Personal identification device and method

• US 20050281442A1
• Filed: 08/23/2005
• Published: 12/22/2005
• Est. Priority Date: 09/06/2000
• Status: Active Grant

• Current Assignee: Akio Nagasaka, Naoto Miura, Takafumi Miyatake
• Original Assignee: Akio Nagasaka, Naoto Miura, Takafumi Miyatake
• Inventors: Miyatake, Takafumi, Miura, Naoto, Nagasaka, Akio
• Granted Patent: US 7,280,676 B2
• Time in Patent Office: Days
• US Class Current: 382/124
• CPC Class Codes: G06V 10/10 Image acquisition document image scanning and transmission H04N1/00; control of digital cameras H04N23/60
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/12 Fingerprints or palmprints
• CPC Class Codes: G06V 40/1312 direct reading, e.g. contactless acquisition
• CPC Class Codes: G06V 40/1341 Sensing with light passing through the finger
• CPC Class Codes: G06V 40/14 Vascular patterns

Abstract

The invention aims at providing personal identification in environments where non-contact is required, with high accuracy even though using a finger vein pattern images unclear and susceptible to positional deviations, wherein it has: a means for acquiring finger vein patterns without contact; a means for carrying out rotational correction using the outline of a finger as a method of taking out a vein pattern contained in the acquired image; a means for normalizing the position of the finger image with reference to the fingertip; a means for acquiring an overall vein pattern statistically by repetitively tracking regions of dark luminance intensities for a desired length from a desired position in the image; a matching means for comparing regions where vein patterns manifest vivid features; and a means for independent matching of subregions and evaluating positional deviations where matching is recognized.

Claims

1-27. -27. (canceled)

28. A personal identification apparatus comprising:

a light source;

a camera which captures a light transmitted through a set finger to generate an image; and

an image processing unit which extracts a blood vessel pattern from an image captured by the camera and executes personal identification using the blood vessel pattern and a registered pattern,

wherein the image processing unit classifies pixels in the blood vessel pattern into three categories, these categories being a first category in which no blood vessel is supposed to be present, a second category in which a blood vessel is highly likely to be present and a third category in which a blood vessel may or may not be present, and

wherein the image processing unit executes personal identification using the pixels which are classified into the first and second categories.

29. A personal identification apparatus according to claim 28,

wherein the image processing unit counts the number of mismatching pixels in the blood vessel pattern and registered pattern, which are classified into the first and second categories, repeats the counting by shifting both patterns and decides the minimum number of mismatching pixels.

30. A personal identification apparatus according to claim 29,

wherein the image processing unit stops counting the number of mismatching pixiel at a shifted position when the number exceeds the number of mismatching pixels which are counted previously.

31. A personal identification apparatus according to claim 29,

wherein the image processing unit performs personal identification by calculating a ratio of the minimum number of mismatching pixels and a total number of pixels which are classified into the first category.

32. A personal identification apparatus according to claim 29,

wherein the image processing unit reduces a size of either the registered pattern or the blood vessel pattern by cutting out pixels on a circumference, and counts the number of mismatching pixels using the reduced pattern.

33. A personal identification apparatus according to claim 29,

wherein the image processing unit starts the counting at the position where central parts of the blood vessel pattern and the registered pattern are aligned.

34. A blood vessel pattern extraction apparatus for a personal identification comprising:

a light source;

a camera which captures a light transmitted through a set finger to generate an image; and

an image processing unit which extracts a blood vessel pattern from the image captured by the camera,

wherein the image processing unit classifies pixels in the blood vessel pattern into three categories, these categories being a first category in which no blood vessel is supposed to be present, a second category in which a blood vessel is highly likely to be present and a third category in which a blood vessel may or may not be present, and makes personal identification possible using the pixels which are classified into the first and second categories.

35. A blood vessel pattern extraction apparatus for a personal identification according to claim 34, wherein the image processing unit counts the number of mismatching pixels in the blood vessel pattern and registered pattern, which are classified into the first and second categories, repeats the counting by shifting both patterns and decides the minimum number of mismatching pixels.

36. A blood vessel pattern extraction apparatus for a personal identification according to claim 35, wherein the image processing unit stops counting the number of mismatching pixiel at a shifted position when the number exceeds the number of mismatching pixels which are counted previously.

37. A blood vessel pattern extraction apparatus for a personal identification according to claim 35, wherein the image processing unit reduces a size of either the registered pattern or the blood vessel pattern by cutting out pixels on a circumference, and counts the number of mismatching pixels using the reduced pattern.

38. A blood vessel pattern extraction apparatus for a personal identification according to claim 35,

wherein the image processing unit starts the counting at the position where central parts of the blood vessel pattern and the registered pattern are aligned.