CN108288052B - Iris image normalization method and device and computer readable storage medium - Google Patents
Iris image normalization method and device and computer readable storage medium Download PDFInfo
- Publication number
- CN108288052B CN108288052B CN201810171295.7A CN201810171295A CN108288052B CN 108288052 B CN108288052 B CN 108288052B CN 201810171295 A CN201810171295 A CN 201810171295A CN 108288052 B CN108288052 B CN 108288052B
- Authority
- CN
- China
- Prior art keywords
- sampling
- iris image
- iris
- processed
- image
- 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.)
- Active
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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
Abstract
The invention discloses an iris image normalization method, an iris image normalization device and a computer readable storage medium, wherein the method comprises the following steps: acquiring an iris image to be processed, and determining the state type of the iris image to be processed; searching a corresponding sampling model according to the state type; and carrying out nonlinear sampling on the iris image to be processed according to the sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points. Because the influence of the pupil enlargement or the pupil reduction on the iris part is fully considered, the error caused by the pupil enlargement or the pupil reduction can be well reduced, the performance of the iris image normalization processing part is improved, and the accuracy of the subsequent iris part characteristic extraction and iris identification can be improved.
Description
Technical Field
The invention relates to the field of iris image processing, in particular to an iris image normalization method, an iris image normalization device and a computer readable storage medium.
Background
Nowadays, the era of the rapid development of informatization, and the concept of the internet is deeply embedded into our lives. How to accurately identify the true identity of an individual and protect information security becomes a critical problem to be solved urgently. The traditional identity authentication is easy to forge and lose, and is difficult to meet the social requirements of rapid development, and the most convenient and safe solution at present is biological identification. Iris recognition is an organism feature recognition technology based on human physiological features, and compared with the feature recognition of human textures, palm prints, facial complexion, audio frequency, step frequency, blood and the like, the iris recognition technology has the advantages of uniqueness, high stability, high recognition rate, convenience in detection and the like, so that the iris recognition technology becomes the popular field of current identity identification research.
Because the pupil of a person can change under different illumination, the area of the iris can also change, so that the iris characteristics are difficult to directly compare, and the detected iris image needs to be subjected to standardization treatment, namely, the annular iris area is mapped into a rectangular area with the length being angular resolution and the width being radial resolution through coordinate transformation, so that the rotational translation influence of the iris image due to external interference is reduced. The process is called normalization, and the normalization processing of the iris image is a very important link in the iris recognition system. The iris area is ring-like shaped and not conducive to feature extraction analysis. The purpose of iris normalization is to adjust each original image to the same size and corresponding position, thereby eliminating the effects of translation, scaling and rotation on iris recognition, and improving the efficiency of iris recognition.
In general, the centers of the inner and outer boundaries of the iris are not coincident but have a certain deviation, so that the annular regions formed by the inner and outer edges have different widths due to the deviation. The current iris normalization methods are all linear normalization, namely the iris is mapped to a rectangle with a fixed size from a ring shape in a linear mapping mode, and the current iris normalization methods comprise linear methods such as integral linear normalization and dual-spring model normalization. However, due to the change of the external illumination and the like, the pupil zooming can be caused, and the pupil zooming can cause the corresponding zooming change of the iris texture, and the zooming is uneven and non-linear. Therefore, the linear normalization method of iris texture is ineffective in eliminating such uneven scaling, thereby reducing the accuracy of subsequent iris recognition.
Disclosure of Invention
The invention mainly aims to provide an iris image normalization method, an iris image normalization device and a computer readable storage medium, and aims to solve the technical problem that iris image normalization processing cannot be accurately performed in the prior art.
In order to achieve the above object, the present invention provides an iris image normalization method, which comprises the following steps:
acquiring an iris image to be processed, and determining the state type of the iris image to be processed;
searching a corresponding sampling model according to the state type;
and carrying out nonlinear sampling on the iris image to be processed according to the sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
Preferably, the non-linear sampling of the iris image to be processed according to the sampling model to obtain sampling points, and the normalization of the iris image to be processed into a rectangular image according to the sampling points specifically include:
calculating preset parameters of the sampling model according to the sampling model and preset point coordinates to obtain a target sampling model;
and carrying out nonlinear sampling on the iris image to be processed according to the target sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
Preferably, the calculating preset parameters of the sampling model according to the sampling model and preset point coordinates to obtain a target sampling model specifically includes:
acquiring preset point coordinates, and converting the sampling model into an equation set containing preset parameters according to the preset point coordinates;
and assigning the preset parameters according to a preset rule, and when the current assignment enables the equation to be formed, taking the current assignment as the preset parameters to obtain the target sampling model.
