TWI459309B - System and method for identifying irises - Google Patents

Description

Iris recognition system and method

The present invention relates to an identification system and method, and more particularly to a system and method for identifying a user identity using an iris.

With the development of society, the importance of identity recognition is becoming more and more obvious, and the traditional identification method is far from satisfactory due to its inherent limitations. Keys, cards and ID cards are easy to be lost and forged, and passwords are easy to forget. What is more serious is that these traditional methods of identification cannot distinguish between true owners and impostors who obtain identity markers. Once others have obtained these identity markers, they can enjoy the same rights as owners.

In recent years, biometric-based recognition technology has emerged, for example, fingerprint recognition. However, since the fingerprint is easily destroyed, it is also unstable.

In view of the above, it is necessary to provide an iris recognition system and method that can enhance the accuracy and stability of identity recognition by utilizing the biological characteristics of the iris.

An iris recognition system is installed in an electronic device, the electronic device includes a camera module and a memory, and the memory stores a feature value of a feature point of an original iris of each user as an identification code, the system The method includes: acquiring a module, wherein the camera module captures a user's iris and acquires a corresponding certified iris image; and the processing module is configured to process the acquired authentication iris image; the iris feature extraction a module for extracting feature points of the certified iris in the processed certified iris image, and calculating feature values of the extracted feature points of the certified iris; and a comparison module for comparing the extracted authentication irises Whether the feature value of the feature point matches the identification code in the memory, and confirms that the user is identified by the identity when the feature value of the extracted feature point of the authentication iris matches the identification code in the memory.

An iris recognition method is applied to an electronic device, the electronic device comprising a camera module and a memory, the method comprising the steps of: storing feature values of feature points of each user's original iris into the memory The camera module is configured to capture a user's iris, and obtain a corresponding certified iris image; process the acquired authentication iris image; extract a feature point of the certified iris in the processed certified iris image, and Calculating a feature value of each feature point of the extracted authentication iris; comparing whether the feature value of the extracted feature point of the authentication iris matches the identification code in the memory; and if the feature value of the extracted feature point of the authentication iris is If the identification code in the memory matches, the user is confirmed to be identified.

Compared with the prior art, the iris recognition system and method can utilize the biological characteristics of the iris (for example, the uniqueness, stability, etc. of the iris) to enhance the accuracy and stability of the identification.

1‧‧‧Electronic device

10‧‧‧ camera module

12‧‧‧ Processor

14‧‧‧ memory

2‧‧‧Iris Recognition System

20‧‧‧Getting module

22‧‧‧Processing module

24‧‧‧Feature Extraction Module

26‧‧‧Storage module

28‧‧‧ Alignment module

5‧‧‧ iris

6‧‧‧ crypt

7‧‧‧瞳孔

1 is a diagram showing an operating environment and a functional module of a preferred embodiment of the iris recognition system of the present invention.

2 is a flow chart of a preferred embodiment of the iris recognition method of the present invention.

3 is a schematic view showing the structure of an iris of the iris recognition system of the present invention.

4 is a graph showing the coordinates of an iris feature point of the iris recognition system of the present invention.

Figure 5 is a schematic illustration of the relative positions of iris feature points of the iris recognition system of the present invention.

FIG. 1 is a diagram showing an operating environment and a functional module of a preferred embodiment of the iris recognition system of the present invention. The iris recognition system 2 is installed and operated in the electronic device 1. The electronic device 1 can be a portable electronic device such as a mobile phone, a PDA (personal digital assistant), a handheld game console, a digital camera or a palmtop computer, or a fixed access control system.

The electronic device 1 further includes a camera module 10, a processor 12, and a memory 14. The camera module 10 generally includes an image sensor, a lens and a lens holder, and may also include other components or devices. The image sensor may be a CCD (Charge Coupled Device) or a CMOS (Complementary Metal-Oxide-Semiconductor Transistor). In the preferred embodiment, the camera module 10 is used to capture the iris of the user for recognition. The processor 12 is configured to execute the iris recognition system 2 and other applications in the electronic device 1, such as an operating system.

The memory 14 can be built in the memory of the electronic device 1 itself, or can be an external storage card, such as a SIM card (Smart Media Card), an SD card (Secure Digital Card). Wait. The memory 14 is used for storing various types of materials, including an image of an iris photographed by the camera module 10, data obtained by processing the image of the iris by the iris recognition system 2, and the like.

The iris recognition system 2 mainly includes an acquisition module 20, a processing module 22, a feature extraction module 24, a storage module 26, and a comparison module 28.

Before identifying the user's iris to verify the identity of the user, it is necessary to first establish an iris feature database storing the original iris image and related data of each user, so as to perform the comparison in the subsequent identification process to verify the identity of the user.

The acquiring module 20 is connected to the camera module 10 for causing the camera module 10 to capture a user's iris and acquire a corresponding original iris image.

The processing module 22 is configured to process the acquired original iris image, including: changing the original iris image from color to black and white; reducing the brightness of the original iris image; and increasing the contrast of the original iris image.

The feature extraction module 24 is configured to extract feature points of the original iris in the processed original iris image, and calculate feature values of the extracted feature points of the original iris. The feature points of the original iris include a primary feature point and a secondary feature point, and the feature values of the feature point include, but are not limited to, the number of feature points, the feature point coordinates, the shape of the feature points, and the feature point distance.

Figure 3 is a simplified schematic view of the iris structure, wherein the iris 5 is an annular portion between the black pupil 7 of the eye and the white sclera (not shown), generally showing a radiation from the inside out. The structure is composed of a relatively complicated fibrous structure, and contains many intertwined details such as spots, filaments, crowns, stripes, crypts, etc. In the preferred embodiment, the crypt is characterized. Only a portion of the crypt 6 is depicted in FIG. 3 to illustrate the preferred embodiment, while other features such as spots, filaments, crowns, stripes, and the like are not drawn.

In the preferred embodiment, the original iris feature points include a primary feature point and a secondary feature point, wherein a crypt having the largest area in the original iris is used as the main feature point, as shown in FIG. 4 and FIG. The box part is the main feature point, while the rest of the original iris The crypt is used as a sub-feature point, and the circle portion shown in FIGS. 4 and 5 is a sub-feature point. In the schematic diagrams of FIGS. 4 and 5, the number of main feature points of the original iris is 1, and the number of sub-feature points is 9.

The method for the feature extraction module 24 to calculate the coordinates of each feature point of the original iris is as shown in FIG. 4 . After extracting the main feature points and the sub-feature points of the original iris, a coordinate map is established on each of the main feature points and the secondary feature points, and then the coordinates of the feature points of the original iris can be calculated according to the coordinate map.

The feature extraction module 24 calculates the shape of each feature point of the original iris as shown in FIG. 5, and connects each feature point with the feature point closest to the distance, and the figure is connected to obtain the shape of the feature point of the original iris. In addition, the feature extraction module 24 may further calculate a distance between each feature point according to the calculated coordinates of each feature point.

The storage module 26 is configured to store the feature points of the original iris extracted by the feature extraction module 24 and the calculated feature values of the feature points into the iris feature database in the memory 14 as the electronic device 1 An identification code that identifies each user's identity. The iris feature database includes one or more sets of identification codes to identify the identity of one or more users.

When the user identity needs to be recognized, the acquiring module 20 is further configured to enable the camera module 10 to capture the iris of the user (for convenience of description, the iris of the user to be identified is collectively referred to as “authentic iris”). And get the corresponding certified iris image.

The processing module 22 is further configured to process the acquired authentication iris image, including: changing the authentication iris image from color to black and white; reducing the brightness of the certified iris image; and increasing the contrast of the certified iris image. .

The feature extraction module 24 is configured to extract recognition from the processed authentication iris image The feature points of the iris are verified, and the feature values of the extracted feature points of the certified iris are calculated. The method for extracting the feature points of the authentication iris is the same as the method for extracting the feature points of the original iris, and the method for calculating the feature values of the feature points of the authentication iris is the same as the method for calculating the feature values of the original iris feature points.

The comparison module 28 is configured to compare whether the feature value of the authentication iris feature point matches the identification code of the iris feature database in the memory 14. If the iris feature database includes multiple sets of identification codes, it is determined whether the feature values of the certified iris feature points match one of the set of identification codes.

Wherein, the comparison criterion may be set according to each parameter of the feature value. For example, the comparison criterion includes, but is not limited to, the following item: item 1 when the primary feature point of the iris is authenticated and one of the original irises as the identification code If the coordinates of the main feature points are the same, it can be confirmed that the main feature points of the authentication iris are the same as the main feature points of the original iris; in the second item, when the number of sub-feature points of the authentication iris reaches the number of sub-feature points of the original iris If it is more than 60%, it can be considered that the certified iris matches the number of sub-feature points of the original iris; in the third item, when the coordinates of the characteristic points of the certified iris and the coordinates of the feature points of the original iris are six If the same is the same, it can be considered that the authentication iris matches the original iris on the coordinates of the sub-feature points. The details of the above comparison criteria can be set, added, reduced or modified according to actual requirements.

The comparison module 28 is further configured to: when the feature value of the feature point of the authentication iris satisfies each item of the comparison standard, confirm that the feature value of the feature point of the authentication iris matches the identification code, and Confirm that the user is identified.

2 is a flow chart of a preferred embodiment of the iris recognition method of the present invention. First, in step S2, the acquisition module 20 causes the camera module 10 to capture irises of a plurality of users and acquire corresponding original iris images.

In step S4, the processing module 22 processes the acquired original iris image, including: changing the original iris image from color to black and white; reducing the brightness of the original iris image; and increasing the contrast of the original iris image.

In step S6, the feature extraction module 24 extracts feature points of the original iris in the processed original iris image, and calculates feature values of the extracted feature points of the original iris. The feature points of the original iris include a primary feature point and a secondary feature point, and the feature values of the feature point include, but are not limited to, the number of feature points, the feature point coordinates, the shape of the feature points, and the feature point distance.

In the preferred embodiment, the original iris feature points include a primary feature point and a secondary feature point, wherein a crypt having the largest area in the original iris is used as the main feature point, as shown in FIG. 4 and FIG. The box part is the main feature point, and the remaining crypts in the original iris are used as the sub-feature points, and the circle parts shown in FIG. 4 and FIG. 5 are the sub-feature points.

In step S8, the storage module 26 stores the extracted feature points of the original iris and the calculated feature values of the feature points into the memory 14, as the identification code for identifying the identity of each user by the electronic device 1.

In step S10, the acquiring module 20 causes the camera module 10 to capture the iris of the user to be identified, and acquire a corresponding authentication iris image.

Step S12, the processing module 22 processes the acquired authentication iris image, including: changing the authentication iris image from color to black and white; reducing the brightness of the authentication iris image; and increasing the contrast of the authentication iris image.

In step S14, the feature extraction module 24 extracts feature points of the authentication iris in the processed authentication iris image, and calculates feature values of the extracted feature points of the authentication iris. Wherein, the method for extracting characteristic points of the certified iris and the original iris feature The extraction method of the points is the same, and the calculation method of the feature values of the feature points of the authentication iris is the same as the calculation method of the feature values of the original iris feature points.

In step S16, the comparison module 28 compares whether the feature value of the certified iris feature point matches a set of identification codes of the iris feature database in the memory 14. Wherein, the comparison criterion can be set according to each parameter of the feature value. If the feature value of the authentication iris feature point matches the identification code in the memory 14, step S18 is performed; otherwise, the flow is ended.

In step S18, the comparison module 28 confirms that the user is identified by the identity and ends the process.

In summary, the present invention complies with the requirements of the invention patent and submits a patent application according to law. However, the above description is only a preferred embodiment of the present invention, and the scope of the present invention is not limited to the above-described embodiments, and equivalent modifications or variations made by those skilled in the art in accordance with the spirit of the present invention are It should be covered by the following patent application.

1‧‧‧Electronic device

10‧‧‧ camera module

12‧‧‧ Processor

14‧‧‧ memory

2‧‧‧Iris Recognition System

20‧‧‧Getting module

22‧‧‧Processing module

24‧‧‧Feature Extraction Module

26‧‧‧Storage module

28‧‧‧ Alignment module

Claims (12)

An iris recognition system is installed in an electronic device, the electronic device includes a camera module and a memory, and the memory stores a feature value of a feature point of an original iris of each user as an identification code, the system The method includes: acquiring a module, wherein the camera module captures a user's iris and acquires a corresponding certified iris image; and the processing module is configured to process the acquired authentication iris image; the iris feature extraction mode a group for extracting feature points of the authentication iris in the processed authentication iris image, and calculating feature values of the extracted feature points of the authentication iris, wherein the feature points of the original iris and the authentication iris respectively include a main a feature point and a sub-feature point; and a comparison module, configured to compare the feature value of the extracted feature point of the certified iris with the identification code in the memory according to a preset comparison criterion, and extract the extracted Confirming that the user passes the identity when the feature value of the feature point of the authentication iris matches the identification code in the memory, wherein the comparison criterion includes: when the authentication iris The same coordinates in which the main subject feature point the feature point as an original iris identification code, can confirm that the main point of the feature in the iris authentication same as the primary point of the original iris feature. The image recognition system of claim 1, wherein the acquisition module is further configured to: capture the original iris of the user by the camera module, and acquire a corresponding original iris image; The group is further configured to process the acquired original iris image; the feature extraction module is further configured to extract feature points of the original iris in the processed original iris image, and calculate the extracted original iris features. The feature value of the point; and the system further includes a storage module, configured to store the extracted feature points of each original iris and the calculated feature values of the feature points of each original iris into the memory as the identification of each user ID of the identification. The iris recognition system according to claim 1, wherein the main feature point is a crypt having the largest area in the iris, and the sub-feature point is outside the crypt in the iris except for being confirmed as the main feature point. The rest of the crypt. The iris recognition system according to claim 1, wherein the comparison standard according to the comparison module further comprises one or more of the following items: when the number of sub-feature points of the authentication iris reaches the original iris If the number of sub-feature points is more than 60%, the authentication iris may be considered to correspond to the number of sub-feature points of the original iris; and/or when the coordinates of each feature point of the iris are authenticated and the feature points of the original iris If the coordinates of the coordinates are the same or more than 60%, the authentication iris can be considered to coincide with the coordinates of the original iris at the sub-feature point. The iris recognition system according to claim 1, wherein the processing module performs the processing of authenticating the iris image by: changing the authentication iris image from color to black and white; and reducing the brightness of the authentication iris image; Increase the contrast of the certified iris image. The iris recognition system according to claim 1, wherein the feature values of the original iris feature points and the feature values of the certified iris feature points include the number of feature points, the feature point coordinates, the shape of the feature points, and the feature point distance. . An iris recognition method is applied to an electronic device, the electronic device comprising a camera module and a memory, the method comprising the steps of: storing feature values of feature points of each user's original iris into the memory The camera module is configured to capture a user's iris, and obtain a corresponding certified iris image; process the acquired authentication iris image; extract a feature point of the certified iris in the processed certified iris image, and Calculating the feature values of the extracted feature points of the authentication iris, wherein the feature points of the original iris and the authentication iris respectively include a primary feature point and a secondary feature point; And comparing, according to a preset comparison criterion, whether the feature value of the extracted feature point of the authentication iris matches the identification code in the memory, wherein the comparison criterion comprises: when the primary feature point of the authentication iris The same as the coordinate of the main feature point of one of the original irises as the identification code, it can be confirmed that the main feature point of the authentication iris is the same as the main feature point of the original iris; and if the characteristic point of the extracted authentication iris is selected If the value matches the identification code in the memory, the user is confirmed to be authenticated. The iris recognition method of claim 7, wherein the storing the feature values of the feature points of the original iris of each user into the memory includes: causing the camera module to capture a user The original iris, and obtain the corresponding original iris image; process the acquired original iris image; extract the feature points of the original iris in the processed original iris image, and calculate the extracted feature points of the original iris And the feature values of the extracted original irises and the calculated feature values of the feature points of the original irises are stored in the memory as identification codes for identifying the identity of each user. The iris recognition method according to claim 7, wherein the main feature point is a crypt having the largest area in the iris, and the sub-feature point is outside the crypt in the iris except for being confirmed as the main feature point. The rest of the crypt. The iris recognition method according to claim 7, wherein the step of processing the acquired authentication iris image comprises: changing the authentication iris image from color to black and white; and reducing brightness of the authentication iris image; And increase the contrast of the certified iris image. The iris recognition method according to claim 7, wherein the comparison standard further includes one or more of the following items: when the number of sub-feature points of the authentication iris reaches the number of sub-feature points of the original iris Cheng Above, it can be considered that the authentication iris matches the original iris in the number of sub-feature points; and/or when the coordinates of each feature point of the authentication iris are more than 60% identical to the coordinates of each feature point of the original iris, Then, the authentication iris can be considered to coincide with the original iris on the coordinates of the sub-feature points. The iris recognition method according to claim 7, wherein the feature values of the original iris feature points and the feature values of the certified iris feature points include the number of feature points, the feature point coordinates, the shape of the feature points, and the feature point distance. .