Personal identification device and method

• US 7,627,145 B2
• Filed: 10/12/2007
• Issued: 12/01/2009
• Est. Priority Date: 09/06/2000
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Miyatake, Takafumi, Miura, Naoto, Nagasaka, Akio
• Primary Examiner(s): Bali; Vikkram
• Assistant Examiner(s): Seth; Manav
• Application Number:
  US11/907,421
• Publication Number:
  US 20080044066A1
• Time in Patent Office: 781 Days
• Field of Search: 382115-116, 382124-127, 382/132, 382180-181, 382190-195, 382/199, 382/202, 382/206, 382/209, 382218-221, 382224-228, 340/5.53, 340/5.83
• US Class Current: 382/115
• 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 40/1312 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. A personal identification method comprising the steps of:

irradiating light to a finger,

extracting an image of the light transmitted through the finger, and

identifying said image with a registered image by local matching of a part of said image,

wherein said local matching is processed by dividing said image and the registered image into a plurality of subregions and obtaining location information of the matching subregions, acquiring an extent of deviation of matching as movement information in each subregion from the initial location and evaluating correlativity of the movement information in each subregion.

2. The personal identification method according to claim 1, wherein said local matching is processed in addition to whole image matching between said image and the registered image.

3. The personal identification method according to claim 1, further comprising the step of:

tracking a blood vessel in said image by picking out loci in different locations and superposing them over one another to highlight a blood vessel pattern statistically.

4. The personal identification method according to claim 3, wherein pixels having the lowest luminous intensity are used for the initial location and pixels having the highest luminous intensity are also used as the initial location at a certain probability.

5. The personal identification method according to claim 3, wherein a direction easier for a certain tracking point to shift and a length of tracking of the tracking point are determined, and said tracking is discontinued when tracking has been done for a distance determined by the length.

6. The personal identification method according to claim 5, wherein after tracking is discontinued, the tracking point is shifted to the pixel having the lowest luminance intensity out of the trackable points, and the location is registered or updated as locus information so that the current tracking point is not tracked again.