Preferably, the non-linear sampling of the iris image to be processed according to the target sampling model to obtain sampling points, and the normalization of the iris image to be processed into a rectangular image according to the sampling points specifically include:
equally dividing the circumference of the iris image to be processed according to a first preset number of parts;
and carrying out nonlinear sampling on each boundary line according to the target sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
Preferably, the non-linear sampling is performed on each boundary line according to the target sampling model to obtain sampling points, and the iris image to be processed is normalized into a rectangular image according to the sampling points, which specifically includes:
determining the serial numbers of the sampling points according to a second preset number, normalizing the serial numbers of the sampling points, taking the normalized serial numbers of the sampling points as an abscissa, and calculating a corresponding ordinate according to the abscissa and the target sampling model;
and taking the product of the ordinate and the second preset number as the distance from the sampling point to the pupil edge, carrying out nonlinear sampling on each boundary line according to the distance from the sampling point to the pupil edge to obtain the sampling point, and normalizing the iris image to be processed into a rectangular image according to the sampling point.
Preferably, the determining the state type of the iris image to be processed specifically includes:
making a ray from the center of the pupil to the outside in the iris image to be processed, respectively obtaining intersection points of the ray, the iris edge and the pupil edge, and calculating the intersection point distance;
and comparing the intersection point distance with a preset distance, and determining the state type of the iris image to be processed according to the comparison result.
Preferably, the searching for the corresponding sampling model according to the state type specifically includes:
when the state type is iris compression, the sampling model is y ═ aebxA, wherein y is the ratio of the intersection point distance to the preset distance, and x is the pupil edge and the iris edgeThe distance after the normalization, a and b are preset parameters;
when the state type is iris dilation, the sampling model is y-aln (bx + 1).
Preferably, the acquiring an iris image to be processed specifically includes:
and acquiring a human eye image, carrying out iris positioning on the human eye image, and carrying out pupil removal processing on the positioned image to obtain the iris image to be processed.
In addition, to achieve the above object, the present invention provides an iris image normalization apparatus, including: the iris image normalization program is stored on the memory and can run on the processor, and when being executed by the processor, the iris image normalization program realizes the steps of the iris image normalization method.
In addition, to achieve the above object, the present invention further provides a computer readable storage medium having stored thereon an iris image normalization program, which when executed by a processor, implements the steps of the iris image normalization method as described above.
In the invention, the state type of the iris image to be processed is determined by acquiring the iris image to be processed; searching a corresponding sampling model according to the state type; and carrying out nonlinear sampling on the iris image to be processed according to the sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points. Because the influence of the pupil enlargement or the pupil reduction on the iris part is fully considered, the error caused by the pupil enlargement or the pupil reduction can be well reduced, the performance of the iris image normalization processing part is improved, and the accuracy of the subsequent iris part characteristic extraction and iris identification can be improved.
Drawings
FIG. 1 is a schematic diagram of an apparatus in a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a first embodiment of a method for normalizing an iris image according to the present invention;
FIG. 3 is a normalized expanded view of an iris image according to the present invention;
FIG. 4 is a flowchart illustrating a second embodiment of the iris image normalization method according to the present invention;
FIG. 5 is a distance graph of iris compression sampling points according to the present invention;
FIG. 6 is a graph of distance curves of iris dilation sampling points of the present invention;
FIG. 7 is a flowchart illustrating a third embodiment of a method for normalizing an iris image according to the present invention;
FIG. 8 is a graph of normalized processing of an iris image;
FIG. 9 is an iris localization diagram of the present invention;
fig. 10 is an iris image after pupil removal according to the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the apparatus may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may comprise a Display screen (Display), and the optional user interface 1003 may also comprise a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage server separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the apparatus, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, which is a kind of computer-readable storage medium, may include therein an operating system, a network communication module, a user interface module, and an iris image normalization program.
The server calls, through the processor 1001, the iris image normalization program stored in the memory 1005, and performs the following operations:
acquiring an iris image to be processed, and determining the state type of the iris image to be processed;
searching a corresponding sampling model according to the state type;
and carrying out nonlinear sampling on the iris image to be processed according to the sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
Further, the processor 1001 may call the iris image normalization program stored in the memory 1005, and further perform the following operations:
calculating preset parameters of the sampling model according to the sampling model and preset point coordinates to obtain a target sampling model;
and carrying out nonlinear sampling on the iris image to be processed according to the target sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
Further, the processor 1001 may call the iris image normalization program stored in the memory 1005, and further perform the following operations:
acquiring preset point coordinates, and converting the sampling model into an equation set containing preset parameters according to the preset point coordinates;
and assigning the preset parameters according to a preset rule, and when the current assignment enables the equation to be formed, taking the current assignment as the preset parameters to obtain the target sampling model.
