CN115063834A - Palm vein and palm artery based identity recognition method, device and system - Google Patents
Palm vein and palm artery based identity recognition method, device and system Download PDFInfo
- Publication number
- CN115063834A CN115063834A CN202210591650.2A CN202210591650A CN115063834A CN 115063834 A CN115063834 A CN 115063834A CN 202210591650 A CN202210591650 A CN 202210591650A CN 115063834 A CN115063834 A CN 115063834A
- Authority
- CN
- China
- Prior art keywords
- palm
- image
- artery
- vein
- value
- 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.)
- Pending
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
- G06V40/107—Static hand or arm
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- 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
- G06V40/14—Vascular patterns
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Library & Information Science (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Vascular Medicine (AREA)
- General Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to the field of identity recognition, and provides a palm vein and palm artery based identity recognition method, a device and a system, wherein the device comprises the following steps: acquiring a palm image and a back image of a person to be identified; judging whether the palm image and the back image are qualified or not; respectively processing the palm image and the back-hand image through a palm model library and a back-hand model library to obtain a palm key area image and a back-hand key area image; respectively carrying out binarization processing on the palm key area image and the back key area image to obtain a palm binarization picture and a back binarization picture; respectively judging the quality of the palm binary image and the quality of the hand back binary image through a palm vein model library and a palm artery model library to determine whether to extract a palm vein characteristic value and a palm artery characteristic value; according to the technical scheme, the accuracy of identity recognition is improved.
Description
Technical Field
The invention relates to the field of identity recognition, in particular to an identity recognition method, device and system based on a palm vein and a palm artery.
Background
Vein identification is a new biological characteristic identification technology, and vein veins can not be copied and people are different, so compared with other biological characteristic identification technologies, such as fingerprint identification, facial identification and the like, vein identification is not easy to imitate and the identification security is higher.
The existing vein recognition technology is generally finger veins, the finger veins are recognized as processing to obtain finger vein characteristic values of a person to be recognized, the finger vein characteristic values are compared with finger vein characteristic values stored in a database to determine identity characteristics of the person to be recognized, however, the number of veins in fingers is small, and further, extracted vein characteristic values are few, so that recognition accuracy is low.
Disclosure of Invention
The invention solves the problem of how to improve the accuracy of vein identification.
In a first aspect, the present invention provides an identification method based on a palm vein and a palm artery, including:
acquiring a palm image and a back image of a person to be identified;
judging whether the palm image and the back image are qualified or not;
respectively processing the palm image and the back hand image through a palm model library and a back hand model library to obtain a palm key area image and a back hand key area image;
respectively carrying out binarization processing on the palm key area image and the back key area image to obtain a palm binarization picture and a back binarization picture;
respectively judging the quality of the palm binary image and the quality of the hand back binary image through a palm vein model library and a palm artery model library to determine whether to extract a palm vein characteristic value and a palm artery characteristic value;
and comparing the palm vein characteristic value and the palm artery characteristic value with a total characteristic value acquired during user registration in a database, and judging whether the palm vein characteristic value and the palm artery characteristic value are the same person or not according to a comparison result.
Optionally, the palm image is a palm near-infrared image, the back of the hand image is a back of the hand near-infrared image, and the palm near-infrared image and the back of the hand near-infrared image are obtained by irradiating the palm and the back of the hand respectively with infrared rays emitted by corresponding infrared sensors.
Optionally, the determining whether the palm image and the back image are qualified includes:
firstly, judging whether the acquired palm image and the acquired hand back image are clear or not;
if so, comparing the palm image and the back image with a palm reference model and a back reference model in a palm model library and a back model library respectively to distinguish the left hand from the right hand and judge whether the left hand is the palm or the back of the hand,
if yes, executing the next step; and if not, re-acquiring the palm image and the back image of the person to be identified.
Optionally, the palm key area image and the back key area image are a palm-to-finger connection point area and a back-to-finger connection point area, respectively.
Optionally, the respectively performing binarization processing on the palm key region image and the back key region image to obtain a palm binarization picture and a back binarization picture includes:
adjusting the gray values of the palm veins and other palm parts of the palm key area image to obtain a palm binary image, and adjusting the gray values of the palm arteries and other palm parts of the back key area image to obtain a back binary image;
and marking the size and position information of the palm binarization picture and the back binarization picture.
Optionally, the determining, by the palm vein model library and the palm artery model library, the quality of the palm binarized picture and the quality of the back binarized picture respectively to determine whether to extract the palm vein feature value and the palm artery feature value includes:
processing the palm binary image through the palm vein model library to obtain a palm vein integrity value; processing the hand back binary image through the palm artery model library to obtain a palm artery integrity value;
judging whether the palm vein integrity value and the palm artery integrity value are lower than a set threshold value or not, if so, re-acquiring the palm image and the back image of the person to be identified; if not, extracting the palm vein characteristic value and the palm artery characteristic value.
Optionally, the palm vein feature value is a proportional relationship and a proportional distance value between a line position point of the palm vein and a corresponding line; the palm artery characteristic value is a proportional relation and a proportional distance value between the line position points of the palm artery and the corresponding lines.
Optionally, the total feature value refers to a set of the palm vein feature reference value and the palm artery feature reference value obtained in the database during user registration, comparing the palm vein feature value and the palm artery feature value with the total feature value collected in the database during user registration, and determining whether the two are the same person according to a comparison result includes:
randomly capturing a plurality of palm vein characteristic reference values and palm artery characteristic reference values from the database, and respectively comparing the palm vein characteristic reference values and the palm artery characteristic values with the palm vein characteristic values and the palm artery characteristic values of a person to be identified;
and if the similarity reaches a set threshold value, judging the same person, and if the acquaintance does not reach the set threshold value, continuously capturing a plurality of the palm vein characteristic reference values and the palm artery characteristic reference values in the database until the capturing is finished.
Compared with the prior art, the method has the advantages that firstly, the palm image and the back image of a person to be identified are obtained, then whether the palm image and the back image are qualified is judged, if so, the palm image and the back image are respectively processed through the palm model library and the back model library to obtain a palm key area image and a back key area image, then the palm key area image and the back key area image are subjected to binarization processing to obtain a palm binarization picture and a back binarization picture, the palm binarization picture and the back binarization picture are input into the palm vein model library and the palm artery model library for quality judgment to determine whether a palm vein characteristic value and a palm artery characteristic value are extracted, and after the palm vein characteristic value and the palm artery characteristic value are extracted, the palm vein characteristic value and the palm artery characteristic value are compared with a total characteristic value collected during user registration in the database, and according to the comparison result, whether the palm vein and the palm artery are distributed on the palm of the same person is judged, and the palm vein characteristic value and the palm artery characteristic value obtained by processing are more, so that the comparison accuracy can be improved in the comparison process, the palm vein characteristic value and the palm vein characteristic value are compared at the same time, and the comparison accuracy is further improved.
In a second aspect, the present invention further provides a palm vein and palm artery-based identity recognition apparatus, including:
the acquisition module is used for acquiring a palm image and a back image of a person to be identified;
the control module is used for judging whether the palm image and the back hand image are qualified or not; the palm model library and the back model library are used for respectively processing the palm image and the back image so as to obtain a palm key area image and a back key area image; the palm key area image and the back key area image are respectively subjected to binarization processing to obtain a palm binarization picture and a back binarization picture; the palm vein model library and the palm artery model library are used for respectively judging the quality of the palm binary image and the quality of the back binary image so as to determine whether to extract a palm vein characteristic value and a palm artery characteristic value; and the palm vein characteristic value and the palm artery characteristic value are compared with a total characteristic value collected during user registration in a database, and whether the user is the same person is judged according to a comparison result.
The palm vein and palm artery-based identity recognition device and the palm vein and palm artery-based identity recognition method have the same beneficial effects, and are not repeated herein
In a third aspect, the invention further provides an identification system based on the palm vein and the palm artery, which comprises an infrared collector and an industrial personal computer and is used for realizing the identification method based on the palm vein and the palm artery.
The palm vein and palm artery-based identity recognition system has the same beneficial effects as the palm vein and palm artery-based identity recognition method, and is not repeated herein.
Drawings
FIG. 1 is a schematic diagram illustrating an embodiment of a method for identity-based authentication;
fig. 2 is a schematic flow chart of an identity-based identification method in an embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below.
It is noted that the terms first, second and the like in the description and in the claims, as well as in the drawings, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; may be a mechanical connection; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In the description herein, references to the terms "an embodiment," "one embodiment," and "one implementation," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or implementation is included in at least one embodiment or example implementation of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or implementation. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or implementations.
