. When the feature information meets at least one filtering condition, the corresponding ridge line of the fingerprint is an abnormal ridge line, and the connected domain is an abnormal connected domain; when the feature information does not meet all the filtering conditions, the ridge line of the fingerprint is a normal ridge line, and the connected domain is a normal connected domain.

[0086] Among them, the multiple screening conditions are:

[0087] The first screening condition is: the area S is smaller than the first area (for example, 50), that is, S<50;

[0088] The second screening condition is: the height H is less than the first height value (for example, 20), and the width W is less than the first width value (for example, 20); that is, H<20 and W<20;

[0089] The third screening condition is: the perimeter C is less than the preset perimeter (for example, 30); that is, C<30;

[0090] The fourth screening condition is: the width W is less than the second width value (for example, 3), and the height H is greater than the second height value (for example, 70); that is, W<3 and H>70;

[0091] The fifth screening condition is: the width W is less than the third width value (for example, 10), and the height H is greater than the third height value (for example, 90); that is, W<10 and H>90;

[0092] The sixth screening condition is: the width W is less than the fourth width value (for example, 15), and the height H is greater than the fourth height value (for example, 150); that is, W<15 and H>150; wherein the second width value, the third width value, and the fourth width value increase in sequence, the second height value, the third height value, and the fourth height value increase in sequence, and the second height value is much greater than the second width value;

[0093] The seventh screening condition is: the ratio of the width W to the number of singular points Nodd is less than the first value (for example, 6), and the number of singular points Nodd is greater than the first number (for example, 10); that is, W / Nodd<6 and Nodd>10;

[0094] The eighth screening condition is: the ratio of the width W to the number of singular points Nodd is less than the second value (for example, 15), and the number of singular points is greater than the second number (for example, 20); that is, W / Nodd<15 and Nodd>20; wherein the first value, the first number, the second value, and the second number increase in order.

[0095] In the embodiment of the present invention, the area is S, the height is H, the width is W, the perimeter is C, the unit of Nodd is the number of pixels, and C / Nodd is a ratio, which is a dimensionless quantity.

[0096] The purpose of the screening conditions is to distinguish the connected domains corresponding to abnormal ridges and normal ridges. Therefore, the screening conditions are not limited to the above 8 conditions. The screening conditions can also be determined by combining the actual effects of individual ridges and the characteristics of the corresponding connected domains. Similarly, the various thresholds can also be adjusted accordingly according to actual conditions.

[0097] As long as the characteristic information of the connected domain meets any one or more of the filtering conditions, the connected domain can be considered to be the connected domain corresponding to the abnormal ridge line. Only when none of these filtering conditions are met can it be considered to be the connected domain corresponding to the normal ridge line. Each value in these filtering conditions is an empirical value and can be determined according to actual conditions. The present invention does not make any special limitations.

[0098] like Figure 5 The image shown is a fingerprint with high humidity. Figure 5 The left side is the original image, the middle is the result of dynamic binarization, which contains multiple connected domains. Those connected domains with smaller areas, more burrs, and irregular edge shapes correspond to abnormal ridges. The right side is the connected domains remaining after removing the connected domains of abnormal ridges. The remaining connected domains correspond to normal ridges.

[0099] like Figure 6 is an image of a normal fingerprint. Figure 6 The left side is the original image. Figure 6The middle part shows the result of dynamic binarization. From the middle part, we can see that these connected domains are relatively complete, large in area, and have smooth edges. Figure 6 The right side shows the connected domain corresponding to the normal ridge line that remains after conditional screening.

[0100] S140: Calculate the area ratio of each abnormal connected domain to all connected domains, and use the area ratio as a humidity assessment index.

[0101] It should be noted that, after determining each abnormally connected domain, the area of ​​all the abnormally connected domains can be compared with the area of ​​all the connected domains to obtain a corresponding ratio, and the ratio is used as a humidity assessment index.

[0102] Specifically, in practical applications, we can first calculate the sum of the areas of all connected domains in the binarization result S All , and then calculate the sum of the connected domain areas after the "abnormal ridge" condition screening S normal , S All -S normal It is the total area of ​​the abnormally connected domain, and then the ratio is further obtained, as follows:

[0103]

[0104]

[0105]

[0106] Wherein, i' represents the i'th connected domain among all connected domains, N' represents the number of all connected domains, j' represents the j'th normal connected domain among all normal connected domains, and M' represents the number of all normal connected domains.

[0107] Thus, the humidity evaluation index H' of the fingerprint can be obtained. From the above formula, it can be seen that the larger the H' is, the greater the humidity is, and the worse the corresponding image effect is.

[0108] It can be seen that the embodiment of the present invention performs dynamic binarization processing on the fingerprint image to obtain the binarized image, then performs connected domain analysis on the binarized image to obtain feature information of each connected domain, and then screens each connected domain according to the feature information of each connected domain to screen out abnormal connected domains, and further determines the humidity assessment index of the fingerprint image according to the area ratio of the abnormal connected domain in all connected domains. In the present invention, since the fingerprint image is binarized by dynamic binarization processing, it is not affected by the light and dark changes of the fingerprint itself, so that the humidity assessment index finally obtained is more accurate, which is beneficial to improving the accuracy of the humidity assessment of the fingerprint image.

[0109] Based on the above embodiment, the present invention also provides a fingerprint image humidity assessment device. Figure 7 , the device comprises:

[0110] The processing module 21 is used to perform dynamic binarization processing on the fingerprint image to obtain a binary image;

[0111] The analysis module 22 is used to perform connected domain analysis on the binary image to obtain each connected domain and feature information of each connected domain;

[0112] A screening module 23 is used to screen out abnormal connected domains from all connected domains according to various feature information;

[0113] The calculation module 24 is used to calculate the area ratio of the abnormal connected domain in all connected domains, and use the area ratio as a humidity assessment index.

[0114] It should be noted that the humidity assessment device for a fingerprint image provided in an embodiment of the present invention has the same beneficial effects as the humidity assessment method for a fingerprint image provided in the above embodiment, and for the specific introduction to the humidity assessment method for a fingerprint image designed in an embodiment of the present invention, please refer to the above embodiment, and the present invention will not go into details here.

[0115] Based on the above embodiment, the embodiment of the present invention further provides a fingerprint image humidity assessment system, which includes:

[0116] Memory for storing computer programs;

[0117] A processor is used to implement the steps of the above-mentioned fingerprint image moisture assessment method when executing a computer program.

[0118] For example, the processor in the embodiment of the present invention is specifically used to implement dynamic binarization processing of the fingerprint image to obtain a binary image; perform connected domain analysis on the binary image to obtain each connected domain and feature information of each connected domain; filter out abnormal connected domains from all connected domains based on each feature information; calculate the area ratio of the abnormal connected domain in all connected domains, and use the area ratio as a humidity assessment indicator.

[0119] Based on the above embodiment, an embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the humidity assessment method for a fingerprint image are implemented.

[0120] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0121] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0122] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0123] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for evaluating humidity of a fingerprint image, characterized in that: include: Perform dynamic binarization processing on the fingerprint image to obtain a binary image; Performing connected domain analysis on the binary image to obtain each connected domain and feature information of each connected domain; Filtering out abnormal connected domains from all connected domains according to each of the characteristic information; The area ratio of the abnormally connected domain in all connected domains is calculated, and the area ratio is used as a humidity assessment index; wherein: The process of screening out abnormal connected domains from all connected domains according to each of the feature information is as follows: For each of the connected domains, judging whether the ridges of the fingerprint are normal according to the characteristic information of the connected domain, if normal, the connected domain is a normal connected domain; if abnormal, the connected domain is an abnormal connected domain; the characteristic information includes the area, perimeter, height, width and the number of singular points on the edge of the connected domain; The process of judging whether the ridge line of the fingerprint is normal according to the characteristic information of the connected domain is as follows: presetting multiple screening conditions; when the characteristic information corresponding to the connected domain satisfies at least one screening condition, the ridge line of the fingerprint is an abnormal ridge line; when the characteristic information corresponding to the connected domain does not satisfy each of the screening conditions, the ridge line of the fingerprint is a normal ridge line; The plurality of said screening conditions are: The first screening condition is: the area S is smaller than the first area; The second screening condition is: the height H is less than the first height value, and the width W is less than the first width value; The third screening condition is: the perimeter C is less than the preset perimeter; The fourth screening condition is: the width W is less than the second width value, and the height H is greater than the second height value; The fifth screening condition is: the width W is less than the third width value, and the height H is greater than the third height value, wherein; The sixth screening condition is: the width W is less than the fourth width value, and the height H is greater than the fourth height value; wherein the second width value, the third width value, and the fourth width value increase in sequence, the second height value, the third height value, and the fourth height value increase in sequence, and the second height value is much greater than the second width value; The seventh screening condition is: the ratio of the perimeter C to the number of singular points Nodd is less than the first value, and the number of singular points Nodd is greater than the first number; The eighth screening condition is: the ratio of the perimeter C to the number of singular points Nodd is less than the second value, and the number of singular points is greater than the second number; wherein the first value, the first number, the second value, and the second number increase in order.

2. The fingerprint image humidity assessment method according to claim 1, characterized in that: The process of dynamically binarizing the fingerprint image to obtain the binary image is as follows: For each pixel in the fingerprint image, obtain a neighborhood corresponding to the pixel; Determine a dynamic grayscale threshold corresponding to the pixel point according to the grayscale mean of the neighborhood corresponding to the pixel point; Binarize the grayscale value of the pixel point according to the dynamic grayscale threshold to obtain a binarization result; A binary image is constructed based on the binarization results of all pixels.

3. The method for evaluating humidity of a fingerprint image according to claim 2, characterized in that: The process of determining the dynamic grayscale threshold corresponding to the pixel point according to the grayscale mean value of the neighborhood is: The grayscale mean of all pixels in the neighborhood corresponding to the pixel is calculated according to the first calculation formula, wherein the first calculation formula is: Where M is the grayscale mean, N is the side length of the neighborhood, and I(i, j) is the grayscale value of the pixel with relative coordinates (i, j) in the neighborhood. According to the second calculation relationship and the grayscale mean, a dynamic grayscale threshold corresponding to the pixel point is obtained, wherein the second calculation relationship is: Thr=M+a, wherein Thr is the grayscale threshold and a is an adjustable constant.

4. The method for evaluating humidity of a fingerprint image according to claim 3, characterized in that: The process of binarizing the grayscale value of the pixel point according to the dynamic grayscale threshold is as follows: According to the third calculation relationship and the grayscale threshold, a binarization result corresponding to the pixel point is obtained, wherein the third calculation relationship is:

5. The method for evaluating humidity of a fingerprint image according to claim 3, characterized in that: The process of performing connected domain analysis on the binary image is as follows: A seed filling algorithm is used to perform connected domain analysis on the binary image.

6. A fingerprint image humidity assessment device, characterized in that: include: A processing module, used for dynamically binarizing the fingerprint image to obtain a binary image; An analysis module, used for performing connected domain analysis on the binary image to obtain each connected domain and feature information of each connected domain; A screening module, used for screening out abnormal connected domains from all connected domains according to each of the characteristic information; A calculation module is used to calculate the area ratio of the abnormal connected domain in all connected domains, and use the area ratio as a humidity assessment index; wherein the screening module is used to: For each of the connected domains, judging whether the ridges of the fingerprint are normal according to the characteristic information of the connected domain, if normal, the connected domain is a normal connected domain; if abnormal, the connected domain is an abnormal connected domain; the characteristic information includes the area, perimeter, height, width and the number of singular points on the edge of the connected domain; The process of judging whether the ridge line of the fingerprint is normal according to the characteristic information of the connected domain is as follows: presetting multiple screening conditions; when the characteristic information corresponding to the connected domain satisfies at least one screening condition, the ridge line of the fingerprint is an abnormal ridge line; when the characteristic information corresponding to the connected domain does not satisfy each of the screening conditions, the ridge line of the fingerprint is a normal ridge line; The plurality of said screening conditions are: The first screening condition is: the area S is smaller than the first area; The second screening condition is: the height H is less than the first height value, and the width W is less than the first width value; The third screening condition is: the perimeter C is less than the preset perimeter; The fourth screening condition is: the width W is less than the second width value, and the height H is greater than the second height value; The fifth screening condition is: the width W is less than the third width value, and the height H is greater than the third height value, wherein; The sixth screening condition is: the width W is less than the fourth width value, and the height H is greater than the fourth height value; wherein the second width value, the third width value, and the fourth width value increase in sequence, the second height value, the third height value, and the fourth height value increase in sequence, and the second height value is much greater than the second width value; The seventh screening condition is: the ratio of the perimeter C to the number of singular points Nodd is less than the first value, and the number of singular points Nodd is greater than the first number; The eighth screening condition is: the ratio of the perimeter C to the number of singular points Nodd is less than the second value, and the number of singular points is greater than the second number; wherein the first value, the first number, the second value, and the second number increase in order.

7. A fingerprint image humidity assessment system, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the fingerprint image moisture assessment method according to any one of claims 1 to 5 when executing the computer program.

Images