Further, the processor 1001 may call the iris image normalization program stored in the memory 1005, and further perform the following operations:
equally dividing the circumference of the iris image to be processed according to a first preset number of parts;
and carrying out nonlinear sampling on each boundary line according to the target sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
Further, the processor 1001 may call the iris image normalization program stored in the memory 1005, and further perform the following operations:
determining the serial numbers of the sampling points according to a second preset number, normalizing the serial numbers of the sampling points, taking the normalized serial numbers of the sampling points as an abscissa, and calculating a corresponding ordinate according to the abscissa and the target sampling model;
and taking the product of the ordinate and the second preset number as the distance from the sampling point to the pupil edge, carrying out nonlinear sampling on each boundary line according to the distance from the sampling point to the pupil edge to obtain the sampling point, and normalizing the iris image to be processed into a rectangular image according to the sampling point.
Further, the processor 1001 may call the iris image normalization program stored in the memory 1005, and further perform the following operations:
making a ray from the center of the pupil to the outside in the iris image to be processed, respectively obtaining intersection points of the ray, the iris edge and the pupil edge, and calculating the intersection point distance;
and comparing the intersection point distance with a preset distance, and determining the state type of the iris image to be processed according to the comparison result.
Further, the processor 1001 may call the iris image normalization program stored in the memory 1005, and further perform the following operations:
when the state type is iris compression, the sampling model is y ═ aebxA, wherein y is the ratio of the intersection point distance to the preset distance, x is the normalized distance between the pupil edge and the iris edge, and a and b are preset parameters;
when the state type is iris dilation, the sampling model is y-aln (bx + 1).
Further, the processor 1001 may call the iris image normalization program stored in the memory 1005, and further perform the following operations:
and acquiring a human eye image, carrying out iris positioning on the human eye image, and carrying out pupil removal processing on the positioned image to obtain the iris image to be processed.
In the embodiment, the state type of the iris image to be processed is determined by acquiring the iris image to be processed; searching a corresponding sampling model according to the state type; and carrying out nonlinear sampling on the iris image to be processed according to the sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points. Because the influence of the pupil enlargement or the pupil reduction on the iris part is fully considered, the error caused by the pupil enlargement or the pupil reduction can be well reduced, the performance of the iris image normalization processing part is improved, and the accuracy of the subsequent iris part characteristic extraction and iris identification can be improved.
Based on the hardware structure, the embodiment of the iris image normalization method is provided.
Referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of the iris image normalization method of the present invention.
In a first embodiment, the iris image normalization method includes the steps of:
step S10: and acquiring an iris image to be processed, and determining the state type of the iris image to be processed.
It should be noted that the state types include iris compression and iris expansion, and in the iris image, because the near-pupil region of the iris has rich texture information and more sampling points when the pupil is expanded, and the far-pupil region of the iris has rich texture information and more sampling points when the pupil is compressed, the method of the present invention fully considers the influence of the expansion or compression of the pupil on the iris part, i.e., adopts a related mathematical model to correct the nonlinearity of the iris, thereby correcting the uneven scaling of the iris texture, and having accurate actual effect.
In the specific implementation, an iris image to be processed is obtained, a difference value between the radius of the iris and the radius of the pupil in a standard state is obtained when the pupil does not change, the state type of the iris image to be processed is determined by comparing the difference value between the radius of the iris and the radius of the pupil of the iris image to be processed with the difference value between the radius of the iris and the radius of the pupil in the standard state, when the difference value between the radius of the iris and the radius of the pupil of the iris image to be processed is greater than the difference value between the radius of the iris and the radius of the pupil in the standard state, the state type of the iris image to be processed is determined as iris expansion, and when the difference value between the radius of the iris and the radius of the pupil of the iris image to be processed is less than the difference value between the radius of the iris and the radius of the pupil.
Step S20: and searching a corresponding sampling model according to the state type.
It is to be understood that the sampling model refers to the sampling rule equation followed during sampling. Since the sampling points in the near pupil area are denser and the sampling points in the far pupil area are sparser in the case of pupil dilation (i.e., iris compression), the distance between each sampling point increases with the distance. In the case of pupil constriction (i.e., iris dilation), the iris is stretched, the near-pupil sampling points are sparse, and the sampling points are denser in the far-pupil region, i.e., the distance between each sampling point decreases as the distance increases. Therefore, for different state types, different sampling models are adopted, the uneven scaling of the iris texture can be corrected, and the actual effect is accurate.
Step S30: and carrying out nonlinear sampling on the iris image to be processed according to the sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
It should be noted that, for different states to which the iris image to be processed belongs, different sampling models are adopted for sampling to realize the correction of the nonlinear scaling of the iris texture, so that a corresponding sampling model is searched according to the state type, the sampling model is a nonlinear equation, the iris image to be processed is subjected to nonlinear sampling according to the sampling model to obtain sampling points, the iris image to be processed is normalized into a rectangular image according to the sampling points, as shown in fig. 3, and fig. 3 is an iris image normalization expansion diagram of the present invention.
In the embodiment, the state type of the iris image to be processed is determined by acquiring the iris image to be processed; searching a corresponding sampling model according to the state type; and carrying out nonlinear sampling on the iris image to be processed according to the sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points. Because the influence of the pupil enlargement or the pupil reduction on the iris part is fully considered, the error caused by the pupil enlargement or the pupil reduction can be well reduced, the performance of the iris image normalization processing part is improved, and the accuracy of the subsequent iris part characteristic extraction and iris identification can be improved.
Referring to fig. 4, fig. 4 is a schematic flowchart of a second embodiment of the iris image normalization method according to the present invention, and the second embodiment of the iris image normalization method according to the present invention is proposed based on the embodiment shown in fig. 2.
In the second embodiment, the step S30 specifically includes:
step S301: and calculating preset parameters of the sampling model according to the sampling model and preset point coordinates to obtain a target sampling model.
It should be noted that the preset point coordinates refer to coordinates of a point with a gradient of 1 in the sampling model; the sampling model is an unknown equation containing preset parameters, and the target sampling model is a known equation obtained by solving the preset parameters by the sampling model; and calculating preset parameters in the sampling model according to the sampling model and the preset point coordinates to obtain a target sampling model.
Step S302: and carrying out nonlinear sampling on the iris image to be processed according to the target sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
Further, step S301 specifically includes:
step S311: and acquiring a preset point coordinate, and converting the sampling model into an equation set containing preset parameters according to the preset point coordinate.
It should be noted that, according to the property that the gradient at the preset point is 1, the derivative function of the sampling model at the preset point is 1, the coordinates of the preset point are substituted into the sampling model to obtain two equations, and the two equations are derived to obtain an equation set containing preset parameters.
In a specific implementation, as shown in fig. 5, fig. 5 is a distance graph of sampling points in iris compression according to the present invention, and when the state type is iris compression, the sampling model is y ═ aebxA, preset point coordinates of (x)0，y0) From the gradient of 1 at the preset point, the following equation can be obtained:
the following derivation is carried out:
the solution to the above equation can be converted to the intersection of two curves, the equation for which is as follows:
in a specific implementation, as shown in fig. 6, fig. 6 is a distance graph of the iris expansion sampling points of the present invention, when the state type is iris expansion, the sampling model is y-aln (bx +1), and the preset point coordinate is (x)0，y0) From the gradient of 1 at the preset point, the following equation can be obtained:
the following derivation is carried out:
the solution to the above equation can be converted to the intersection of two curves, the equation for which is as follows:
step S312: and assigning the preset parameters according to a preset rule, and when the current assignment enables the equation to be formed, taking the current assignment as the preset parameters to obtain the target sampling model.
It can be understood that the preset rule is to take a constant every 0.001 interval with 0 as a starting point, assign the constant to a preset parameter, and calculate y in the curve equation set for each preset parameter in turn1And y2Value when y1And y2And when the difference value of the preset value is smaller than the preset value, determining that the equation set is established, taking the current assignment which enables the equation set to be established as the determined value of the preset parameter, and substituting the determined value of the preset parameter into the sampling model to obtain the target sampling model.
In a specific implementation, starting from 0, b is assigned a value of 0.001, y1＝1-0.001y0(y since the coordinates of the preset points are known0Is a known value), y2＝e0.001Calculating y1-y2When y is1-y2When the difference is smaller than a predetermined value, for example, the predetermined value is 0.0001, the current value is assigned to 0.001 as the determined value of the predetermined parameter b, and when y is smaller than the predetermined value1-y2When the difference is greater than the preset value, the current assignment is increased by 0.001, and y is calculated again1-y2Until y is different from1-y2Is less than the preset value, the current assignment is 0.001 as the determined value of the preset parameter b, and the current assignment is substituted into the sampling model to obtain the target sampling model, in this embodiment, when the b assignment is 0.546, y is the value1-y2Is less than 0.0001, and b is 0.546 is substituted into any of the above equationsIn the above-described method, a is determined to be 1.061, b is determined to be 0.546, and the obtained target sampling model is y is determined to be 1.061e0.546x-1.061。
Further, the step S302 specifically includes:
step S321: and equally dividing the circumference of the iris image to be processed according to a first preset number.
Step S322: and carrying out nonlinear sampling on each boundary line according to the target sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
It should be noted that, the inner and outer circumferences of the iris image to be processed are respectively divided equally according to a first preset number, nonlinear sampling is performed on each boundary line according to the target sampling model to obtain sampling points, and the iris image to be processed is normalized into a rectangular image according to the sampling points.
In the specific implementation, the inner circumference and the outer circumference of the iris image to be processed are respectively and correspondingly divided into 512 parts, and as the target sampling model is a curve equation, nonlinear sampling can be performed on each boundary line according to the target sampling model to obtain sampling points, and the iris image to be processed is normalized into a rectangular image according to the sampling points.
Further, step S322 specifically includes:
and determining the serial numbers of the sampling points according to the second preset number, normalizing the serial numbers of the sampling points, taking the normalized serial numbers of the sampling points as an abscissa, and calculating a corresponding ordinate according to the abscissa and the target sampling model.
And taking the product of the ordinate and the second preset number as the distance from the sampling point to the pupil edge, carrying out nonlinear sampling on each boundary line according to the distance from the sampling point to the pupil edge to obtain the sampling point, and normalizing the iris image to be processed into a rectangular image according to the sampling point.
In a specific implementation, when the second preset number is 60, natural numbers 1, 2, 3, … …, 59 and 60 with sampling point serial numbers within 1-60 are determined, the sampling point serial numbers are normalized to be between 0-1, the normalized values are used as abscissa, and a corresponding ordinate is calculated according to the abscissa and the target sampling model. And taking the product of the longitudinal coordinate and 60 obtained by calculation as the distance from the sampling point to the pupil edge, carrying out nonlinear sampling on each boundary line according to the distance from the sampling point to the pupil edge to obtain the sampling point, and normalizing the iris image to be processed into a rectangular image according to the sampling point.
In this embodiment, a target sampling model is obtained by calculating preset parameters of the sampling model according to the sampling model and preset point coordinates; and carrying out nonlinear sampling on the iris image to be processed according to the target sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points. Due to the curve characteristic of the target sampling model, nonlinear sampling is carried out on the iris image to be processed to obtain sampling points, uneven scaling of iris textures can be corrected, and the actual effect is accurate.
Referring to fig. 7, fig. 7 is a flowchart illustrating an iris image normalization method according to a third embodiment of the present invention, and the iris image normalization method according to the third embodiment of the present invention is proposed based on the embodiment shown in fig. 2.
In this embodiment, the determining the state type of the to-be-processed iris image specifically includes:
step S101: and making a ray from the center of the pupil to the outside in the iris image to be processed, respectively obtaining intersection points of the ray, the iris edge and the pupil edge, and calculating the intersection point distance.
Step S102: and comparing the intersection point distance with a preset distance, and determining the state type of the iris image to be processed according to the comparison result.
It should be noted that, in order to determine the state type of the iris image to be processed, the intersection distance is compared with a preset distance, where the intersection distance is a difference between the iris radius and the pupil radius of the iris image to be processed, and the preset distance is a difference between the iris radius and the pupil radius in a standard state. And when the difference value between the iris radius and the pupil radius of the iris image to be processed is larger than that in the standard state, determining that the state type of the iris image to be processed belongs to iris expansion, and when the difference value between the iris radius and the pupil radius of the iris image to be processed is smaller than that in the standard state, determining that the state type of the iris image to be processed belongs to iris compression.
In a specific implementation, as shown in fig. 8, fig. 8 is a graph of normalized processing coordinates of an iris image, and the center of a pupil is used as the center of a polar coordinate to obtain the radius R of the iris image to be processedi106.484 and pupil radius Ro60.192, and marking the center O (O) of the outer circle of the irisx,Oy) And the center of the inner circle of the pupil I (I)x,Iy)；
Making a horizontal ray with an angle theta, the ray having an intersection with the iris edge and the pupil edge, respectively denoted as B (x)i(θ),yi(θ)),A(xo(θ),yo(θ)), then:
∠OIA＝π-θ+α
∠IOA＝π-∠OIA-∠OAI
wherein α is an included angle between the horizontal direction and the IO direction.
And after calculating the IA (theta), subtracting the pupil radius from the IA (theta) to obtain the intersection point distance.
Further, the step S20 specifically includes:
step S201: when the state type is iris compression, the sampling model is y ═aebxA, wherein y is the ratio of the intersection point distance to the preset distance, x is the normalized distance between the pupil edge and the iris edge, and a and b are preset parameters.
Step S202: when the state type is iris dilation, the sampling model is y-aln (bx + 1).
It can be understood that, in the case of pupil expansion (i.e., iris compression), the sampling points in the near pupil region are denser, and the sampling points in the far pupil region are sparser, i.e., as the distance increases, the distance between each sampling point also increases, so the sampling model adopts an exponential-like function. Under the condition of pupil contraction (namely iris expansion), the iris is stretched, sampling points in a near pupil area are sparse, and sampling points in a far pupil area are denser, namely the distance between each sampling point is reduced along with the increase of the distance, so that the sampling model adopts a log-like function.
Further, the acquiring the iris image to be processed specifically includes:
step S01: and acquiring a human eye image, carrying out iris positioning on the human eye image, and carrying out pupil removal processing on the positioned image to obtain the iris image to be processed.
It should be noted that, in an actual situation, before the iris image to be processed is obtained, generally, only the human eye image is obtained, and the human eye image needs to be preprocessed, and the preprocessed image is used as the iris image to be processed. As shown in fig. 9 and 10, fig. 9 is an iris positioning diagram of the present invention, and fig. 10 is an iris image after pupil removal of the present invention, where the preprocessing includes performing iris positioning on the human eye image and performing pupil removal processing on the positioned image.
Further, the step S30 further includes:
any point on the IA ray between two intersections can be represented by B (x)i(θ),yi(θ)),A(xo(θ),yo(θ)) represents:
wherein r is a proportional parameter, and (x (r, theta), y (r, theta)) is the coordinate of any point between two intersection points on the IA ray in the rectangular coordinate system, and each point in the iris image to be processed is mapped into a polar coordinate pair one by one. This mapping from the iris image in the rectangular coordinate system to the polar coordinate system can be expressed as:
I(x(r,θ),y(r,θ))→I(r,θ)
the invention takes the center of a pupil as the center and the width of an iris as the radius to establish a polar coordinate system, and expands the iris into a 512 x 60 rectangle with the abscissa as theta and the ordinate as r under the polar coordinate system.
In the embodiment, the intersection point distance is compared with the preset distance, so that the state type of the iris image to be processed is rapidly determined; searching corresponding sampling models through different state types, correcting the uneven scaling of the iris texture, and achieving accurate actual effect; by preprocessing the images of the human eyes, the accuracy of normalization processing of the iris images to be processed is improved.
Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, where an iris image normalization program is stored on the computer-readable storage medium, and when executed by a processor, the iris image normalization program implements the following operations:
acquiring an iris image to be processed, and determining the state type of the iris image to be processed;
searching a corresponding sampling model according to the state type;
and carrying out nonlinear sampling on the iris image to be processed according to the sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
Further, the iris image normalization program when executed by the processor further implements the following operations:
calculating preset parameters of the sampling model according to the sampling model and preset point coordinates to obtain a target sampling model;
and carrying out nonlinear sampling on the iris image to be processed according to the target sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
Further, the iris image normalization program when executed by the processor further implements the following operations:
acquiring preset point coordinates, and converting the sampling model into an equation set containing preset parameters according to the preset point coordinates;
and assigning the preset parameters according to a preset rule, and when the current assignment enables the equation to be formed, taking the current assignment as the preset parameters to obtain the target sampling model.
Further, the iris image normalization program when executed by the processor further implements the following operations:
equally dividing the circumference of the iris image to be processed according to a first preset number of parts;
and carrying out nonlinear sampling on each boundary line according to the target sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
Further, the iris image normalization program when executed by the processor further implements the following operations:
determining the serial numbers of the sampling points according to a second preset number, normalizing the serial numbers of the sampling points, taking the normalized serial numbers of the sampling points as an abscissa, and calculating a corresponding ordinate according to the abscissa and the target sampling model;
and taking the product of the ordinate and the second preset number as the distance from the sampling point to the pupil edge, carrying out nonlinear sampling on each boundary line according to the distance from the sampling point to the pupil edge to obtain the sampling point, and normalizing the iris image to be processed into a rectangular image according to the sampling point.
Further, the iris image normalization program when executed by the processor further implements the following operations:
making a ray from the center of the pupil to the outside in the iris image to be processed, respectively obtaining intersection points of the ray, the iris edge and the pupil edge, and calculating the intersection point distance;
and comparing the intersection point distance with a preset distance, and determining the state type of the iris image to be processed according to the comparison result.
Further, the iris image normalization program when executed by the processor further implements the following operations:
when the state type is iris compression, the sampling model is y ═ aebxA, wherein y is the ratio of the intersection point distance to the preset distance, x is the normalized distance between the pupil edge and the iris edge, and a and b are preset parameters;
when the state type is iris dilation, the sampling model is y-aln (bx + 1).
Further, the iris image normalization program when executed by the processor further implements the following operations:
and acquiring a human eye image, carrying out iris positioning on the human eye image, and carrying out pupil removal processing on the positioned image to obtain the iris image to be processed.
In the embodiment, the state type of the iris image to be processed is determined by acquiring the iris image to be processed; searching a corresponding sampling model according to the state type; and carrying out nonlinear sampling on the iris image to be processed according to the sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points. Because the influence of the pupil enlargement or the pupil reduction on the iris part is fully considered, the error caused by the pupil enlargement or the pupil reduction can be well reduced, the performance of the iris image normalization processing part is improved, and the accuracy of the subsequent iris part characteristic extraction and iris identification can be improved.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
The use of the words first, second, third, etc. do not denote any order, but rather the words are to be construed as names.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a computer-readable storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. An iris image normalization method, characterized by comprising the steps of:
acquiring an iris image to be processed, and determining the state type of the iris image to be processed;
searching a corresponding sampling model according to the state type;
carrying out nonlinear sampling on the iris image to be processed according to the sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points;
the searching for the corresponding sampling model according to the state type specifically includes:
when the state type is iris compression, the sampling model is y ═ aebxA, wherein y is the ratio of the intersection point distance to the preset distance, x is the normalized distance between the pupil edge and the iris edge, and a and b are preset parameters;
when the state type is iris dilation, the sampling model is y ═ a ln (bx + 1).
2. The method for normalizing an iris image according to claim 1, wherein the non-linear sampling of the iris image to be processed according to the sampling model to obtain sampling points, and the normalizing of the iris image to be processed into a rectangular image according to the sampling points specifically comprises:
calculating preset parameters of the sampling model according to the sampling model and preset point coordinates to obtain a target sampling model;
and carrying out nonlinear sampling on the iris image to be processed according to the target sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
3. The method for normalizing an iris image according to claim 2, wherein the calculating preset parameters of the sampling model according to the sampling model and preset point coordinates to obtain a target sampling model specifically comprises:
acquiring preset point coordinates, and converting the sampling model into an equation set containing preset parameters according to the preset point coordinates;
and assigning the preset parameters according to a preset rule, and when the current assignment enables the equation to be formed, taking the current assignment as the preset parameters to obtain the target sampling model.
4. The iris image normalization method of claim 3, wherein the non-linear sampling of the iris image to be processed according to the target sampling model to obtain sampling points, and the normalization of the iris image to be processed into a rectangular image according to the sampling points specifically comprises:
equally dividing the circumference of the iris image to be processed according to a first preset number of parts;
and carrying out nonlinear sampling on each boundary line according to the target sampling model to obtain sampling points, and normalizing the iris image to be processed into a rectangular image according to the sampling points.
5. The method for normalizing an iris image according to claim 4, wherein the non-linear sampling is performed on each boundary line according to the target sampling model to obtain sampling points, and the normalization of the iris image to be processed into a rectangular image according to the sampling points specifically comprises:
determining the serial numbers of the sampling points according to a second preset number, normalizing the serial numbers of the sampling points, taking the normalized serial numbers of the sampling points as an abscissa, and calculating a corresponding ordinate according to the abscissa and the target sampling model;
and taking the product of the ordinate and the second preset number as the distance from the sampling point to the pupil edge, carrying out nonlinear sampling on each boundary line according to the distance from the sampling point to the pupil edge to obtain the sampling point, and normalizing the iris image to be processed into a rectangular image according to the sampling point.
6. An iris image normalization method according to any one of claims 1 to 5, wherein the determining of the state type to which the iris image to be processed belongs specifically includes:
making a ray from the center of the pupil to the outside in the iris image to be processed, respectively obtaining intersection points of the ray, the iris edge and the pupil edge, and calculating the intersection point distance;
and comparing the intersection point distance with a preset distance, and determining the state type of the iris image to be processed according to the comparison result.
7. An iris image normalization method according to any one of claims 1 to 5, wherein the acquiring of the iris image to be processed specifically includes:
and acquiring a human eye image, carrying out iris positioning on the human eye image, and carrying out pupil removal processing on the positioned image to obtain the iris image to be processed.
8. An iris image normalization apparatus, comprising: a memory, a processor and an iris image normalization program stored on the memory and executable on the processor, the iris image normalization program when executed by the processor implementing the steps of the iris image normalization method of any one of claims 1 to 7.
9. A computer-readable storage medium, having stored thereon an iris image normalization program which, when executed by a processor, implements the steps of the iris image normalization method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810171295.7A CN108288052B (en) | 2018-03-01 | 2018-03-01 | Iris image normalization method and device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810171295.7A CN108288052B (en) | 2018-03-01 | 2018-03-01 | Iris image normalization method and device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108288052A CN108288052A (en) | 2018-07-17 |
| CN108288052B true CN108288052B (en) | 2020-12-01 |
Family
ID=62833259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810171295.7A Active CN108288052B (en) | 2018-03-01 | 2018-03-01 | Iris image normalization method and device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108288052B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113574862B (en) * | 2020-02-28 | 2023-04-25 | 京东方科技集团股份有限公司 | Image processing apparatus, image processing method, display apparatus, and computer-readable storage medium |
| CN112287872B (en) * | 2020-11-12 | 2022-03-25 | 北京建筑大学 | Iris image segmentation, positioning and normalization method based on multitask neural network |
| CN112949518B (en) * | 2021-03-09 | 2024-04-05 | 上海聚虹光电科技有限公司 | Iris image processing method, device, equipment and storage medium |
| CN113160153A (en) * | 2021-04-06 | 2021-07-23 | 宁波大学医学院附属医院 | Lung nodule screening method and system based on deep learning technology |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1445714A (en) * | 2003-03-19 | 2003-10-01 | 上海交通大学 | Iris marking normalization process method |
| CN1776710A (en) * | 2005-11-17 | 2006-05-24 | 上海交通大学 | Body iris texture non-linear normalizing method |
| KR20110078468A (en) * | 2009-12-31 | 2011-07-07 | 서강대학교산학협력단 | A system and method for identifying the iris of persons in unrestricted condition |
| CN102663372A (en) * | 2012-04-25 | 2012-09-12 | 中国科学技术大学 | Iris texture normalization method based on dual-spring model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7593550B2 (en) * | 2005-01-26 | 2009-09-22 | Honeywell International Inc. | Distance iris recognition |
-
2018
- 2018-03-01 CN CN201810171295.7A patent/CN108288052B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1445714A (en) * | 2003-03-19 | 2003-10-01 | 上海交通大学 | Iris marking normalization process method |
| CN1776710A (en) * | 2005-11-17 | 2006-05-24 | 上海交通大学 | Body iris texture non-linear normalizing method |
| KR20110078468A (en) * | 2009-12-31 | 2011-07-07 | 서강대학교산학협력단 | A system and method for identifying the iris of persons in unrestricted condition |
| CN102663372A (en) * | 2012-04-25 | 2012-09-12 | 中国科学技术大学 | Iris texture normalization method based on dual-spring model |
Non-Patent Citations (4)
| Title |
|---|
| A Biomechanical Approach to Iris Normalization;Inmaculada Tomeo-Reyes等;《2015 International Conference on Biometrics》;20150522;第9-16页 * |
| Iris Recognition: An Analysis of the Aliasing Problem in the Iris Normalization Stage;Hugo Proenca等;《2006 International Conference on Computational Intelligence and Security》;20061106;第2卷;第1771-1774页 * |
| 基于线段提取的虹膜归一化方法;郭巧丽等;《计算机技术与发展》;20090430;第19卷(第4期);第58-59页 * |
| 虹膜图像的预处理;张德馨;《中国科学院机构知识库网格》;20031231;正文第10、14、51-55页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108288052A (en) | 2018-07-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108288052B (en) | Iris image normalization method and device and computer readable storage medium | |
| US11468913B1 (en) | Method for real-time video processing involving retouching of an object in the video | |
| AU2019200754B2 (en) | Methods and Systems for Capturing Biometric Data | |
| JP6837288B2 (en) | Fingerprint authentication method and device | |
| CN108961175B (en) | Face brightness adjusting method and device, computer equipment and storage medium | |
| CN106778453B (en) | Method and device for detecting glasses wearing in face image | |
| US20160162673A1 (en) | Technologies for learning body part geometry for use in biometric authentication | |
| WO2015106700A1 (en) | Method and apparatus for implementing image denoising | |
| KR102313981B1 (en) | Fingerprint verifying method and apparatus | |
| CA2764855A1 (en) | Methods and systems of authentication | |
| CN106557770B (en) | Identifying shapes in images by comparing bezier curves | |
| CN110717484B (en) | Image processing method and system | |
| JP5882929B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| JP6658188B2 (en) | Image processing apparatus, image processing method, and image processing program | |
| US20150110365A1 (en) | Methods and systems for detecting biometric characteristics in an image | |
| JP6448253B2 (en) | Data creation program, data creation method, and data creation device | |
| JP6366420B2 (en) | Data creation program, data creation method, and data creation device | |
| CN111199176B (en) | Face identity detection method and device | |
| JP2017157095A (en) | Device, method, and program for processing biological image | |
| CN110020577B (en) | Face key point expansion calculation method, storage medium, electronic device and system | |
| WO2020082686A1 (en) | Image processing method and apparatus, and computer-readable storage medium | |
| CN108288023B (en) | Face recognition method and device | |
| WO2020215854A1 (en) | Method and apparatus for rendering image, electronic device, and computer readable storage medium | |
| WO2018023549A1 (en) | Terminal fingerprint-processing method and terminal | |
| CN111274846B (en) | Method and system for identifying opening and closing actions |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |