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

• US 20020039433A1
• Filed: 09/24/2001
• Published: 04/04/2002
• Est. Priority Date: 10/07/2000
• Status: Abandoned Application

• Current Assignee: Oritek Company Limited
• Original Assignee: Oritek Company Limited
• Inventors: Shin, Sung Bok
• Application Number:
  US09/962,751
• Publication Number:
  US 20020039433A1
• 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 includes a mode converter for selecting one of registration and identification modes, an image input means for capturing an iris image, an image control unit for registering a plurality of instances of the iris image captured in the image input means as reference iris images in the registration mode and retrieving a corresponding reference iris image when an iris image is presented to the image input means in the identification mode, an iris reference iris image storage for storing the registered reference iris images, and a main control unit for controlling the image input means, mode converter, image control unit and the iris reference iris image storage so as to cooperates one another.

Claims

1. An iris identification system comprising:

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

an image input means for capturing an iris image;

an image control unit for registering a plurality of instances of the iris image captured in the image input means as reference iris images in the registration mode and retrieving a corresponding reference iris image when an iris image is presented to the image input means in the identification mode;

an iris reference iris image storage for storing the registered reference iris images; and

a main control unit for controlling the image input means, mode converter, image control unit and the iris reference iris image storage so as to cooperates one another.

2. An iris identification system of claim 1 wherein the image control unit comprises:

a registration module for registering the instances as the iris reference samples; and

an image analysis module for retrieving the corresponding reference iris image when the iris image is presented to the image input means and analyzing similarity between the presented iris image and the retrieved reference iris image.

3. An iris identification system of claim 2 further comprises a luminance adjustment module for detecting luminance of the input image and adjusting the luminance around an eyepiece of the image input means.

4. An iris identification system of claim 3 wherein the iris instances have different pupil radius.

5. An iris identification system of claim 4 wherein the pupil radium is adjusted by the luminance adjustment module adjusting luminance around the eyepiece of the image input means using visible ray.

6. An iris identification system of claim 5 wherein the luminance adjustment module further adjusts the luminance using invisible ray when the luminance is less than a predetermined threshold level.

7. An iris identification system of claim 2 wherein the registration module takes the instances having predetermined pupil radius, classifies the instances into at least one class, and stores the instances as reference iris images with class information.

8. An iris identification system of claim 7 wherein each reference iris image belonged to a class is vertically divided so as to form a plurality of horizontal bands and 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.

9. An iris identification system of claim 8 wherein the classes are defined by dividing a distance between minimum pupil radium and maximum pupil radium by a predetermined interval in a range of the iris radium.

10. An iris identification system of claim 7 wherein the reference iris image is stored as absolute coordinates data in relation with the center of the pupil.

11. An iris identification system of claim 8 wherein the horizontal bands have priorities assigned in a predetermined order.

12. An iris identification system of claim 11 wherein a size of the block is determined according to where the block locates in the range of iris radium.

13. An iris identification system of claim 12 wherein the block comprises a main, auxiliary, and negative main data that are defined by pixel density.

14. An iris identification system of claim 13 wherein the auxiliary data has a luminance less than a predetermined standard luminance and the main data are the data that have a pixel density greater than a predetermined standard pixel density among the auxiliary data.

15. An iris identification system of claim 13 wherein the negative main data are the data that have a pixel density less than the predetermined standard pixel density among data that have a luminance greater than the predetermined standard luminance.

16. An iris identification system of claim 14 wherein the auxiliary data is divided into an upper and lower level portions on the basis of a predetermined luminance level.

17. An iris identification system of claim 18 wherein the upper level portion is defined between the predetermined luminance level and a lowest luminance level, and the lower level portion is defined between the predetermined luminance level and the standard luminance level such that the auxiliary data is stored as one of the upper and lower levels.

18. An iris identification system of claim 17 wherein a compensation area is defined around the predetermined luminance level such that a data level of a vague iris image can be compensated through exclusive-OR and logical multiply computation using the compensation level.

19. An iris identification system of claim 10 wherein a center of the pupil is calculated in such an order of obtaining a plurality of random pupil centers I_i, extracting candidate pupil centers from the random pupil centers, calculating a final pupil center T_p (x_p, y_p) using the candidate pupil centers.

20. An iris identification system of claim 19 wherein the random pupil center I_i is obtained in such a manner of randomly selecting two points of S(x₁, y₁) and E(x₂, y₂) on an actual pupil boundary, 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 on the basis of arc SE and point C thereon.

21. An iris identification system of claim 19 wherein the random pupil center I_I(x₀, y₀) is obtained as following calculations:

22. An iris identification system of claim 21 wherein the candidate pupil centers have radius that are in whole class range β

.

23. An iris identification system of claim 22 wherein the final pupil center T_p(x_p, y_p) is obtained as following calculations:

24. An iris identification system of claim 23 wherein the registration module determines a pupil boundary as following equation,

when I_mm<

I_b<

I_ma,

$I_{\mathrm{mb}}=\frac{1}{N_b}<br><br>\sum <br><br>I_b$$\mathrm{where}<br><br>\text{\hspace{1em}<br><br>}<br><br>I_{\mathrm{ma}}=\frac{1}{N_a}<br><br>\sum <br><br>I_a,I_a<br><br>\left(I_b\right)$

is luminance of a pixel, I_ma(I_mb) is an average luminance, N_a(N_b) is number of executions, and I_min is a minimum luminance limit.

25. An iris identification system of claim 2 wherein the image analysis module retrieves a target class when the iris image is presented to the image input means and retrieves a target reference iris image in the class if the target class exists.

26. An iris identification system of claim 25 wherein the image analysis module partitions the presented iris image into a plurality of horizontal bands, creates data blocks by symmetrically dividing the bands, and codes the data blocks with a main, auxiliary, and negative main data.

27. An iris identification system of claim 26 wherein the image analysis module compares the presented iris image with the target reference iris image and analyzes data similarity and band dependency.

28. An iris identification system of claim 27 wherein the image analysis module determines whether the presented iris image satisfies condition of a predetermined security level on the basis of result from the analysis of the similarity and band dependency.

29. An iris identification system of claim 28 wherein the image analysis module takes more than one iris images having different pupil radius for preventing misidentification or usage of a forged inorganic iris.

30. An iris identification system of claim 29 wherein the pupil radius is adjusted by adjusting luminance around an eyepiece of the image input means using visible ray.

31. An iris identification system of claim 30 wherein the luminance around eyepiece is further adjusted using invisible ray if the adjusted luminance is lower than a predetermined luminance.

32. An iris identification system of claim 25 wherein the image analysis module immediately outputs denial result if the target class does not exist.

33. An iris identification system of claim 25 wherein the image analysis module scales the presented image as in corresponding iris image size if the target class exists.

34. An iris identification system of claim 33 wherein the image analysis module compares the presented image and the target reference iris image in unit of block in consideration with absolute positions of the blocks.

35. An iris identification system of claim 34 wherein the image analysis module classifies data in the block into main, auxiliary, and negative main data according to pixel density and assigns a band priority.

36. An iris identification system of claim 35 wherein the image analysis module analyzes similarity of corresponding main, auxiliary, and negative main data of the blocks by reflecting the band priority, determines whether or not the similarity satisfies a predetermined condition of the security, and outputs analysis result for identification.

37. An iris identification system of claim 36 wherein the image analysis module gives the block similarity weight according to the band priority of the block.

38. An iris identification system of claim 37 wherein the image analysis module reflects the data similarities of the main, auxiliary, and negative main data to the final result as absolute factors.

39. An iris identification system of claim 36 wherein the image analysis module reflects data similarities of upper and lower level and compensation level of the auxiliary data to the final result.

40. An iris identification system of claim 39 wherein the image analysis module outputs the final result together with a reflection degree of the compensation level of the auxiliary data.

41. An iris identification method comprising the steps of:

(a) taking a plurality of iris images from a human eye through an input means;

(b) classifying the iris images into at least one class;

(c) registering the iris images to corresponding classes as reference iris images per the human eye;

(d) storing the reference iris images in a storage medium;

(e) receiving a plurality of iris instances of a person for identification;

(f) retrieving target reference iris image by comparing each iris instance to reference iris images in a corresponding class;

(g) determining whether the iris instance is identified or denied.

42. An iris identification method of claim 41 further comprises the step of selecting the iris images having different pupil radius to the identical human eye after the step (a).

43. An iris identification method of claim 42 further comprises the step of adjusting pupil radium for taking iris images having different pupil radius.

44. An iris identification method of claim 43 wherein the pupil radium is adjusted by controlling luminance around an eyepiece of the image input means.

45. An iris identification method of claim 44 wherein the luminance is adjusted by irradiating visible ray around the eyepiece.

46. An iris identification method of claim 45 wherein the luminance is further adjusted by irradiating invisible ray if the luminance is lower than a predetermined standard luminance.

47. An iris identification method of claim 41 wherein the classes are defined according to the pupil radius.

48. An iris identification method of claim 41 wherein the step (d) comprises the steps of:

(d1) vertically dividing each iris image on the basis of horizontal line passing the center of the pupil for forming a plurality of bands;

(d2) creating data blocks by symmetrically dividing the bands;

(d3) encoding the iris image in unit of block;

(d4) storing the iris image as the reference iris image.

49. An iris identification method of claim 47 wherein the classes are defined by dividing a distance between minimum pupil radium and maximum pupil radium by a predetermined interval in a range of an iris radium.

50. An iris identification method of claim 49 wherein the iris image is stored as absolute coordinates data in relation to the center of the pupil.

51. An iris identification method of claim 50 wherein the iris image is stored together with information of the bands.

52. An iris identification method of claim 51 wherein the information of the band includes reference priority.

53. An iris identification method of claim 52 wherein the bands are symmetrically divided by a vertical line passing the center of the pupil so as to create a plurality of blocks.

54. An iris identification method of claim 53 wherein the blocks have different sizes according to locations thereof in space between the pupil and iris boundaries.

55. An iris identification method of claim 54 wherein the block contains a main, auxiliary, and negative main data classified by pixel density.

56. An iris identification method of claim 53 wherein the auxiliary data is an area where luminance of the area is less than a predetermined standard luminance and the main data is a portion of the auxiliary data where the pixel density is greater than a predetermined value.

57. An iris identification method of claim 55 wherein the negative main data is a portion where the pixel density is greater than a predetermined standard value in an area of which luminance is greater than the predetermined standard luminance.

58. An iris identification method of claim 56 wherein the auxiliary data is divided into upper and lower luminance level portions on the basis of a predetermined division luminance level such that the auxiliary data is stored with information on one of the upper and lower luminance level portions.

59. An iris identification method of claim 58 wherein the auxiliary data has a compensation level portion formed around the predetermined division luminance level such that data level of a vague iris image is compensated with the compensation level.

60. An iris identification method of claim 50 wherein the pupil center is calculated in such an order of obtaining a plurality of random pupil centers I_I, extracting candidate pupil centers from the random pupil centers, calculating a final pupil center T_p (x_p, y_p) using the candidate pupil centers.

61. An iris identification method of claim 60 wherein the random pupil center I_I, is obtained in such a manner of randomly selecting two points of S(x₁, y₁) and E(x₂, Y₂) on an actual pupil boundary, 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 on the basis of arc SE and point C thereon.

62. An iris identification method of claim 61 wherein the random pupil center I_i(x₀, y₀) is obtained as following calculations:

63. An iris identification system of claim 62 wherein the candidate pupil centers have radius that are in whole class range β

.

64. An iris identification system of claim 63 wherein the final pupil center T_p(x_p, y_p) is obtained as following calculations:

65. An iris identification system of claim 64 wherein a pupil boundary as following equation is calculated as following equation:

when I_min<

I_b<

I_ma,

$I_{\mathrm{mb}}=\frac{1}{N_b}<br><br>\sum <br><br>I_b$$\mathrm{where}<br><br>\text{\hspace{1em}<br><br>}<br><br>I_{\mathrm{ma}}=\frac{1}{N_a}<br><br>\sum <br><br>I_a,I_a<br><br>\left(I_b\right)$

is luminance of a pixel, I _ma(I_mb) is an average luminance, N_a(N_b) is number of executions, and I_min is a minimum luminance limit.

66. An iris identification method of claim 41 further comprises the steps of retrieving a target class when the iris image is presented and retrieving a target reference iris image in the class if the target class exists.

67. An iris identification method of claim 66 wherein the presented image is divided into a plurality of horizontal bands and the bands are divided in order for the bands are divided into symmetrical blocks such that the blocks are coded with main, auxiliary, and negative main data.

68. An iris identification method of claim 67 wherein the presented iris image is compared with the target reference iris image and analyzed in data similarity and band dependency.

69. An iris identification method of claim 68 wherein more than one iris images having different pupil radius are taken for preventing misidentification or usage of a forged inorganic iris.

70. An iris identification method of claim 69 wherein the pupil radius is adjusted by controlling luminance around an eye to provide the iris image using visible ray.

71. An iris identification method of claim 70 wherein the luminance is adjusted using invisible ray if the adjusted luminance is lower than a predetermined luminance.

72. An iris identification method of claim 66 wherein if the target class does not exist, a denial result is immediately outputted.

73. An iris identification method of claim 72 wherein the target reference iris image is retrieved in a class corresponding to the class of the presented iris image.

74. An iris identification method of claim 73 wherein if the garget class exists, the presented image is scaled in corresponding image size.

75. An iris identification method of claim 74 wherein the presented image and the target reference iris image are compared in unit of data block in consideration with absolute positions of the blocks.

76. An iris identification method of claim 75 wherein data of the block are classified into main, auxiliary, and negative main data according to pixel density and the block is assigned with a band priority.

77. An iris identification method of claim 76 wherein similarities of corresponding main, auxiliary, and negative main data of the block are analyzed by reflecting the band priority so as to be determined whether or not the similarity satisfies a predetermined condition of the security, and analysis result is outputted.

78. An iris identification method of claim 77 wherein the block is assigned with a similarity weight according to the band priority of the block.

79. An iris identification method of claim 78 wherein the data similarities of the main, auxiliary, and negative main data is reflected to final analysis result as absolute factors.

80. An iris identification method of claim 79 wherein the data similarities of upper and lower level an compensation level of the auxiliary data is reflected to the final analysis result.

81. An iris identification method of claim 80 wherein the final result is outputted together with a reflection degree of the compensation level of the auxiliary data.

92. A computer readable storage medium of claim 51 wherein the iris image is stored together with information of the bands.

93. A computer readable storage medium of claim 92 wherein the information of the band includes reference priority.

94. A computer readable storage medium of claim 93 wherein the bands are symmetrically divided by a vertical line passing the center of the pupil so as to create a plurality of blocks.

95. A computer readable storage medium of claim 94 wherein the blocks have different sizes according to locations thereof in space between the pupil and iris boundaries.

96. A computer readable storage medium of claim 95 wherein the block contains a main, auxiliary, and negative main data classified by pixel density.

97. A computer readable storage medium of claim 95 wherein the the auxiliary data is an area where luminance of the area is less than a predetermined standard luminance and the main data is a portion of the auxiliary data where the pixel density is greater than a predetermined value.

98. A computer readable storage medium of claim 97 wherein the negative main data is a portion where the pixel density is greater than a predetermined standard value in an area of which luminance is greater than the predetermined standard luminance.

99. A computer readable storage medium of claim 98 wherein the auxiliary data is divided into upper and lower luminance level portions on the basis of a predetermined division luminance level such that the auxiliary data is stored with information on one of the upper and lower luminance level portions.

100. A computer readable storage medium of claim 99 wherein the auxiliary data has a compensation level portion formed around the predetermined division luminance level such that data level of a vague iris image is compensated with the compensation level.

82. A computer readable storage medium stored therein computer executable instructions to implement an iris identification method, the iris identification method comprising the processes of:

taking a plurality of iris images from a human eye through an input means;

classifying the iris images into at least one class;

registering the iris images to corresponding classes as reference iris images per the human eye;

storing the reference iris images in a storage medium;

receiving a plurality of iris instances of a person for identification;

retrieving target reference iris image by comparing each iris instance to reference iris images in a corresponding class;

determining whether the iris instance is identified or denied.

83. A computer readable storage medium of claim 82 wherein the iris identification method further comprises a process of selecting the iris images having different pupil radius to an identical human eye.

84. A computer readable storage medium of claim 83 wherein the iris identification method further comprises a process of adjusting pupil radium for taking iris images having different pupil radius.

85. A computer readable storage medium of claim 84 wherein the pupil radium is adjusted by controlling luminance around an eyepiece of the image input means.

86. A computer readable storage medium of claim 85 wherein the luminance is adjusted by irradiating visible ray around the eyepiece.

87. A computer readable storage medium of claim 86 wherein the luminance is further adjusted by irradiating invisible ray if the luminance is lower than a predetermined standard luminance.

88. A computer readable storage medium of claim 82 wherein the classes are defined according to the pupil radius.

89. A computer readable storage medium of claim 82 wherein the process for storing the reference iris images in a storage medium comprises the steps of:

vertically dividing each iris image on the basis of horizontal line passing the center of the pupil for forming a plurality of bands;

creating data blocks by symmetrically dividing the bands;

encoding the iris image in unit of block;

storing the iris image as the reference iris image.

90. A computer readable storage medium of claim 88 wherein the classes are defined by dividing a distance between minimum pupil radium and maximum pupil radium by a predetermined interval in a range of an iris radium.

91. A computer readable storage medium of claim 89 wherein the iris image is stored as absolute coordinates data in relation to the center of the pupil.

101. A computer readable storage medium of claim 91 the pupil center is calculated in such an order of obtaining a plurality of random pupil centers I_I, extracting candidate pupil centers from the random pupil centers, calculating a final pupil center T_p(x_p, y_p) using the candidate pupil centers.

102. A computer readable storage medium of claim 101 wherein the random pupil center I_I is obtained in such a manner of randomly selecting two points of S(x₁, y₁) and E(x₂, y₂) on an actual pupil boundary, 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 on the basis of arc SE and point C thereon.

103. A computer readable storage medium of claim 102 wherein the random pupil center I_I(x₀, y₀) is obtained as following calculations:

104. A computer readable storage medium of claim 103 wherein the candidate pupil centers have radius that are in whole class range β

.

105. A computer readable storage medium of claim 104 wherein the final pupil center T_p(x_p, y_p) is obtained as following calculations:

106. A computer readable storage medium of claim 104 wherein a pupil boundary as following equation is calculated as following equation:

when I_min<

I_b<

I_ma

$I_{\mathrm{mb}}=\frac{1}{N_b}<br><br>\sum <br><br>I_b$

where

$I_{\mathrm{ma}}=\frac{1}{N_a}<br><br>\sum <br><br>I_a,I_a<br><br>\left(I_b\right)$

is luminance of a pixel, I_ma(I_mb) is an average luminance, N_a(N_b) is number of executions, and I_min is a minimum luminance limit.

107. A computer readable storage medium of claim 82 wherein the iris identification method further comprises the processes of retrieving a target class when the iris image is presented and retrieving a target reference iris image in the class if the target class exists.

108. A computer readable storage medium of claim 107 wherein the presented image is divided into a plurality of horizontal bands and the bands are divided in order for the bands are divided into symmetrical blocks such that the blocks are coded with main, auxiliary, and negative main data.

109. A computer readable storage medium of claim 108 wherein the presented iris image is compared with the target reference iris image and analyzed in data similarity and band dependency.

110. A computer readable storage medium of claim 109 wherein more than one iris images having different pupil radius are taken for preventing misidentification or usage of a forged inorganic iris.

111. A computer readable storage medium of claim 110 wherein the pupil radius is adjusted by controlling luminance around an eye to provide the iris image using visible ray.

112. A computer readable storage medium of claim 111 wherein the luminance is adjusted using invisible ray if the adjusted luminance is lower than a predetermined luminance.

113. A computer readable storage medium of claim 112 wherein if the target class does not exist, a denial result is immediately outputted.

114. A computer readable storage medium of claim 113 wherein the target reference iris image is retrieved in a class corresponding to the class of the presented iris image.

115. A computer readable storage medium of claim 114 wherein if the garget class exists, the presented image is scaled in corresponding image size.

116. A computer readable storage medium of claim 115 wherein the presented image and the target reference iris image are compared in unit of data block in consideration with absolute positions of the blocks.

117. A computer readable storage medium of claim 116 wherein data of the block are classified into main, auxiliary, and negative main data according to pixel density and the block is assigned with a band priority.

118. A computer readable storage medium of claim 117 wherein similarities of corresponding main, auxiliary, and negative main data of the block are analyzed by reflecting the band priority so as to be determined whether or not the similarity satisfies a predetermined condition of the security, and analysis result is outputted.

119. A computer readable storage medium of claim 118 wherein the block is assigned with a similarity weight according to the band priority of the block.

120. A computer readable storage medium of claim 119 wherein the data similarities of the main, auxiliary, and negative main data is reflected to final analysis result as absolute factors.

121. A computer readable storage medium of claim 120 wherein the data similarities of upper and lower level an compensation level of the auxiliary data is reflected to the final analysis result.

122. A computer readable storage medium of claim 121 wherein the final result is outputted together with a reflection degree of the compensation level of the auxiliary data.