The present invention will be described in detail with reference to the accompanying drawings.
In order to solve the above technical problem, with reference to fig. 1, an embodiment of the present invention provides an identification method based on a palm vein and a palm artery, including:
step S1, acquiring a palm image and a back image of the person to be recognized;
step S2, judging whether the palm image and the back hand image are qualified;
step S3, processing the palm image and the back-hand image respectively through a palm model library and a back-hand model library to obtain a palm key area image and a back-hand key area image;
step S4, performing binarization processing on the palm key area image and the back key area image respectively to obtain a palm binarization picture and a back binarization picture;
step S5, respectively judging the quality of the palm binary image and the quality of the back binary image through a palm vein model library and a palm artery model library to determine whether to extract a palm vein characteristic value and a palm artery characteristic value;
and step S6, comparing the palm vein characteristic value and the palm artery characteristic value with a total characteristic value collected during user registration in a database, and judging whether the user is the same person or not according to a comparison result.
In step S1, the person to be recognized needs to select one hand, remove obstacles on the hand, such as gloves, and then unfold the palm to acquire an image of the palm portion of the person to be recognized as the palm image, and turn over the palm image to acquire an image of the back of the hand to acquire the back of the hand of the person to be recognized as the back of the hand image after the palm image is acquired, or acquire the back of the hand image first and then acquire the palm image;
in step S2, if the recognition action of the person to be recognized is not standardized, or the palm image and the back-of-hand image are easily blurred due to the influence of a foreign object, or other situations that are not the palm and the back of the hand occur, and the subsequent steps are influenced, it is necessary to determine whether the palm image and the back-of-hand image are qualified;
in step S3, the palm image and the back-of-hand image are respectively input into the palm model library and the back-of-hand model library, and the palm model library and the back-of-hand model library respectively process the palm image and the back-of-hand image to obtain a palm key area image and a back-of-hand key area image, which includes the following steps: the palm model library selects a central point of a palm displayed on the palm image, cuts the palm image according to the central point to obtain the palm key area image, and similarly cuts the back image by the back model library to obtain the palm key area image.
In step S4, since the machine recognition image is limited, a colorful image becomes an object that is not easily recognized, the palm key region image and the back key region image are represented by images with different gray values, and the palm vein and the palm artery therein cannot be recognized, so that the palm key region image and the back key region image need to be binarized to obtain a palm binarized image and a back binarized image, and the processed palm binarized image and back binarized image are respectively displayed as a linear image of the palm vein and a linear image of the palm artery.
In step S5, after the palm binarization image and the back-of-the-hand binarization image are obtained, the palm vein feature value and the palm artery feature value therein need to be extracted respectively, and it is first necessary to determine the quality of the obtained palm binarization image and the back-of-the-hand binarization image, so as to prevent the extracted palm vein feature value and the extracted back-of-the-hand binarization image from being incomplete and affecting subsequent comparison.
In step S6, the palm vein feature value and the palm artery feature value are extracted and then compared with a total feature value already stored in the database, the total feature value is acquired when the user registers, whether the person to be identified is the registered user in the database is determined according to the comparison result, and the identity of the person to be identified is determined.
To sum up, palm vein palm distributes more, and the palm vein eigenvalue that the processing obtained is also many, consequently at the in-process of comparing, can improve the degree of accuracy of comparing, and the further simultaneous comparison of palm vein eigenvalue and palm artery eigenvalue can further improve the degree of accuracy of comparing, and a large amount of the comparison of palm vein eigenvalue with palm artery eigenvalue also can the quick discernment wait to detect people's identity information, has improved the efficiency of discernment.
In an embodiment of the present invention, the palm image is a palm near-infrared image, the back-of-hand image is a back-of-hand near-infrared image, and the palm near-infrared image and the back-of-hand near-infrared image are obtained by respectively irradiating the palm and the back of the hand with infrared rays emitted by corresponding infrared sensors.
It should be noted that the palm and the back of the hand are flatly placed at the infrared emission position of the infrared sensor, the infrared rays irradiate the palm and the back of the hand, the palm vein of the palm and the palm artery of the back of the hand contain red cell hemoglobin, and the red cell hemoglobin of the palm vein and the palm artery respectively absorb the infrared rays with relative wavelengths so that the palm vein and the palm artery area are dark areas, therefore, the palm image includes a bright area of the palm part and a dark area of the palm vein, and the back of the hand image includes a bright area of the back of the hand part and a dark area of the palm artery.
In an embodiment of the present invention, the determining whether the palm image and the back hand image are qualified includes:
firstly, judging whether the acquired palm image and the acquired hand back image are clear or not;
if so, comparing the palm image and the back image with a palm reference model and a back reference model in a palm model library and a back model library respectively to distinguish the left hand from the right hand and judge whether the left hand is the palm or the back of the hand,
if yes, executing the next step; and if not, re-acquiring the palm image and the back image of the person to be identified.
It should be noted that, the following method can be selected to determine whether the image of the palm and the image of the back of the hand are clear: calculating the Laplace variance of each image, and then performing local normalization to obtain normalized variances, wherein if the normalized variances are smaller than a set threshold value, the normalized variances can be judged to be unclear palm images and back hand images; if the palm image and the back-hand image are judged to be unclear, re-acquiring the palm image and the back-hand image of the person to be recognized; inputting the palm image and the back image into the palm model library and the back model library, comparing the palm image and the back image with a palm reference model and a back reference model in the palm model library and the back model library respectively, distinguishing a left hand and a right hand, judging whether the collected palm image and the collected back image are the palm and the back, and if so, executing the next step; if not, acquiring the palm image and the back image of the person to be identified again; through judging whether the palm image and the back of the hand image are qualified or not so as to take clear palm and back of the hand image of the person to be identified and distinguish the left hand from the right hand, so that the left hand and the right hand of the person to be identified can be collected.
In an embodiment of the invention, the palm key area image and the back key area image are a palm-to-finger connection point area and a back-to-finger connection point area, respectively.
It should be noted that the palm key area image is the palm to finger connection point area, the back of the hand key area image is the back of the hand to finger connection point area, the palm is the dense area of palm vein to finger connection point area, the back of the hand is the dense area of palm artery to finger connection point area, acquires the dense area of palm vein with the dense area of palm artery of the back of the hand can extract as much as possible the palm vein with the eigenvalue of palm artery increases the accuracy of comparison.
In an embodiment of the present invention, the respectively performing binarization processing on the palm key region image and the back key region image to obtain a palm binarized picture and a back binarized picture includes:
adjusting the gray values of the palm veins and other palm parts of the palm key area image to obtain a palm binary image, and adjusting the gray values of the palm arteries and other palm parts of the back key area image to obtain a back binary image;
and marking the size and position information of the palm binarization picture and the back binarization picture.
It should be noted that the acquired palm key area image and the back key area image are represented by images with different gray values, the images with different gray values cannot be identified and the palm veins and the palm arteries in the images can not be selected, so that binarization processing needs to be performed, a gray threshold value is set to be T, the palm key area image data is divided into two parts by using T, a pixel group larger than T is the palm veins, a pixel group smaller than T is the rest part of the palm, the gray value of the pixel group larger than T is set to be 255, the gray value of the pixel group smaller than T is set to be 0, namely the palm veins are displayed as a black linear image, the rest part of the palm is displayed as white, the palm binarization image is obtained, the back hand binarization image is obtained in the same way, and positioning patterns are arranged at three corners of the palm binarization image and the back hand binarization image, the position information and the size of the palm binarization picture and the back hand binarization picture are marked, so that the palm binarization picture and the back hand binarization picture can be identified no matter what angle is identified.
In an embodiment of the present invention, the determining, by respectively judging the quality of the palm binary image and the quality of the back binary image through a palm vein model library and a palm artery model library, whether to extract a palm vein characteristic value and a palm artery characteristic value includes:
processing the palm binary image through the palm vein model library to obtain a palm vein integrity value; processing the hand back binary image through the palm artery model library to obtain a palm artery integrity value;
judging whether the palm vein integrity value and the palm artery integrity value are lower than a set threshold value or not, if so, re-acquiring the palm image and the back image of the person to be identified; if not, extracting the palm vein characteristic value and the palm artery characteristic value.
The palm binary image is input into the palm vein model library, the palm vein model library identifies the palm veins, the distribution condition of the palm veins on the palm is detected to judge the integrity of the palm veins, the palm veins are digitized into a palm vein integrity value, the palm vein integrity value is compared with a set integrity threshold value, if the palm vein integrity value is smaller than the palm vein integrity value, the quality of the palm binary image is judged to be unqualified, and the palm image and the back image of the person to be identified are obtained again; if the palm vein integrity value is larger than or equal to the palm vein integrity value, judging that the quality of the palm binary image is qualified, and extracting to obtain a palm vein characteristic value; extracting and obtaining the palm artery characteristic value in the same way; and judging the quality of the palm binary image and the quality of the back binary image through the palm vein model library and the palm artery model library, and then extracting corresponding characteristic values, so that the quality of the extracted palm vein characteristic values and the quality of the palm artery characteristic values are ensured.
In one embodiment of the present invention, the palm vein feature value is a proportional relationship and a proportional distance value between a line position point of the palm vein and a corresponding line; the palm artery characteristic value is a proportional relation and a proportional distance value between the line position points of the palm artery and the corresponding lines.
It should be noted that the extracted palm vein feature value is a line position point of the palm vein and a proportional relation and a proportional distance value between corresponding lines, a linear pattern of the palm vein can be determined through the proportional relation and the proportional distance value between the line position point and the corresponding line, and the comparison is performed by using the proportional relation and the proportional distance value between the line position point and the corresponding line, so that the comparison result can be prevented from being influenced by other factors such as the size of the palm binary image, and the palm artery feature value is the same.
The total characteristic value refers to a set of the palm vein characteristic reference value and the palm artery characteristic reference value acquired in the database during user registration, the palm vein characteristic value and the palm artery characteristic value are compared with the total characteristic value acquired in the database during user registration, and whether the palm vein characteristic value and the palm artery characteristic value are the same person is judged according to a comparison result, wherein the step of:
randomly capturing a plurality of palm vein characteristic reference values and palm artery characteristic reference values from the database, and respectively comparing the palm vein characteristic reference values and the palm artery characteristic values with the palm vein characteristic values and the palm artery characteristic values of a person to be identified;
and if the similarity reaches a set threshold value, judging the same person, and if the acquaintance does not reach the set threshold value, continuously capturing a plurality of the palm vein characteristic reference values and the palm artery characteristic reference values in the database until the capturing is finished.
It should be noted that the step of registering the user is: and repeating the steps S1-S5, continuously selecting and processing to obtain a plurality of palm vein characteristic values and a plurality of palm artery characteristic values, and storing each palm vein characteristic value and each palm artery characteristic value into a database to form the palm vein characteristic reference value and the palm artery characteristic reference value so as to finish user registration. The palm vein characteristic value and the palm artery characteristic value can change along with the difference of blood flow rate, infrared ray angle and the like, and a plurality of characteristic values need to be collected for many times so as to facilitate the comparison of the characteristic values when a user identifies. And randomly grabbing a plurality of the palm vein characteristic reference values and the palm artery characteristic reference values from the database, comparing the palm vein characteristic reference values and the palm artery characteristic values with the palm vein characteristic values and the palm artery characteristic values of a person to be identified one by one, judging the same person if the compared similarity reaches a set threshold value, continuously grabbing the plurality of the palm vein characteristic reference values and the palm artery characteristic reference values from the database for comparison if the compared identification degree does not reach the set threshold value until the palm vein characteristic reference values and the palm artery characteristic reference values are grabbed completely, wherein the palm vein characteristic values are different from the characteristic codes of the palm artery characteristic values, so that the corresponding palm vein characteristic values and the palm artery characteristic values can be quickly grabbed from the database, and the comparison efficiency is improved.
In another embodiment of the present invention, a palm vein and palm artery based identification apparatus includes:
the acquisition module is used for acquiring a palm image and a back image of a person to be identified;
the control module is used for judging whether the palm image and the back hand image are qualified or not; the palm model library and the back of the hand model library are used for respectively processing the palm image and the back of the hand image so as to obtain a palm key area image and a back of the hand key area image; the palm key area image and the back key area image are respectively subjected to binarization processing to obtain a palm binarization picture and a back binarization picture; the palm vein model library and the palm artery model library are used for respectively judging the quality of the palm binary image and the quality of the back binary image so as to determine whether to extract a palm vein characteristic value and a palm artery characteristic value; and the palm vein characteristic value and the palm artery characteristic value are compared with a total characteristic value collected during user registration in a database, and whether the user is the same person is judged according to a comparison result.
In another embodiment of the present invention, an identification system based on a palm vein and a palm artery includes an infrared collector and an industrial personal computer, and is used for implementing the identification method based on the palm vein and the palm artery as described in the above embodiments.
It should be noted that the infrared collector is used for collecting the palm image and the back-of-hand image, and the industrial personal computer is used for controlling the control module and the acquisition module, so as to realize the identification method based on the palm vein and the palm artery.
The technical features mentioned above are combined with each other to form various embodiments which are not listed above, and all of them are regarded as the scope of the present invention described in the specification; also, modifications and variations may be suggested to those skilled in the art in light of the above teachings, and it is intended to cover all such modifications and variations as fall within the true spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. An identity recognition method based on a palm vein and a palm artery is characterized by comprising the following steps:
acquiring a palm image and a back image of a person to be identified;
judging whether the palm image and the back image are qualified or not;
respectively processing the palm image and the back hand image through a palm model library and a back hand model library to obtain a palm key area image and a back hand key area image;
respectively carrying out binarization processing on the palm key area image and the back key area image to obtain a palm binarization picture and a back binarization picture;
respectively judging the quality of the palm binary image and the quality of the back binary image through a palm vein model library and a palm artery model library to determine whether to extract a palm vein characteristic value and a palm artery characteristic value;
and comparing the palm vein characteristic value and the palm artery characteristic value with a total characteristic value acquired during user registration in a database, and judging whether the palm vein characteristic value and the palm artery characteristic value are the same person or not according to a comparison result.
2. The palm vein and palm artery based identity recognition method according to claim 1, wherein the palm image is a palm near-infrared image, the back image is a back near-infrared image, and the palm near-infrared image and the back near-infrared image are obtained by irradiating the palm and the back of the hand with infrared rays emitted by corresponding infrared sensors, respectively.
3. The palm vein and palm artery-based identity recognition method of claim 1, wherein the determining whether the palm image and the back-of-hand image are qualified comprises:
judging whether the acquired palm image and the acquired hand back image are clear or not;
if so, comparing the palm image and the back image with a palm reference model and a back reference model in a palm model library and a back model library respectively to distinguish the left hand from the right hand and judge whether the left hand is the palm or the back of the hand,
if yes, executing the next step; and if not, re-acquiring the palm image and the back image of the person to be identified.
4. The palm vein and palm artery-based identification method according to claim 1, wherein the palm key area image and the back key area image are a palm-to-finger connection point area and a back-to-finger connection point area, respectively.
5. The palm vein and palm artery-based identity recognition method according to claim 1, wherein the binarizing the palm key region image and the back key region image to obtain the palm binarized picture and the back binarized picture respectively comprises:
adjusting the gray values of the palm veins and other palm parts of the palm key area image to obtain a palm binary image, and adjusting the gray values of the palm arteries and other palm parts of the back key area image to obtain a back binary image;
and marking the size and position information of the palm binary image and the back binary image.
6. The palm vein and palm artery based identity recognition method according to claim 1, wherein the determining the quality of the palm binary image and the back binary image by the palm vein model library and the palm artery model library respectively to determine whether to extract the palm vein feature value and the palm artery feature value comprises:
processing the palm binary image through the palm vein model library to obtain a palm vein integrity value; processing the hand back binary image through the palm artery model library to obtain a palm artery integrity value;
judging whether the palm vein integrity value and the palm artery integrity value are lower than a set threshold value or not, if so, re-acquiring the palm image and the back image of the person to be identified; if not, extracting the palm vein characteristic value and the palm artery characteristic value.
7. The palm vein and palm artery-based identity recognition method according to claim 6, wherein the palm vein feature value is a proportional relationship and a proportional distance value between a line position point of the palm vein and a corresponding line; the palm artery characteristic value is a proportional relation and a proportional distance value between the line position points of the palm artery and the corresponding lines.
8. The palm vein and palm artery-based identity recognition method according to claim 1, wherein the total feature value is a set of the palm vein feature reference value and the palm artery feature reference value acquired in the database at the time of user registration, and the comparing of the palm vein feature value and the palm artery feature value with the total feature value acquired in the database at the time of user registration and the determining of whether the same person is the same person according to the comparison result comprises:
randomly capturing a plurality of palm vein characteristic reference values and palm artery characteristic reference values from the database, and respectively comparing the palm vein characteristic reference values and the palm artery characteristic values with the palm vein characteristic values and the palm artery characteristic values of a person to be identified;
and if the similarity reaches a set threshold value, judging the same person, and if the acquaintance does not reach the set threshold value, continuously capturing a plurality of the palm vein characteristic reference values and the palm artery characteristic reference values in the database until the capturing is finished.
9. An identification device based on palm vein and palm artery, characterized by comprising:
the acquisition module is used for acquiring a palm image and a back image of a person to be identified;
the control module is used for judging whether the palm image and the back image are qualified or not; the palm model library and the back model library are used for respectively processing the palm image and the back image so as to obtain a palm key area image and a back key area image; the palm key area image and the back key area image are respectively subjected to binarization processing to obtain a palm binarization picture and a back binarization picture; the palm vein model library and the palm artery model library are used for respectively judging the quality of the palm binary image and the quality of the back binary image so as to determine whether to extract a palm vein characteristic value and a palm artery characteristic value; and the palm vein characteristic value and the palm artery characteristic value are compared with a total characteristic value collected during user registration in a database, and whether the user is the same person is judged according to a comparison result.
10. An identification system based on palm vein and palm artery, which is characterized by comprising an infrared collector and an industrial personal computer and is used for realizing the identification method based on palm vein and palm artery as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210591650.2A CN115063834A (en) | 2022-05-27 | 2022-05-27 | Palm vein and palm artery based identity recognition method, device and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210591650.2A CN115063834A (en) | 2022-05-27 | 2022-05-27 | Palm vein and palm artery based identity recognition method, device and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115063834A true CN115063834A (en) | 2022-09-16 |
Family
ID=83199335
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210591650.2A Pending CN115063834A (en) | 2022-05-27 | 2022-05-27 | Palm vein and palm artery based identity recognition method, device and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115063834A (en) |
-
2022
- 2022-05-27 CN CN202210591650.2A patent/CN115063834A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mulyono et al. | A study of finger vein biometric for personal identification | |
| Verma et al. | Daughman’s algorithm method for iris recognition—a biometric approach | |
| KR101266422B1 (en) | Image processing apparatus, and method and program for creating mask | |
| CN107563364B (en) | Sweat gland-based fingerprint authenticity identification method and fingerprint identification method | |
| CN104809451B (en) | A kind of person's handwriting identification system based on stroke curvature measuring | |
| US20120020535A1 (en) | Unique, repeatable, and compact biometric identifier | |
| Sandhiya et al. | Extraction of dorsal palm basilic and cephalic hand vein features for human authentication system | |
| Devadoss et al. | Performance improvement using an automation system for recognition of multiple parametric features based on human footprint | |
| JP2017053699A (en) | Wavelength decision method of near-infrared image capturing used in substance determination, and substance determination method using near-infrared image | |
| Villariña et al. | Palm vein recognition system using directional coding and back-propagation neural network | |
| KR20080079798A (en) | Method of face detection and recognition | |
| Tazim et al. | Biometric authentication using CNN features of dorsal vein pattern extracted from NIR image | |
| CN115063834A (en) | Palm vein and palm artery based identity recognition method, device and system | |
| Munshi et al. | A rough-set based binarization technique for fingerprint images | |
| Kubanek et al. | Feature extraction of palm vein patterns based on two-dimensional density function | |
| Ibrahim | Iris recognition using Haar wavelet transform | |
| KR101767051B1 (en) | Method and apparatus for extracting finger vein image based on fuzzy inference | |
| Jin et al. | Fingerprint identification and recognition using backpropagation neural network | |
| Vishwakarma et al. | Biometric Iris Recognition using Sobel Edge Detection for Secured Authentication | |
| Vasquez et al. | Features extraction in images on finger veins with hybrid curves | |
| CN112801034A (en) | Finger vein recognition device | |
| WO2011068395A2 (en) | A method for identity recognition based on lip image | |
| Kaur et al. | Enhanced Iris Recognition System–an Integrated Approach to Person Identification | |
| Khokher et al. | Palmprint recognition using geometrical and texture properties | |
| CN111582014A (en) | Container identification method, device and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |