Iris identification system and method and computer readable storage medium stored therein computer executable instructions to implement iris identification method

• US 20040037452A1
• Filed: 04/23/2003
• Published: 02/26/2004
• Est. Priority Date: 10/07/2000
• Status: Active Grant

• Current Assignee: Sung-Hyun Kim
• Original Assignee: Qritek Company Limited
• Inventors: Shin, Sung Bok
• Granted Patent: US 7,277,561 B2
• Time in Patent Office: Days
• US Class Current: 382/117
• CPC Class Codes: G06V 40/18 Eye characteristics, e.g. of the iris

Abstract

An iris identification system for confirming identity of a person and method thereof are disclosed. The iris identification system comprises a mode converter for selecting one of registration and identification modes, an image input means, a luminance adjustment module, a registration module, an identification module, a reference iris image storage, and a main control unit. The registration module captures iris images when the registration mode is selected, preprocesses the captured iris image, defines the preprocessed iris image as main, auxiliary, negative main and compensation data, encodes the defined data, and registers the encoded data as data of the reference iris images; The identification module captures an iris image when the identification mode is selected, preprocesses the captured iris image, defines the preprocessed iris image as main, auxiliary, negative main and compensation data, encodes the defined data, and analyzes similarity both data.

Claims

1. An iris identification system for confirming identity of a person, wherein the iris identification system comprising:

a mode converter for selecting one of registration and identification modes;

an image input means for inputting an iris image;

a luminance adjustment module for sequentially selecting predetermined luminance levels when the registration mode is selected by the mode converter and irradiating the light of the selected luminance level together with infrared ray to the eye for iris registration;

a registration module for capturing a plurality of iris images inputted by the image input means whenever the light selected by the luminance adjustment module is irradiated to the eye, preprocessing the captured iris image to decide pupil boundary, pupil center, iris size, and class to which the iris image belongs, defining the preprocessed iris image as main, auxiliary, negative main and compensation data, encoding the defined data, and registering the encoded data as data of the reference iris images;

an identification module for capturing an iris image inputted by the image input means when the identification mode is selected by the mode converter, preprocessing the captured iris image to decide pupil boundary, pupil center, iris size, and class to which the iris image belongs, defining the preprocessed iris image as main, auxiliary, negative main and compensation data, encoding the defined data, and analyzing similarity between the encoded data of the iris image for identification and the encoded data of the reference iris images registered in the registration module;

a reference iris image storage for storing the data of the reference iris images registered in the registration module; and

a main control unit for controlling the image input means, the luminance adjustment module, the registration module, the identification module and the reference iris image storage according to the operation mode of the mode converter.

2. The iris identification system of claim 1, wherein each iris image captured by the registration module or the identification module is horizontally divided so as to form a plurality of horizontal bands, the horizontal bands are divided by a perpendicular line passing through a center of the pupil such that a plurality of blocks are symmetrically formed, each block is divided into a plurality of sub-blocks and each sub-block is divided into a plurality of units.

3. The iris identification system of claim 2, wherein each band has its own priority and a weighted value to be considered at the analysis for identification.

4. The iris identification system of claim 3, wherein each unit in a sub-block is classified into an auxiliary data, a main data, a negative main data, and a compensation data according to the luminance level of the unit.

5. The iris identification system of claim 4, wherein the units of which luminance are less than the average luminance of the sub-block are defined as the auxiliary data;

among the units defined as the auxiliary data, the units that have luminance less than average luminance of the auxiliary data and length larger than a predetermined length are defined as the main data, the units of which luminance is greater than the average luminance of the sub-block and has length larger than the predetermined length are defined as a negative main data; and

the units corresponding the 9/10˜

11/10 of the average luminance of the auxiliary data are defined as the compensation data.

6. The iris identification system of claim 2, wherein a center of the pupil is calculated by obtaining a plurality of random pupil centers I_i, extracting candidate pupil centers from the random pupil centers, and calculating a final pupil center T_p(x_p, y_p) using the candidate pupil centers.

7. The iris identification system of claim 6, wherein the random pupil center I_i is obtained by randomly selecting two points of S(x₁, y₁) and E(x₂, y₂) on the pupil boundary of the iris image, creating a segment SE by drawing a line connecting the points S and E, drawing a perpendicular line from a center of the segment SE such that the perpendicular line crosses the pupil boundary at a point C(x₃, y₃), and calculating the random pupil center I_i(x₀, y₀) as following calculations:

a=½

{square root}{square root over ((x₁−

x₂)²+(y₁−

y₂)²)},c=½

{square root}{square root over ((x₁+x₂−

2x₃)²+(y₁+y₂−

2y₃)²)}

8. The iris identification system of claim 2, wherein the pupil boundary is determined as following equation,

when I_min <

I_b<

I_ma,

9. An iris identification method for confirming identity of a person, wherein the method comprising the steps of:

(a) selecting one of registration and identification modes;

(b) inputting an iris image;

(c) sequentially selecting predetermined luminance levels when the registration mode is selected, and irradiating the light of the selected luminance level together with infrared ray to the eye for iris registration;

(d) capturing a plurality of iris images inputted at the step (b) whenever the light selected at the step (c) is irradiated to the eye, preprocessing the captured iris image to decide pupil boundary, pupil center, iris size, and class to which the iris image belongs, defining the preprocessed iris image as main, auxiliary, negative main and compensation data, encoding the defined data, and registering the encoded data as data of the reference iris images;

(e) for storing the data of the reference iris images registered at the step (d);

(f) capturing an iris image inputted at the step (b) when the identification mode is selected at the step (a), preprocessing the captured iris image to decide pupil boundary, pupil center, iris size, and class to which the iris image belongs, defining the preprocessed iris image as main, auxiliary, negative main and compensation data, encoding the defined data, and analyzing similarity between the encoded data of the iris image for identification and the data of the reference iris image stored at the step (e).

10. The iris identification method of claim 9 wherein each iris image captured at the step (d) or (f) is horizontally divided so as to form a plurality of horizontal bands, the horizontal bands are divided by a perpendicular line passing through a center of the pupil such that a plurality of blocks are symmetrically formed, each block is divided into a plurality of sub-blocks and each sub-block is divided into a plurality of units.

11. The iris identification method of claim 10, wherein each band has its own priority and a weighted value to be considered at the analysis for identification.

12. The iris identification method of claim 11, wherein each unit in a sub-block is classified into an auxiliary data, a main data, a negative main data, and a compensation data according to the luminance level of the unit.

13. The iris identification method of claim 12, wherein the units of which luminance are less than the average luminance of the sub-block are defined as the auxiliary data;

among the units defined as the auxiliary data, the units that have luminance less than average luminance of the auxiliary data and length larger than a predetermined length are defined as the main data, the units of which luminance is greater than the average luminance of the sub-block and has length larger than the predetermined length are defined as a negative main data; and

the units corresponding the {fraction (9/10)}˜

{fraction (11/10)} of the average luminance of the auxiliary data are defined as the compensation data.

14. The iris identification method of claim 10, wherein a center of the pupil is calculated by obtaining a plurality of random pupil centers I_i, extracting candidate pupil centers from the random pupil centers, and calculating a final pupil center T_p (x_p, y_p) using the candidate pupil centers.

15. The iris identification method of claim 14, wherein the random pupil center I_i is obtained by randomly selecting two points of S(x₁, y₁) and E(x₂, y₂) on the pupil boundary of the iris image, creating a segment SE by drawing a line connecting the points S and E, drawing a perpendicular line from a center of the segment SE such that the perpendicular line crosses the pupil boundary at a point C(x₃, y₃), and calculating the random pupil center I_i(x₀, y₀) as following calculations:

a=½

{square root}{square root over ((x₁−

x₂)²+(y₁−

y₂)},a=½

{square root}{square root over ((x₁=x₂2x₃)²+(y₁+y₂−

2y₃)²)}

16. The iris identification method of claim 10, wherein the pupil boundary is determined as following equation,

when I_min<

I_b<

I_max,

17. A computer readable storage medium stored thereon computer executable instructions to implement an iris identification method for confirming identity of a person, wherein the method comprising the steps of:

(a) selecting one of registration and identification modes;

(b) inputting an iris image;

(c) sequentially selecting predetermined luminance levels when the registration mode is selected, and irradiating the light of the selected luminance level together with infrared ray to the eye for iris registration;

(d) capturing a plurality of iris images inputted at the step (b) whenever the light selected at the step (c) is irradiated to the eye, preprocessing the captured iris image to decide pupil boundary, pupil center, iris size, and class to which the iris image belongs, defining the preprocessed iris image as main, auxiliary, negative main and compensation data, encoding the defined data, and registering the encoded data as data of the reference iris images;

(e) for storing the data of the reference iris images registered at the step (d); and

(f) capturing an iris image inputted at the step (b) when the identification mode is selected at the step (a), preprocessing the captured iris image to decide pupil boundary, pupil center, iris size, and class to which the iris image belongs, defining the preprocessed iris image as main, auxiliary, negative main and compensation data, encoding the defined data, and analyzing similarity between the data of the iris image for identification and the encoded data of the reference iris image stored at the step (e).

18. The computer readable storage medium of claim 17, wherein each iris image captured at the step (d) or (f) is horizontally divided so as to form a plurality of horizontal bands, the horizontal bands are divided by a perpendicular line passing through a center of the pupil such that a plurality of blocks are symmetrically formed, each block is divided into a plurality of sub-blocks and each sub-block is divided into a plurality of units.

19. The computer readable storage medium of claim 18, wherein each band has its own priority and a weighted value to be considered at the analysis for identification.

20. The computer readable storage medium of claim 19, wherein each unit in a sub-block is classified into an auxiliary data, a main data, a negative main data, and a compensation data according to the luminance level of the unit.

21. The computer readable storage medium of claim 20, wherein the units of which luminance are less than the average luminance of the sub-block are defined as the auxiliary data;

among the units defined as the auxiliary data, the units that have luminance less than average luminance of the auxiliary data and length larger than a predetermined length are defined as the main data, the units of which luminance is greater than the average luminance of the sub-block and has length larger than the predetermined length are defined as a negative main data; and

the units corresponding the {fraction (9/10)}˜

{fraction (11/10)} of the average luminance of the auxiliary data are defined as the compensation data.

22. The computer readable storage medium of claim 18, wherein a center of the pupil is calculated by obtaining a plurality of random pupil centers I_i, extracting candidate pupil centers from the random pupil centers, and calculating a final pupil center T_p (x_p, y_p) using the candidate pupil centers.

23. The computer readable storage medium of claim 22, wherein the random pupil center I_i is obtained by randomly selecting two points of S(x₁, y₁) and E(x₂, y₂) on the pupil boundary of the iris image, creating a segment SE by drawing a line connecting the points S and E, drawing a perpendicular line from a center of the segment SE such that the perpendicular line crosses the pupil boundary at a point C(x₃, y₃), and calculating the random pupil center I_i(x₀, y₀) as following calculations:

a=½

{square root}{square root over ((x₁−

x₂)²+(y₁−

y₂)²)},c={fraction (1/2)}{square root}{square root over ((x₁+x₂−

2x₃)²+(y₁+y₂−

2y₃)²)}

24. The computer readable storage medium of claim 18, wherein the pupil boundary is determined as following equation,

when I_min<

I_b<

I_ma,