CN106250890B - Fingerprint identification method and device - Google Patents
Fingerprint identification method and device Download PDFInfo
- Publication number
- CN106250890B CN106250890B CN201610846389.0A CN201610846389A CN106250890B CN 106250890 B CN106250890 B CN 106250890B CN 201610846389 A CN201610846389 A CN 201610846389A CN 106250890 B CN106250890 B CN 106250890B
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- target
- determining
- preset
- sweat
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1382—Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger
- G06V40/1388—Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger using image processing
Abstract
The embodiment of the invention discloses a fingerprint identification method and a fingerprint identification device. Wherein, the method comprises the following steps: the fingerprint identification device can collect a fingerprint image aiming at a target object, determine a target fingerprint line from the fingerprint image, judge whether sweat gland holes exist in the target fingerprint line, and determine that the fingerprint of the target object is a fingerprint living body if the sweat gland holes exist; if sweat pores are not present, the fingerprint of the target object is determined to be a fingerprint prosthesis. By the embodiment of the invention, the fingerprint identification device can identify sweat gland holes in the fingerprint image and identify the authenticity of the fingerprint according to whether the sweat gland holes exist in the fingerprint image, so that the authenticity of the fingerprint can be accurately identified, and the safety of fingerprint identification is improved.
Description
Technical Field
The invention relates to the technical field of biological identification, in particular to a fingerprint identification method and a fingerprint identification device.
Background
The fingerprint refers to the lines generated by the convex and concave unevenness on the skin on the front side of the tail end of the finger of the user, and the fingerprint identification refers to the identification of the finger by comparing the minutiae characteristic points of different fingerprints. Since fingerprints of different users are different, the fingerprints can be used for identity authentication. At present, fingerprint identification is widely applied to security and settlement systems of entrance guard attendance, e-commerce transactions, financial transactions, personal computers and mobile phones.
With the development of fingerprint identification technology, fingerprint identification devices are excellent in convenience and correctness, but also have the problem of false fingerprint misrecognition. The false fingerprint is generally made of printed paper or film and also made of silica gel or rubber, and the texture of the false fingerprint is approximately the same as that of a true fingerprint, so that the existing fingerprint identification technology is difficult to identify the true fingerprint and the false fingerprint. Therefore, how to accurately identify the true and false fingerprints has become an urgent problem to be solved.
Disclosure of Invention
The embodiment of the invention discloses a fingerprint identification method and a fingerprint identification device, which can accurately identify the authenticity of a fingerprint, thereby improving the safety of fingerprint identification.
The embodiment of the invention discloses a fingerprint identification method, which comprises the following steps:
acquiring a fingerprint image aiming at a target object, and determining target fingerprint lines from the fingerprint image;
judging whether sweat gland holes exist in the target fingerprint lines or not;
if the sweat pore exists, determining that the fingerprint of the target object is a fingerprint living body;
if the sweat pore is not present, determining the fingerprint of the target object as a fingerprint prosthesis.
Correspondingly, the embodiment of the invention discloses a fingerprint identification device, which comprises:
an acquisition unit for acquiring a fingerprint image for a target object;
a first determination unit for determining a target fingerprint pattern from the fingerprint image;
the judging unit is used for judging whether sweat pores exist in the target fingerprint lines or not;
the second determining unit is used for determining the fingerprint of the target object as a fingerprint living body when the judging unit judges that the target fingerprint lines have the sweat pores;
the second determining unit is further configured to determine that the fingerprint of the target object is a fingerprint prosthesis when the determining unit determines that the target fingerprint pattern does not have the sweat pore.
The embodiment of the invention has the following beneficial effects:
in the embodiment of the invention, the fingerprint identification device can collect a fingerprint image aiming at a target object, determine a target fingerprint line from the fingerprint image, judge whether sweat pores exist in the target fingerprint line, and determine that the fingerprint of the target object is a fingerprint living body if the sweat pores exist; if sweat pores are not present, the fingerprint of the target object is determined to be a fingerprint prosthesis. By the embodiment of the invention, the fingerprint identification device can identify sweat gland holes in the fingerprint image and identify the authenticity of the fingerprint according to whether the sweat gland holes exist in the fingerprint image, so that the authenticity of the fingerprint can be accurately identified, and the safety of fingerprint identification is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a fingerprint identification method according to an embodiment of the present invention;
FIG. 2 is a fingerprint image disclosed by an embodiment of the present invention;
FIG. 3 is a gray scale diagram of a target fingerprint texture section according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart illustrating another fingerprint identification method according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of a fingerprint identification device according to an embodiment of the present invention;
FIG. 6 is a schematic structural diagram of another fingerprint identification device according to an embodiment of the present disclosure;
fig. 7 is a schematic structural diagram of a fingerprint identification device disclosed in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention discloses a fingerprint identification method and a fingerprint identification device. The method can accurately identify the authenticity of the fingerprint, thereby improving the safety of fingerprint identification. The following are detailed below.
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a fingerprint identification method according to an embodiment of the present invention. The method shown in fig. 1 may be applied to security and settlement systems of terminal devices such as an access attendance system, an e-commerce transaction system, a financial transaction system, a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palm computer, a Personal Digital Assistant (PDA), a Mobile Internet Device (MID), an intelligent wearable Device, etc. As shown in fig. 1, the fingerprint identification method may include the steps of:
101. the fingerprint identification device collects a fingerprint image for a target object and determines a target fingerprint pattern from the fingerprint image.
In the embodiment of the present invention, the target fingerprint grain is any grain in the fingerprint image, and the target object may be a user, or a finger of the user or another object having a fingerprint grain. The fingerprint identification device can acquire the fingerprint of a target object through the fingerprint sensor and capture a frame of fingerprint image. At this moment, the collected fingerprint image comprises a plurality of fingerprint lines, and the fingerprint identification device only needs to determine one fingerprint line at will. As shown in fig. 2, fig. 2 is a fingerprint image disclosed in the embodiment of the present invention, and in fig. 2, it can be clearly seen that the fingerprint image is composed of a plurality of fingerprint lines.
102. The fingerprint identification device judges whether sweat pores exist in the target fingerprint lines, if so, step 103 is executed; if not, go to step 104.
In the embodiment of the invention, after the target fingerprint line is determined, the fingerprint identification device searches sweat gland holes in the target fingerprint line, if sweat gland holes exist in the target fingerprint line, the fingerprint can be determined to be true, and if sweat gland holes do not exist in the target fingerprint line, the fingerprint is determined to be false.
Further, the specific manner of the fingerprint identification device determining whether sweat pores exist in the target fingerprint lines may be:
acquiring a gray-scale image of a target fingerprint grain section, and determining characteristic information of the gray-scale image;
judging whether the characteristic information is matched with preset characteristic information or not;
and if the characteristic information is matched with preset characteristic information, searching a target characteristic point in the gray-scale image according to the characteristic information, and determining the target characteristic point as a sweat gland hole.
In a specific implementation, after determining a target fingerprint grain, the fingerprint identification device selects any point on the target fingerprint grain, and with the point as a center, first cuts a section in any direction, calculates gray scale values of all positions on the section, and draws a gray scale map of the section, as shown in fig. 3, where fig. 3 is a gray scale map of a section of the target fingerprint grain disclosed in the embodiment of the present invention. The gray scale map is composed of gray scale values on a section, and the fingerprint identification device can determine the characteristic information of the gray scale map. The characteristic information may refer to a trend of a connection line between gray scale values, such as forming a horizontal straight line, forming a curve (such as the gray scale graph shown in fig. 3) like a "valley" or a "peak", forming a wavy line, or forming an inclined or vertical straight line, and the like, which is not limited in the embodiment of the present invention.
Further, after determining the characteristic information of the gray-scale image, the fingerprint identification device further judges whether the characteristic information is matched with preset characteristic information, if so, the fingerprint identification device searches a target characteristic point in the gray-scale image according to the characteristic information and determines the target characteristic point as the sweat gland hole of the finger of the user. Specifically, the preset feature information may be that a connection line between the gray-scale values is a curve like a "valley" or a "peak". The matching of the characteristic information of the gray-scale map and the preset characteristic information can be understood as follows: the connecting line between the gray scale values in the gray scale map is a curve like a valley or a peak.
Therefore, if the characteristic information of the gray-scale image is matched with the preset characteristic information, the fingerprint identification device can search the target characteristic point in the gray-scale image. If the characteristic information of the gray-scale image is that the connecting line between the gray-scale values is a curve like a valley, the target characteristic point is specifically the lowest point in the gray-scale image; if the characteristic information of the gray scale map is that the connecting line between the gray scale values is a curve like a peak, the target characteristic point specifically refers to the highest point in the gray scale map.
It should be noted that, if the feature information of the grayscale map does not match the preset feature information, the fingerprint identification device may use the current point as the center and use the tangent plane as the start plane, rotate a certain angle and then obtain the tangent plane again, so as to continue to draw the grayscale map of the tangent plane until the feature information of the grayscale map matches the preset feature information.
Further, if the gray-scale map with the matching feature information and the preset feature information is not found after the current point is rotated by 180 degrees, the fingerprint identification device may find the next point near the point and repeat the above determination. If no gray-scale image with characteristic information matched with the preset characteristic information is found in the target fingerprint grain, the sweat pore does not exist in the target fingerprint grain.
103. The fingerprint recognition device determines the fingerprint of the target object as a live fingerprint.
In the embodiment of the invention, when the fingerprint identification device judges that sweat pores exist in the target fingerprint lines, the fingerprint corresponding to the fingerprint image is a true fingerprint, and the fingerprint of the target object can be determined to be a fingerprint living body to a certain extent.
104. The fingerprint identification device determines the fingerprint of the target object as a fingerprint prosthesis.
In the embodiment of the invention, when the fingerprint identification device judges that sweat pores do not exist in the target fingerprint pattern, the fingerprint corresponding to the fingerprint image is a false fingerprint, and the fingerprint of the target object can be determined to be a fingerprint false body to a certain extent.
For example, if a user needs to enter a vault, a fingerprint model made of silica gel is used for fingerprint authentication, although the fingerprint identification device identifies that the right corresponding to the fingerprint can enter the vault, obviously the sweat gland hole cannot be found in any fingerprint line, and the fingerprint identification device can determine that the fingerprint is a false fingerprint, so that the authentication on the fingerprint fails.
It can be seen that, in the method described in fig. 1, after the fingerprint identification device collects the fingerprint image of the target object, it may determine any fingerprint line from the fingerprint image, and determine whether sweat gland holes exist in the fingerprint line, if sweat gland holes exist, it indicates that the fingerprint of the target object is a living fingerprint, and if sweat gland holes do not exist, it indicates that the fingerprint of the target object is a fingerprint prosthesis. By the embodiment of the invention, the fingerprint identification device can identify sweat gland holes in the fingerprint image and identify the authenticity of the fingerprint according to whether the sweat gland holes exist in the fingerprint image, so that the authenticity of the fingerprint can be accurately identified, and the safety of fingerprint identification is improved.
Referring to fig. 4, fig. 4 is a schematic flowchart illustrating another fingerprint identification method according to an embodiment of the present invention. As shown in fig. 4, the fingerprint identification method may include the steps of:
401. the fingerprint identification device collects a fingerprint image for a target object and determines a target fingerprint pattern from the fingerprint image.
In the embodiment of the present invention, the target fingerprint line is any line in the fingerprint image, and the embodiment of the present invention is not limited.
402. The fingerprint identification device obtains the line width of the target fingerprint line and judges whether the line width is within a preset width range, if so, step 403 is executed; if not, go to step 407.
In the embodiment of the present invention, the preset width range may be 400um to 600um, and the embodiment of the present invention is not limited. After determining the target fingerprint texture, the fingerprint identification device can acquire a gray scale map of the section of the target fingerprint texture. As shown in fig. 2, in a typical gray scale map of a fingerprint section, the gray scale values at the two ends are lower than the gray scale value at the middle portion because the positions represented by the two ends in the gray scale map are the gaps between two fingerprint lines. Therefore, after the fingerprint identification device obtains the gray-scale image of the section of the target fingerprint texture, the texture width of the target fingerprint texture is determined according to the positions corresponding to the two ends in the gray-scale image.
Specifically, the fingerprint identification device determines the line width of the target fingerprint line according to the positions corresponding to the two ends in the gray-scale image, and the determination may be as follows: after the fingerprint identification device acquires the gray scale image, whether a connecting line between all gray scale values in the gray scale image is symmetrical needs to be judged, if the middle position of the connecting line is taken as a central point, the gray scale values of two points which are the same with the central point are basically the same, if the connecting line is symmetrical, the tangent plane is a tangent plane which is vertical to the grain direction of the target fingerprint grain, then the points corresponding to the gray scale values which are positioned at two ends of the connecting line in the gray scale image can be determined to be a gap between the two fingerprint grains, and therefore the distance between the two points can be calculated, and the distance is the grain width of the target fingerprint grain.
Generally, the line width of a normal person fingerprint line is between 400um and 600um, and then the fingerprint identification device can judge whether the line width is in the range after determining the line width of a target fingerprint line, if so, the fingerprint identification device only has to judge whether sweat gland holes exist in the target fingerprint line, and if not, the fingerprint of the target object is a false fingerprint.
In the embodiment of the invention, under the normal condition, the width of each fingerprint line of each user is in a certain range, although the false fingerprint made by silica gel or rubber is almost the same as the line of a real fingerprint, the condition that the width of the fingerprint line is not proper is not eliminated, therefore, the judgment on the width of the fingerprint line is increased, the accuracy of identifying the real and false fingerprints can be improved, and the safety of fingerprint identification is improved.
403. The fingerprint identification device judges whether sweat pores exist in the target fingerprint lines, if so, step 404 is executed; if not, go to step 407.
In the embodiment of the present invention, the way of identifying sweat pores by the fingerprint identification device is the same as the above embodiment, and is not repeated herein.
404. The fingerprint identification device determines the line direction of the target fingerprint line and searches sweat pores in the target fingerprint line along the line direction.
In the embodiment of the present invention, the fingerprint identification device determines the grain direction of the target fingerprint grain, specifically: acquiring a gray-scale image of a target fingerprint grain section, and determining characteristic information of the gray-scale image; judging whether the characteristic information is matched with preset characteristic information or not; and if the characteristic information is matched with the preset characteristic information, determining the direction of the normal of the straight line of the tangent plane in the target fingerprint grain as the grain direction of the target fingerprint grain. The normal line is a straight line perpendicular to the straight line of the tangent plane in the target fingerprint pattern.
Further, after determining the texture direction of the target fingerprint texture, the fingerprint identification device may search sweat pores in the target fingerprint texture along the texture direction, and record the number of sweat pores, and please refer to step 102 for a specific search mode.
Optionally, the fingerprint identification device may search all sweat pores in the target fingerprint grain, or may continuously search for 5 or more sweat pores based on the first found sweat pore.
405. The fingerprint identification device judges whether the number of sweat gland holes in the target fingerprint texture exceeds a preset number threshold, if so, step 406 is executed; if not, go to step 407.
In this embodiment of the present invention, the preset number threshold may be 5, 7, or 10, and the embodiment of the present invention is not limited. After sweat gland holes of target fingerprint lines are found out along the line direction by the fingerprint identification device, whether the number of the sweat gland holes in the target fingerprint lines exceeds a preset number threshold value or not can be judged, if the number of the sweat gland holes exceeds the preset number threshold value, continuous sweat gland holes exist in the line direction of the target fingerprint lines to a certain extent, and then the fingerprint of the target object can be determined as a fingerprint living body. If the number of sweat pores in the target fingerprint pattern does not exceed the preset number threshold, it indicates to some extent that there are no continuous sweat pores in the pattern direction of the target fingerprint pattern, and the fingerprint of the target object may be determined as a fingerprint prosthesis.
In the embodiment of the invention, the judgment of the number of sweat gland holes is added, so that the accidental occurrence of target characteristic points in the section gray-scale image caused by other impurities in the fingerprint acquisition process can be avoided, and the condition of misjudgment of true and false fingerprints can be reduced.
As a possible implementation, after determining that the number of sweat gland holes in the target fingerprint texture exceeds the preset number threshold, the fingerprint identification apparatus may further perform the following operations:
acquiring the distance between any two adjacent sweat gland holes;
judging whether the distance is within a preset distance range;
if the distance is within the preset distance range, determining the fingerprint of the target object as a fingerprint living body;
and if the distance is not within the preset distance range, determining the fingerprint of the target object as the fingerprint prosthesis.
In a specific implementation, the preset distance range may be 150um to 350um, and the sweat gland hole distance of a general person is used as a reference in the embodiment of the present invention, but the preset distance range is not limited in the embodiment of the present invention. Therefore, when the fingerprint identification device judges that the number of sweat gland holes in the target fingerprint texture exceeds a preset number threshold, a sweat gland hole can be determined at will, the distance between the sweat gland hole and the adjacent sweat gland holes is calculated, if the distance is within a preset distance range, the fingerprint of the target object is a fingerprint living body, and if the distance is not within the preset distance range, the fingerprint of the target object is a fingerprint false body.
In the embodiment of the invention, the judgment of the distance between sweat gland holes is added, so that the accuracy of fingerprint identification can be improved, and the safety of fingerprint identification is improved.
Certainly, there may be a special case that the distance between sweat gland holes of the fingerprint of the current user is really not within the preset distance range, in this case, the fingerprint identification device may pre-store the distance between sweat gland holes of the finger corresponding to the real fingerprint, and then when identifying that the feature of the fingerprint is matched with the feature of the fingerprint in the database, obtain the distance between sweat gland holes corresponding to the fingerprint in the database, thereby further determining whether the distance between sweat gland holes of the currently obtained fingerprint is matched with the data stored in the database, and is within the allowable error range, if so, determining that the fingerprint is a living fingerprint.
406. The fingerprint recognition device determines the fingerprint of the target object as a live fingerprint.
407. The fingerprint identification device determines the fingerprint of the target object as a fingerprint prosthesis.
As another possible implementation manner, when the fingerprint identification device identifies that the fingerprint of the target object is a fingerprint prosthesis, the fingerprint identification device may further output an early warning prompt to prompt that the fingerprint is a prosthesis.
For example, some bank insurance systems need to acquire the right to enter the insurance vault through fingerprint identification, and if a criminal makes a fake finger, the fingerprint identification device can identify whether the fingerprint is true or false by determining whether sweat pores exist in fingerprint lines after the fingerprint identification is passed, that is, the fingerprint is identified to have the right to enter the insurance vault. If the fingerprint identification device does not pass through the fingerprint identification, or sweat gland holes do not exist in the fingerprint lines, the fingerprint identification device can send out early warning prompts to prompt bank workers or security department safes that potential safety hazards exist. After receiving the early warning prompt, the bank staff or the public security organization can take corresponding protective measures to ensure the safety of property.
It can be seen that in the method described in fig. 4, the fingerprint identification device can identify sweat pores in the fingerprint image and identify the authenticity of the fingerprint according to whether sweat pores exist in the fingerprint image. Furthermore, the embodiment of the invention increases the judgment on the width of the fingerprint lines, the number of sweat gland holes, the distance between sweat gland holes and the like, and can reduce the error of the judgment of true and false fingerprints, thereby improving the accuracy and the safety of fingerprint identification.
Referring to fig. 5, fig. 5 is a schematic structural diagram of a fingerprint identification device according to an embodiment of the present invention. As shown in fig. 5, the fingerprint recognition device 500 may include the following elements:
an acquiring unit 501, configured to acquire a fingerprint image for a target object.
A first determining unit 502, configured to determine a target fingerprint pattern from the fingerprint image. Wherein, the target fingerprint line is any line in the fingerprint image.
The determining unit 503 is configured to determine whether sweat pores exist in the target fingerprint pattern.
A second determining unit 504, configured to determine that the fingerprint of the target object is a fingerprint living body when the determining unit 503 determines that sweat pores exist in the target fingerprint. Alternatively, when the determining unit 503 determines that sweat pores do not exist in the target fingerprint pattern, it determines that the fingerprint of the target object is a fingerprint prosthesis.
In the embodiment of the present invention, the fingerprint identification apparatus 500 may identify sweat pores in the fingerprint image, and identify the authenticity of the fingerprint according to whether sweat pores exist in the fingerprint image, so as to accurately identify the authenticity of the fingerprint, and improve the security of fingerprint identification.
Specifically, the specific way for determining whether sweat pores exist in the target fingerprint pattern by the determining unit 503 may be:
acquiring a gray-scale image of a target fingerprint grain section, and determining characteristic information of the gray-scale image;
judging whether the characteristic information is matched with preset characteristic information or not;
if the characteristic information is matched with preset characteristic information, detecting whether a target characteristic point exists in the gray-scale image or not according to the characteristic information;
and if the target characteristic point exists, determining the target characteristic point as a sweat pore.
The characteristic information may refer to a trend of a connection line between gray scale values, such as forming a horizontal straight line, forming a curve (such as the gray scale graph shown in fig. 3) like a "valley" or a "peak", forming a wavy line, or forming an inclined or vertical straight line, and the like, which is not limited in the embodiment of the present invention. The preset characteristic information may be that a connection line between the gray-scale values is a curve like a valley or a peak.
Referring to fig. 6, fig. 6 is a schematic structural diagram of another fingerprint identification device according to an embodiment of the present invention. The fingerprint recognition device 500 depicted in fig. 6 is optimized based on the fingerprint recognition device 500 depicted in fig. 5. As shown in fig. 6, the fingerprint identification device 500 may further include an obtaining unit 505 and a searching unit 506, wherein the obtaining unit 505 may perform the operations performed by the first obtaining unit and the second obtaining unit in the claims:
an obtaining unit 505 is configured to obtain a line width of the target fingerprint line.
The determining unit 503 is further configured to determine whether the texture width is within a preset width range, and if the texture width is not within the preset width range, trigger the second determining unit 504 to determine that the fingerprint of the target object is a fingerprint prosthesis. If the line width is in the preset width range, whether sweat pores exist in the target fingerprint line is further judged.
The preset width range may be 400um to 600um, and the embodiment of the present invention is not limited.
As a possible implementation manner, the first determining unit 502 is further configured to determine the line direction of the target fingerprint line when the determining unit 503 determines that sweat pores exist in the target fingerprint line.
And a searching unit 506, configured to search sweat pores in the target fingerprint pattern along the pattern direction.
The determining unit 503 is further configured to determine whether the number of sweat pores in the target fingerprint texture exceeds a preset number threshold, if the number exceeds the preset number threshold, trigger the second determining unit 504 to determine that the fingerprint of the target object is a fingerprint living body, and if the number does not exceed the preset number threshold, trigger the second determining unit 504 to determine that the fingerprint of the target object is a fingerprint prosthesis.
The preset number threshold may be 5, 7, or 10, and the embodiment of the present invention is not limited. The first determining unit 502 may specifically determine the grain direction of the target fingerprint grain as follows: acquiring a gray-scale image of a target fingerprint grain section, and determining characteristic information of the gray-scale image; judging whether the characteristic information is matched with preset characteristic information or not; and if the characteristic information is matched with the preset characteristic information, determining the direction of the normal of the straight line of the tangent plane in the target fingerprint grain as the grain direction of the target fingerprint grain.
As another possible implementation, the obtaining unit 505 is further configured to obtain the distance between any two adjacent sweat pores when the determining unit 503 determines that the number exceeds the preset number threshold.
The determining unit 503 is further configured to determine whether the distance is within a preset distance range, trigger the second determining unit 504 to determine that the fingerprint of the target object is a fingerprint living body if the distance is within the preset distance range, and trigger the second determining unit 504 to determine that the fingerprint of the target object is a fingerprint prosthesis if the distance is not within the preset distance range.
The preset distance range may be 150um to 350um, and the sweat gland hole distance of the general person is taken as a reference in the embodiment of the present invention, but the preset distance range is not limited in the embodiment of the present invention.
It can be seen that in the fingerprint recognition device described in fig. 5 and 6, the fingerprint recognition device can recognize sweat pores in the fingerprint image and recognize the authenticity of the fingerprint according to the presence or absence of sweat pores in the fingerprint image. Furthermore, the embodiment of the invention increases the judgment on the width of the fingerprint lines, the number of sweat gland holes, the distance between sweat gland holes and the like, and can reduce the error of the judgment of true and false fingerprints, thereby improving the accuracy and the safety of fingerprint identification.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a fingerprint identification device according to an embodiment of the present invention. Among them, the fingerprint recognition device 700 shown in fig. 7 may include: one or more processors 701, one or more input devices 702, one or more output devices 703, and memory 704. The processor 701, the input device 702, the output device 703, and the memory are connected by a bus 705. The memory 705 is used for storing instructions and the processor 701 executes the instructions stored in the memory 702 in a language. Wherein:
an input device 702 is used to capture a fingerprint image for a target object.
The processor 701 is configured to determine a target fingerprint pattern from the fingerprint image, determine whether sweat pores exist in the target fingerprint pattern, determine that the fingerprint of the target object is a fingerprint living body if sweat pores exist in the target fingerprint pattern, and determine that the fingerprint of the target object is a fingerprint prosthesis if sweat pores do not exist in the target fingerprint pattern.
Wherein, the target fingerprint line is any line in the fingerprint image.
As a possible implementation manner, the specific way for the processor 701 to determine whether sweat pores exist in the target fingerprint texture may be:
acquiring a gray-scale image of a target fingerprint grain section, and determining characteristic information of the gray-scale image;
judging whether the characteristic information is matched with preset characteristic information or not;
if the characteristic information is matched with preset characteristic information, detecting whether a target characteristic point exists in the gray-scale image or not according to the characteristic information;
and if the target characteristic point exists, determining the target characteristic point as a sweat pore.
The characteristic information may refer to a trend of a connection line between gray scale values, such as forming a horizontal straight line, forming a curve (such as the gray scale graph shown in fig. 3) like a "valley" or a "peak", forming a wavy line, or forming an inclined or vertical straight line, and the like, which is not limited in the embodiment of the present invention. The preset characteristic information may be that a connection line between the gray-scale values is a curve like a valley or a peak.
As another possible implementation manner, the processor 701 is further configured to obtain a line width of the target fingerprint line, determine whether the line width is within a preset width range, determine that the fingerprint of the target object is a fingerprint prosthesis if the line width is not within the preset width range, and further determine whether sweat pores exist in the target fingerprint line if the line width is within the preset width range.
The preset width range may be 400um to 600um, and the embodiment of the present invention is not limited.
As another possible implementation, the processor 701 is further configured to determine a line direction of the target fingerprint line when sweat pores exist in the target fingerprint line, search sweat pores in the target fingerprint line along the line direction, determine whether the number of sweat pores in the target fingerprint line exceeds a preset number threshold, determine that the fingerprint of the target object is a live fingerprint if the number exceeds the preset number threshold, and determine that the fingerprint of the target object is a fingerprint prosthesis if the number does not exceed the preset number threshold.
The preset number threshold may be 5, 7, or 10, and the embodiment of the present invention is not limited. The processor 701 may specifically determine the grain direction of the target fingerprint grain as: acquiring a gray-scale image of a target fingerprint grain section, and determining characteristic information of the gray-scale image; judging whether the characteristic information is matched with preset characteristic information or not; and if the characteristic information is matched with the preset characteristic information, determining the direction of the normal of the straight line of the tangent plane in the target fingerprint grain as the grain direction of the target fingerprint grain.
As another possible implementation, the processor 701 is further configured to, when the number exceeds a preset number threshold, obtain a distance between any two adjacent sweat pores, and determine whether the distance is within a preset distance range, determine that the fingerprint of the target object is a living fingerprint if the distance is within the preset distance range, and determine that the fingerprint of the target object is a fingerprint prosthesis if the distance is not within the preset distance range.
The preset distance range may be 150um to 350um, and the sweat gland hole distance of the general person is taken as a reference in the embodiment of the present invention, but the preset distance range is not limited in the embodiment of the present invention.
It can be seen that in the fingerprint identification apparatus described in fig. 7, the fingerprint identification apparatus can identify sweat pores in the fingerprint image and identify the authenticity of the fingerprint according to whether sweat pores exist in the fingerprint image. Furthermore, the embodiment of the invention increases the judgment on the width of the fingerprint lines, the number of sweat gland holes, the distance between sweat gland holes and the like, and can reduce the error of the judgment of true and false fingerprints, thereby improving the accuracy and the safety of fingerprint identification.
It should be understood that, in the embodiment of the present invention, the Processor 701 may be a Central Processing Unit (CPU), and the Processor may also be other general processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input devices 702 may include a touch pad, a fingerprint sensor (for capturing a fingerprint), a microphone, etc., and the output devices 703 may include a display (LCD, etc.), a speaker, etc.
The memory 704 may include both read-only memory and random-access memory, and provides instructions and data to the processor 701. A portion of the memory 704 may also include non-volatile random access memory. For example, the memory 704 may also store device type information.
In a specific implementation, the processor 701, the input device 702, and the output device 703, which are described in the embodiment of the present invention, may execute the implementation manners described in the first embodiment and the second embodiment of the fingerprint identification method disclosed in the embodiment of the present invention, and may also execute the implementation manner of the fingerprint identification apparatus described in the embodiment of the present invention, which is not described herein again.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (8)
1. A fingerprint identification method, comprising:
acquiring a fingerprint image aiming at a target object, and determining target fingerprint lines from the fingerprint image;
judging whether sweat gland holes exist in the target fingerprint lines or not;
if the sweat pore exists, determining that the fingerprint of the target object is a fingerprint living body;
if the sweat pore does not exist, determining that the fingerprint of the target object is a fingerprint prosthesis;
after the acquiring a fingerprint image for a target object and determining a target fingerprint texture from the fingerprint image, the method further comprises:
acquiring the line width of the target fingerprint line;
and judging whether the line width is within a preset width range, and if so, executing the operation of judging whether sweat gland holes exist in the target fingerprint line.
2. The method of claim 1, wherein the determining whether sweat pores are present in the target fingerprint ridge comprises:
acquiring a gray-scale image of the target fingerprint grain section, and determining the characteristic information of the gray-scale image;
judging whether the characteristic information is matched with preset characteristic information or not;
and if the characteristic information is matched with the preset characteristic information, searching a target characteristic point in the gray-scale image according to the characteristic information, and determining the target characteristic point as a sweat gland hole.
3. The method of claim 2, further comprising:
if the sweat pore exists, determining the texture direction of the target fingerprint texture;
finding sweat pores in the target fingerprint grain along the grain direction;
judging whether the number of sweat gland holes in the target fingerprint lines exceeds a preset number threshold value or not;
if the number exceeds the preset number threshold, determining that the fingerprint of the target object is a fingerprint living body;
and if the number does not exceed the preset number threshold, determining the fingerprint of the target object as a fingerprint prosthesis.
4. The method of claim 3, further comprising:
if the number exceeds the preset number threshold, acquiring the distance between any two adjacent sweat gland holes;
judging whether the distance is within a preset distance range or not;
if the distance is within the preset distance range, determining the fingerprint of the target object as a fingerprint living body;
and if the distance is not within the preset distance range, determining the fingerprint of the target object as a fingerprint prosthesis.
5. A fingerprint recognition device, comprising:
an acquisition unit for acquiring a fingerprint image for a target object;
a first determination unit for determining a target fingerprint pattern from the fingerprint image;
the judging unit is used for judging whether sweat pores exist in the target fingerprint lines or not;
the second determining unit is used for determining the fingerprint of the target object as a fingerprint living body when the judging unit judges that the target fingerprint lines have the sweat pores;
the second determining unit is further configured to determine that the fingerprint of the target object is a fingerprint prosthesis when the determining unit determines that the target fingerprint pattern does not have the sweat pore;
the device further comprises:
the first acquisition unit is used for acquiring the line width of the target fingerprint line;
the judging unit is further configured to judge whether the line width is within a preset width range, and if so, execute the operation of judging whether sweat pores exist in the target fingerprint line.
6. The apparatus of claim 5, wherein the determining unit determines whether sweat pores exist in the target fingerprint texture by:
acquiring a gray-scale image of the target fingerprint grain section, and determining the characteristic information of the gray-scale image;
judging whether the characteristic information is matched with preset characteristic information or not;
and if the characteristic information is matched with the preset characteristic information, searching a target characteristic point in the gray-scale image according to the characteristic information, and determining the target characteristic point as a sweat gland hole.
7. The apparatus of claim 6,
the first determining unit is further configured to determine a line direction of the target fingerprint line when the judging unit judges that the target fingerprint line has the sweat pore;
the device further comprises:
the searching unit is used for searching sweat gland holes in the target fingerprint grains along the grain direction;
the judging unit is also used for judging whether the number of sweat gland holes in the target fingerprint lines exceeds a preset number threshold value;
the second determining unit is further configured to determine that the fingerprint of the target object is a fingerprint living body when the judging unit judges that the number exceeds the preset number threshold;
the second determining unit is further configured to determine that the fingerprint of the target object is a fingerprint prosthesis when the determining unit determines that the number does not exceed the preset number threshold.
8. The apparatus of claim 7, further comprising:
the second obtaining unit is used for obtaining the distance between any two adjacent sweat gland holes when the judging unit judges that the number exceeds the preset number threshold;
the judging unit is also used for judging whether the distance is within a preset distance range;
the second determining unit is further configured to determine that the fingerprint of the target object is a fingerprint living body when the determining unit determines that the distance is within the preset distance range;
the second determining unit is further configured to determine that the fingerprint of the target object is a fingerprint prosthesis when the determining unit determines that the distance is not within the preset distance range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610846389.0A CN106250890B (en) | 2016-09-23 | 2016-09-23 | Fingerprint identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610846389.0A CN106250890B (en) | 2016-09-23 | 2016-09-23 | Fingerprint identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106250890A CN106250890A (en) | 2016-12-21 |
| CN106250890B true CN106250890B (en) | 2020-05-05 |
Family
ID=57611580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610846389.0A Expired - Fee Related CN106250890B (en) | 2016-09-23 | 2016-09-23 | Fingerprint identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106250890B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107145866A (en) * | 2017-05-09 | 2017-09-08 | 北京小米移动软件有限公司 | Fingerprint detection method and device |
| CN109840458A (en) * | 2017-11-29 | 2019-06-04 | 杭州海康威视数字技术股份有限公司 | A kind of fingerprint identification method and fingerprint collecting equipment |
| CN108683968A (en) * | 2018-04-23 | 2018-10-19 | Oppo广东移动通信有限公司 | Display control method and related product |
| CN113496192A (en) * | 2020-04-08 | 2021-10-12 | 杭州萤石软件有限公司 | Fingerprint image identification method, device and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103294987A (en) * | 2012-03-05 | 2013-09-11 | 天津华威智信科技发展有限公司 | Fingerprint matching method and fingerprint matching implementation mode |
| CN104751139A (en) * | 2015-03-31 | 2015-07-01 | 上海大学 | Fast fingerprint recognition method based on feature points of sweat glands and fingerprint images |
| CN105426877A (en) * | 2015-12-22 | 2016-03-23 | 金虎林 | Method and system for information recognition applying sweat gland position information |
| CN105740750A (en) * | 2014-12-11 | 2016-07-06 | 深圳印象认知技术有限公司 | Fingerprint in-vivo detection and identification method and apparatus |
-
2016
- 2016-09-23 CN CN201610846389.0A patent/CN106250890B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103294987A (en) * | 2012-03-05 | 2013-09-11 | 天津华威智信科技发展有限公司 | Fingerprint matching method and fingerprint matching implementation mode |
| CN105740750A (en) * | 2014-12-11 | 2016-07-06 | 深圳印象认知技术有限公司 | Fingerprint in-vivo detection and identification method and apparatus |
| CN104751139A (en) * | 2015-03-31 | 2015-07-01 | 上海大学 | Fast fingerprint recognition method based on feature points of sweat glands and fingerprint images |
| CN105426877A (en) * | 2015-12-22 | 2016-03-23 | 金虎林 | Method and system for information recognition applying sweat gland position information |
Non-Patent Citations (1)
| Title |
|---|
| 《基于小波图像增强的指纹汗腺提取》;冯美仙;《万方数据知识服务平台》;20091230;第四章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106250890A (en) | 2016-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109326058B (en) | Identity verification method and device based on intelligent teller machine, terminal and readable medium | |
| US9934371B2 (en) | Fingerprint recognition method and electronic device performing thereof | |
| EP2199945B1 (en) | Biometric authentication device and method, computer-readable recording medium recorded with biometric authentication computer program, and computer system | |
| US8270726B2 (en) | Authentication apparatus | |
| US7151846B1 (en) | Apparatus and method for matching fingerprint | |
| CN106250890B (en) | Fingerprint identification method and device | |
| US20120057011A1 (en) | Finger vein recognition system and method | |
| KR100940902B1 (en) | The biometrics using finger geometry information | |
| KR101584045B1 (en) | Segment-based manual signature authentication system and method thereof | |
| Hemalatha | A systematic review on Fingerprint based Biometric Authentication System | |
| EP2360619A1 (en) | Fast fingerprint searching method and fast fingerprint searching system | |
| WO2011030675A1 (en) | Biometric authentication system, method and program | |
| US20160147825A1 (en) | Method and electronic device for updating the registered fingerprint datasets of fingerprint recognition | |
| Beton et al. | Biometric secret path for mobile user authentication: A preliminary study | |
| EP1713032B1 (en) | Pattern identifying system, pattern identifying method, and pattern identifying program | |
| US9836662B2 (en) | Authentication device, authentication method and program storage medium | |
| KR101972800B1 (en) | Method and apparatus for authenticating handwritten signature | |
| US11893825B2 (en) | Method for determining a match between a candidate fingerprint and a reference fingerprint | |
| Jeyanthi et al. | Neural network based automatic fingerprint recognition system for overlapped latent images | |
| US9613252B1 (en) | Fingerprint matching method and device | |
| US20230070660A1 (en) | Authentication method, non-transitory computer-readable storage medium for storing authentication program, and information processing device | |
| JP7305183B2 (en) | PEN INPUT PERSONAL AUTHENTICATION METHOD, PROGRAM FOR EXERCISEING PEN INPUT PERSONAL AUTHENTICATION METHOD ON COMPUTER, AND COMPUTER-READABLE STORAGE MEDIUM | |
| CN111832533B (en) | Authentication method, authentication device, authentication system, electronic equipment and readable storage medium | |
| CN110850419B (en) | Handwriting signature recognition method based on acoustics | |
| KR20050014406A (en) | System And Method For Identifying Fingerprint In Mobile Communication Terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 330096 No.699 Tianxiang North Avenue, Nanchang hi tech Industrial Development Zone, Nanchang City, Jiangxi Province Patentee after: Jiangxi OMS Microelectronics Co.,Ltd. Address before: 330000 east of Xueyuan 6th Road, south of Tianxiang Avenue, Nanchang hi tech Industrial Development Zone, Nanchang City, Jiangxi Province Patentee before: OFilm Microelectronics Technology Co.,Ltd. Address after: 330000 east of Xueyuan 6th Road, south of Tianxiang Avenue, Nanchang hi tech Industrial Development Zone, Nanchang City, Jiangxi Province Patentee after: OFilm Microelectronics Technology Co.,Ltd. Address before: 330029 No. 1189 Jingdong Avenue, Nanchang high tech Zone, Jiangxi Patentee before: NANCHANG OFILM BIO-IDENTIFICATION TECHNOLOGY Co.,Ltd. |
|
| CP03 | Change of name, title or address | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200505 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |