Blood vessel image capturing device and personal authentication system
By irradiating near-infrared light on the back side of the blood vessel image capturing device and detecting the brightness saturated area when the finger is bent, the problem that the user cannot accurately confirm and verify when bending his finger is solved, and the effect of improving detection accuracy without increasing costs is achieved.
Patent Information
- Application Number
- CN202410628627.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2023-05-26
- Filing Date
- 2024-05-21
- Publication Date
- 2024-11-26
AI Technical Summary
The existing vascular image shooting device cannot accurately perform personal authentication when the user bends his fingers, and two cameras are required to detect finger bending, which increases the cost.
A vascular image shooting device is designed to detect the bending of the finger by irradiating near-infrared light on the back of the finger and photographing the finger from the ventral side. The light source and the camera device are used to detect the brightness saturated area of the joint part when the finger is bent, and the finger is bent through Control the amount of light and correct the image to achieve accurate personal authentication.
The user can accurately perform personal certification when bending his finger, which reduces costs and improves detection accuracy, avoiding the need to use multiple cameras.
Smart Images

Figure CN119027990A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to a blood vessel image shooting device and a personal authentication system. Background Art
[0002] As a biometric authentication device capable of performing high-precision personal authentication, there is a biometric authentication device using a blood vessel pattern. This is a biometric authentication device that performs personal authentication by comparing the finger blood vessel pattern that emerges when the finger is irradiated with near-infrared light with the information of the finger blood vessel pattern that has been registered in advance, using the fact that the blood vessel pattern varies from person to person.
[0003] In a biometric authentication device using a finger vein pattern, if the finger vein pattern is registered with the finger extended, but the user is to bend the finger for authentication, the finger vein pattern may be deformed due to the bending of the finger, and authentication may not be performed accurately.
[0004] Patent Document 1 describes that two cameras are provided in an authentication device, and distance measurement based on a general stereoscopic viewing technique is used to measure the distance between the finger surface and the device, thereby obtaining the state of the finger being lifted or bent.
[0005] Prior art literature
[0006] Patent Literature
[0007] Patent Document 1: Japanese Patent No. 6005750 Summary of the invention
[0008] Problems to be solved by the invention
[0009] The authentication device of Patent Document 1 can accurately perform user authentication by detecting the bending of a finger and correcting it, but it is necessary to install two cameras, which increases manufacturing costs.
[0010] An object of the present invention is to provide a technology that can accurately perform personal authentication even when a user bends his / her finger and extends it toward a blood vessel imaging device.
[0011] Technical solutions to solve problems
[0012] In order to solve the above-mentioned problems, one of the representative vascular image capturing devices of the present invention is a vascular image capturing device for capturing a vascular image of a user's finger, comprising: a light source for irradiating light to the back side of the finger; an imaging unit for capturing the irradiated finger from the ventral side of the finger; and a control unit for detecting a band-shaped brightness saturation area generated by light transmitted through a joint portion of the finger from the captured vascular image, thereby detecting finger bending.
[0013] Effects of the Invention
[0014] According to the present invention, even when the user bends his fingers and extends them toward the blood vessel imaging device, the present invention can accurately perform the user authentication.
[0015] Problems, structures, and effects other than those described above will be explained through the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 This is a side view showing an example of the structure of the blood vessel imaging device according to the first embodiment.
[0017] Figure 2A This is a side view showing an example of a state where a bent finger is photographed by the blood vessel imaging device of Example 1.
[0018] Figure 2B This is a diagram showing an example of a captured image when a light intensity 20% weaker than the light intensity at which the blood vessels of a finger are clearly reflected is irradiated.
[0019] Figure 2C This is a diagram showing an example of a captured image when the light intensity is irradiated to clearly show the blood vessels of a finger.
[0020] Figure 2D This is a diagram showing an example of a captured image when a light intensity 20% stronger than the light intensity at which the blood vessels of a finger are clearly reflected is irradiated.
[0021] Figure 3A This is a side view showing another example of a state where a bent finger is imaged using the blood vessel image capturing apparatus of the first embodiment.
[0022] Figure 3B This is a diagram showing an example of a captured image when the amount of light that does not generate reflected light in a saturated brightness region other than a light source is irradiated.
[0023] Figure 3C This is a diagram showing an example of a captured image when irradiating with an amount of light 1.5 times the amount of light that generates no reflected light in a saturated brightness region other than a light source.
[0024] Figure 3D This figure shows an example of a captured image when irradiating with light twice the amount of light in a saturated brightness region other than a light source that does not generate reflected light.
[0025] Figure 4A FIG. 1 is a diagram showing an example of a finger vein image captured by the vein image capturing device of Example 1 with the finger bent.
[0026] Figure 4B FIG. 1 is a diagram showing another example of a finger vein image captured by the vein image capturing apparatus of Example 1 with the finger bent.
[0027] Figure 4C FIG. 1 is a diagram showing an example of a finger vein image corrected by the vein image capturing apparatus 100 according to the first embodiment.
[0028] Figure 5 This is a diagram showing an example of the configuration of a personal authentication system according to the second embodiment.
[0029] Figure 6 This is a flowchart showing an example of the authentication process executed by the authentication device of the second embodiment.
[0030] Figure 7 It is a side view showing an example of the structure of the blood vessel imaging device according to the third embodiment.
[0031] Figure 8 This is a side view showing another example of the structure of the blood vessel imaging device according to the third embodiment.
[0032] Fig. 9 This is a side view showing another example of the structure of the blood vessel imaging device according to the third embodiment.
[0033] Fig. 10A This is a diagram for explaining the comparison of finger blood vessel patterns without using joint position additional information in the blood vessel image capturing device of the fourth embodiment.
[0034] Fig. 10B This is a diagram for explaining the comparison of finger blood vessel patterns using joint position additional information in the blood vessel image capturing device of the fourth embodiment.
[0035] Fig.11A This is a diagram showing an example of a display screen when a finger is stretched out on the blood vessel imaging device of the fifth embodiment.
[0036] Fig. 11B This is a diagram showing an example of a display screen when a bent finger is extended to the blood vessel image capturing device of Example 5. DETAILED DESCRIPTION
[0037] Hereinafter, embodiments will be described using the drawings.
[0038] [Example 1]
[0039] This embodiment is an example of a vascular image capturing device that captures a vascular pattern of a user's finger and has the function of detecting when the user bends the finger (hereinafter referred to as "finger bending") and correcting the finger vascular pattern that has been deformed due to the finger bending.
[0040] Figure 1 This is a side view showing an example of the structure of the blood vessel imaging device according to the first embodiment.
[0041] The blood vessel image capturing device 100 includes a plurality of light sources 102 for irradiating the back side of the finger 111 with near-infrared light 103 in order to capture the blood vessels of the finger 111, an upper cover 101 for accommodating the light sources 102, a support column 104 for supporting the upper cover 101, a fingertip-side finger placement table 105 and a finger base-side finger placement table 106 for placing the extended finger 111 when the blood vessel image capturing device 100 is used, an imaging device 110 for capturing a finger blood vessel image from the ventral side of the finger 111, an optical filter 112 for preventing the intrusion of foreign matter and dust and transmitting the near-infrared light 103 used for capturing, and a control device 113 for controlling the light source 102 and the imaging device 110.
[0042] When a finger 111 is extended to the blood vessel image capturing device 100, near infrared light 103 is irradiated from the back side of the finger 111 by the light source 102. The near infrared light 103 is blocked by the finger 111, but a part of it passes through the finger 111. Since hemoglobin contained in the blood blocks the near infrared light more strongly than other parts of the living body, the blood vessel pattern is reflected as a dark line in the image captured by the imaging device 110.
[0043] In addition, the blood vessel image capturing device 100 may include a reflected light source 108 that irradiates the ventral side of the finger 111 with near infrared light 109. The near infrared light 109 irradiated from the reflected light source 108 is reflected on the surface of the finger 111, or enters the inside of the finger 111 and is scattered and then emitted again from the surface of the finger 111. The near infrared light 109 is captured by the imaging device 110.
[0044] Next, in an example where the user bends the finger 111 and extends it toward the blood vessel image capturing device 100, the back side of the finger 111 is illuminated by the light source 102 and captured by the imaging device 110, the following is an example of using Figure 2A-2D Provide explanation.
[0045] Figure 2A FIG. 1 is a side view showing an example of a state where a bent finger is photographed by the blood vessel imaging device 100 according to the first embodiment. Figure 2B 1 is a diagram showing an example of a captured image when irradiation is performed with a light intensity 20% weaker than the light intensity at which the blood vessels of a finger are clearly shown. Figure 2C 1 is a diagram showing an example of a captured image when the amount of light is irradiated to clearly show the blood vessels of a finger. Figure 2D This is a diagram showing an example of a captured image when a light intensity 20% stronger than the light intensity at which the blood vessels of a finger are clearly reflected is irradiated.
[0046] Figure 2AIn the embodiment, the back side of the bent finger 111 is irradiated with near infrared light 103 from the light source 102, and the image is taken by the camera 110. The control device 113 obtains the image by adjusting the light intensity of the light source 102 to a light intensity 20% weaker than the light intensity that clearly reflects the blood vessels of the finger 111, a light intensity that clearly reflects the blood vessels of the finger 111, and a light intensity 20% stronger than the light intensity that clearly reflects the blood vessels of the finger 111, and taking the image. Figure 2B , 2C , captured images 202, 206, 210 shown in 2D.
[0047] Figure 2B , Figure 2C , Figure 2D In the captured images 202, 206, and 210, near-infrared light 103 easily penetrates the first and second joints of the bent finger 111, so that areas 204, 205, 208, 209, 212, and 213 with saturated brightness appear in the joints, extending in a thin band in the width direction of the finger 111. Brightness saturation means that when the brightness of an image captured by the camera 110 exceeds the upper limit of the brightness that can be expressed by the camera 110, the image is actually brighter but is limited to the upper limit of the brightness that can be expressed by the camera 110.
[0048] Figure 2B , Figure 2C , Figure 2D In any of the captured images 202 , 206 , and 210 , brightness saturated areas 204 , 205 , 208 , 209 , 212 , and 213 clearly appear in the first joint and the second joint of the bent finger 111 .
[0049] When the finger 111 is extended toward the blood vessel image capturing device 100, the brightness saturation area appears wider in both the vertical and horizontal directions. When the light intensity of the light source 102 is increased, the brightness saturation area expands in both the vertical and horizontal directions, and when the light intensity of the light source 102 is reduced, the brightness saturation area shrinks in both the vertical and horizontal directions.
[0050] On the other hand, when the finger 111 is bent and extended toward the blood vessel image capturing device 100, a band-shaped saturated brightness region in the width direction of the finger 111, which has the same width as the finger 111 and does not change even when the light amount changes within a range of ±20%, clearly appears near the joint portion of the finger 111. Therefore, the control device 113 can detect that the bent finger 111 is extended toward the blood vessel image capturing device 100 by detecting this saturated brightness region.
[0051] The strip-shaped saturated brightness region has the characteristic of appearing in parallel in two strips at the first joint and the second joint of the finger 111 at the same distance as the interval between the two joints. In addition, both saturated brightness regions have the characteristic of being long in the finger width direction and being orthogonal to the length direction of the finger by the length of the finger width. In addition, since the blood vessels of the finger extend in the length direction of the finger as a whole in order to supply blood to the end of the finger, the strip-shaped saturated brightness region also has the characteristic of being orthogonal to the overall flow direction of the blood vessels of the finger.
[0052] The control device 113 can detect the bending of the finger by recognizing the saturated brightness areas 204 , 205 , 208 , 209 , 212 , and 213 of the joint parts caused by the bending of the finger based on these features.
[0053] In addition, the control device 113 can detect the positions of the first joint and the second joint of the finger 111 by detecting the positions of the strip-shaped brightness saturation areas 204 , 205 , 208 , 209 , 212 , and 213 of the captured images 202 , 206 , and 210 while detecting the bending of the finger.
[0054] In addition, the accuracy of detecting the bending of the finger can be improved by utilizing the fact that when the finger 111 is bent and extended toward the blood vessel image capturing device 100, the ends of the fingertip and the base of the finger are reflected darker than when the finger 111 is extended and extended toward the blood vessel image capturing device 100, and that when the finger 111 is bent and extended toward the blood vessel image capturing device 100, the fingertip and the base of the finger are enlarged and reflected with a thicker width because they are close to the imaging device 110, while the finger width in the middle part of the finger is reflected with a narrower width, together with the detection of the strip-shaped saturated brightness areas 204, 205, 208, 209, 212, and 213.
[0055] In addition, the control device 113 obtains the angles from the first joint to the fingertip and from the second joint to the base of the finger of the finger 111, and obtains the degree of bending of the finger, such as whether the finger is bent more or less. In order to obtain the degree of bending of the finger, the change rate of the finger width determined by the distance from the joint is investigated from the first joint to the fingertip side and from the second joint to the base of the finger, and compared with the change rate of the average finger width obtained in advance, thereby calculating the angles from the first joint to the fingertip and from the second joint to the base of the finger.
[0056] In addition, the rate of change of the brightness of the finger 111 determined by the distance from the joint is investigated from the first joint to the fingertip side and from the second joint to the finger base side, and compared with the average rate of change of brightness obtained in advance, thereby calculating the angle from the first joint to the fingertip side and from the second joint to the finger base.
[0057] Alternatively, machine learning may be performed in advance based on finger vascular images of the finger 111 bent at various angles and finger vascular images of the finger 111 stretched to estimate whether the finger is bent and the angles from the first joint of the finger 111 to the fingertip and from the second joint of the finger to the base of the finger, and the learning results may be used to estimate whether the finger is bent and the angles from the first joint of the finger to the fingertip and from the second joint of the finger to the base of the finger based on the captured images.
[0058] Next, in an example in which a user bends a finger 111 and extends it toward the blood vessel image capturing device 100, the ventral side of the finger 111 is illuminated by the reflected light source 108 and captured by the imaging device 110, the following is used. Figure 3A-3D Provide explanation.
[0059] Figure 3A FIG. 2 is a side view showing another example of a state where a bent finger is photographed by the blood vessel image capturing apparatus 100 according to the first embodiment. Figure 3B 1 is a diagram showing an example of a captured image when the amount of light that does not generate a brightness saturation area outside the reflected light source 108 is irradiated. Figure 3C 1 is a diagram showing an example of a captured image when irradiating with an amount of light 1.5 times the amount of light that does not cause reflection into the brightness saturation area other than the reflected light source 108. Figure 3D This figure shows an example of a captured image when twice the amount of light is irradiated so as not to cause reflection in a saturated brightness region other than the reflected light source 108 .
[0060] Figure 3A In the embodiment, near infrared light 109 is irradiated from the reflected light source 108 to the ventral side of the bent finger 111, and the image is taken by the camera 110. The control device 113 obtains the image by adjusting the light amount of the reflected light source 108 to the amount of light that does not reflect into the brightness saturation area other than the reflected light source 108, the amount of light that is 1.5 times the amount of light that does not reflect into the brightness saturation area other than the reflected light source 108, and the amount of light that is twice the amount of light that does not reflect into the brightness saturation area other than the reflected light source 108, and taking the image. Figure 3B , Figure 3C , Figure 3D The captured images 301 , 308 , 316 are shown.
[0061] Figure 3B , Figure 3C , Figure 3DIn any of the captured images 301, 308, and 316, linear dark portions 306, 307, 313, 314, 321, and 322 due to joint wrinkles appear at the first joint and the second joint of the bent finger 111. The control device 113 can detect the bending of the finger by detecting the linear dark portions 306, 307, 313, 314, 321, and 322 due to joint wrinkles.
[0062] The linear dark portions 306, 307, 313, 314, 321, 322 caused by joint wrinkles have the characteristic of appearing in parallel in two lines at the first joint and the second joint at the same distance as the interval between the two joints, similarly to the band-shaped brightness saturation areas 204, 205, 208, 209, 212, 213 in FIG. 2. In addition, the linear dark portions caused by the two joint wrinkles are both long in the finger width direction and perpendicular to the finger length direction by the length of the finger width. In addition, since the finger blood vessels extend in the length direction of the finger 111 as a whole in order to supply blood to the end of the finger 111, the linear dark portions 306, 307, 313, 314, 321, 322 caused by joint wrinkles also have the characteristic of being perpendicular to the overall flow direction of the finger blood vessels.
[0063] The control device 113 can detect the bending of the finger by recognizing the linear dark parts 306 , 307 , 313 , 314 , 321 , and 322 caused by the joint wrinkles caused by the bending of the finger based on these characteristics.
[0064] in addition, Figure 3B , Figure 3C , Figure 3D In the captured images 301 , 308 , and 316 , portions 303 , 310 , and 318 with high brightness in the center of the finger 111 and brightness saturated areas 304 , 305 , 311 , 312 , 315 , 319 , 320 , and 323 appear.
[0065] In circular saturated brightness regions 304 , 305 , 311 , 312 , 319 , and 320 , the region where near infrared light 109 emitted from reflected light source 108 is reflected on optical filter 112 and projected in the captured image overlaps with the region formed by near infrared light 109 reflected on finger 111 .
[0066] Figure 3C In the captured image 308, in the portion 310 with higher brightness in the center of the finger 111, in addition to the brightness saturated regions 311 and 312 generated by the reflection of the reflected light source 108 on the optical filter 112, a brightness saturated region 315 is also generated in the central part of the finger 111.
[0067] Figure 3D In the captured image 316, in the portion 318 with high brightness at the center of the finger 111, in addition to the brightness saturation regions 319 and 320 generated by the reflection of the reflected light source 108 on the optical filter 112, a portion 318 with high brightness at the center of the finger 111 also generates a portion 318 with high brightness at the center of the finger 111. Figure 3C The brightness saturation area 315 is larger than the brightness saturation area 323.
[0068] When the finger 111 is extended toward the blood vessel image capturing device 100, a brightness saturation area is generated due to the reflection of the reflected light source 108 on the optical filter 112. When the light amount of the light source 102 is enhanced, a brightness saturation area is generated in the central part of the finger 111. When the light amount of the light source 102 is further enhanced, these brightness saturation areas are further increased to become a larger brightness saturation area.
[0069] On the other hand, when the finger 111 is bent and extended toward the blood vessel imaging device 100, even if the light amount changes by 2 times, independent saturated brightness areas 319, 320, and 323 appear. Therefore, the control device 113 can improve the accuracy of detecting the bending of the finger by utilizing the fact that the independent saturated brightness areas 319, 320, and 323 appear even if the light amount is increased, together with the detection of the linear dark parts 306, 307, 313, 314, 321, and 322 caused by the joint wrinkles.
[0070] Next, in an example of correcting the deformation of the finger vein pattern caused by the bending of the finger when the bending of the finger is detected by the vein image capturing device 100, the following is an example of correcting the deformation of the finger vein pattern caused by the bending of the finger. Figure 4A-4C Provide explanation.
[0071] Figure 4A FIG. 1 is a diagram showing an example of a finger vein image captured by the vein image capturing apparatus 100 of the first embodiment with the finger 111 bent. Figure 4B FIG. 2 is a diagram showing another example of a finger vein image captured by the vein image capturing apparatus 100 of the first embodiment with the finger 111 bent. Figure 4C FIG. 1 is a diagram showing an example of a finger vein image corrected by the vein image capturing apparatus 100 according to the first embodiment.
[0072] Figure 4A , Figure 4B The finger vein images 401 and 408 are finger vein images captured by the imaging device 110 when the finger 111 is bent and extended to the vein image capturing device 100, and the finger vein patterns are reflected as dark lines.
[0073] Figure 4AIn the finger vein image 401, in the width direction of the finger 111, compared with the case where the finger 111 is stretched out toward the vein image capturing device 100, the central portion between the first joint and the second joint of the finger 111 is reflected in a smaller size because it is far away from the imaging device 110, and the fingertip portion and the finger base portion are reflected in an enlarged size toward the fingertip direction and the finger base direction because they are relatively close to the imaging device 110.
[0074] In the finger vein image 401 , in the longitudinal direction of the finger 111 , the center portion between the two joints is located at a higher vertical position, so the first joint to the fingertip side and the second joint to the finger base side are tilted in the vertical direction and are thus projected in a smaller size.
[0075] Thus, the control device 113 is as follows Figure 4A As shown, in the finger vein image 401 deformed by the bending of the finger, the first joint to the fingertip side and the second joint to the finger base side are stretched in the directions of arrows 402 and 403 in the length direction of the finger 111, and the finger 111 is reduced in the directions of arrows 404, 405, 406, and 407 in the width direction of the finger 111 so that the image is reduced toward the end of the fingertip side and the finger base side, thereby correcting the deformation of the finger vein pattern. This correction can be achieved by using a general image keystone correction.
[0076] In addition, if Figure 4B As shown, depending on the shape of the finger base side finger placement stand 106 and the properties of the finger 111, when the finger 111 is extended and extended to the blood vessel image capturing device 100, the finger 111 is flattened on the finger base side, thereby widening the finger base side in the finger width direction, and when the finger 111 is bent and extended to the blood vessel image capturing device 100, the finger base side is inclined in the vertical direction and floats, and there is a case where the finger base side is smaller in the finger width direction than when the finger 111 is extended. Therefore, in the finger blood vessel image 408, the finger base side is reflected thinner than the fingertip and the center of the finger.
[0077] In this case, the control device 113 is as follows Figure 4B As shown, in the finger vein image 408 deformed due to the bending of the finger, the length direction of the finger 111 is different from the length direction of the finger 111. Figure 4A Similarly, the first joint to the fingertip side and the second joint to the finger base side are stretched in the directions of arrows 409 and 410, and the width direction of the finger 111 is reduced in the directions of arrows 412 and 414 in a manner that the closer to the end of the fingertip side, the larger the end is, and the stretching in the directions of arrows 411 and 413 is to correct the deformation of the finger blood vessel pattern. This correction can be used with Figure 4A The same keystone correction, through Figure 4AThis is achieved by changing the direction of the trapezoidal correction on the finger base side compared to the situation.
[0078] In addition, regarding deformation correction, a finger vein image that has been deformed due to finger bending and a finger vein image that has not been deformed when the finger is stretched may be used, and learning may be performed in advance using machine learning to infer the finger vein image that has not been deformed when the finger is stretched from the finger vein image that has been deformed due to finger bending. The learning result may be used to infer the finger vein image that has not been deformed when the finger is stretched from the finger vein image that has been deformed due to finger bending.
[0079] According to the present embodiment, the control device 113 detects the bending of the finger by detecting the brightness saturation area of the joint part caused by the bending of the finger, or the linear dark part caused by the joint wrinkles, so that the fingertip side and the base side of the finger vascular image are stretched in the finger length direction, the fingertip side of the finger vascular image is stretched in the finger width direction, and the base side of the vascular image is stretched or reduced in the finger width direction, thereby correcting the vascular image. Therefore, even when the user bends his finger and extends it to the vascular image capturing device, the user can accurately perform the self-authentication.
[0080] [Example 2]
[0081] This embodiment is an example of a personal authentication device system using the blood vessel image capturing device 100 of the first embodiment.
[0082] Figure 5 This is a diagram showing an example of the configuration of a personal authentication system according to the second embodiment. Figure 5 In Figure 1 The same structure is assigned the same reference numerals and the description thereof is omitted.
[0083] Figure 5 The personal authentication system includes a blood vessel image pickup device 100 and an authentication device 500 connected to the blood vessel image pickup device 100. In the first embodiment, the control device 113 of the blood vessel image pickup device 100 controls the light source 102 and detects the finger bending, but in the second embodiment, these processes are executed by the authentication device 500.
[0084] The authentication device 500 includes a near-infrared image input unit 502 , a near-infrared light source control unit 503 , an interface 504 , an external storage device 505 , a CPU (Central Processing Unit) 506 , a memory 507 , a display device 508 , a keyboard 509 , and a speaker 510 .
[0085] When the user extends a finger 111 to the blood vessel image capturing device 100 connected to the authentication device 500 , the imaging device 110 converts the image captured through the optical filter 112 into an electrical signal, which is imported into the CPU 506 as an image via the near-infrared light image input unit 502 and the interface 504 and recorded in the memory 507 .
[0086] The CPU 506 executes the program stored in the memory 507 to detect from the captured image recorded in the memory 507 that the light weakly irradiated from the light source 102 is blocked by the finger 111 , and recognizes that the finger 111 is extended toward the blood vessel imaging device 100 .
[0087] When recognizing that the finger 111 is extended, the CPU 506 executes a program stored in the memory 507 to control the near-infrared light source control unit 503 via the interface 504 to radiate near-infrared light 103 sufficient for capturing a finger blood vessel image from the light source 102 .
[0088] The image of the finger 111 irradiated with near-infrared light 103 from the light source 102 is converted into an electrical signal by the camera device 110 through the optical filter 112 , imported into the CPU 506 as an image via the near-infrared light image input unit 502 and the interface 504 , and recorded in the memory 507 .
[0089] CPU 506 performs user authentication by executing a program recorded in memory 507 to compare the image recorded in memory 507 with one or more finger vein patterns registered in advance in external storage device 505. The result of user authentication is notified to the user by voice through speaker 510 or by display on display device 508 in accordance with instructions from keyboard 509.
[0090] In addition, in this embodiment, the authentication device 500 and the blood vessel image capturing device 100 are described as separate devices, but the blood vessel image capturing device may be configured as a blood vessel image capturing unit having a capturing unit that captures a finger blood vessel image and an authentication unit that performs user authentication based on information from the captured finger blood vessel image.
[0091] Figure 6 1 is a flowchart showing an example of the authentication process executed in the authentication device of Example 2. This process is realized by the CPU 506 executing the program stored in the memory 507 .
[0092] First, when the user extends the finger 111 to the blood vessel image capturing device 100, the light source 102 irradiates the back side of the finger 111 with near infrared light 103 (step S602), and the camera 110 captures the finger 111 from the ventral side to obtain a captured image (step S603).
[0093] Next, the finger is detected from the captured image acquired in step S603 (step S604), and it is determined whether the finger is detected from the captured image in step S604 (step S605). If it is determined in step S605 that the finger is detected from the captured image, the process proceeds to step S606, and if it is determined in step S605 that the finger is not detected from the captured image, the process returns to step S602.
[0094] In step S606, the average brightness of the finger detected in the acquired captured image is calculated. The average brightness of the finger is calculated by, for example, calculating the average brightness of the portion of the captured image where the finger is necessarily reflected when the finger is detected from the captured image.
[0095] Next, it is determined whether the average brightness of the finger calculated in step S606 is between the upper and lower limits of the target brightness (step S607). If the average brightness of the finger is not between the upper and lower limits of the target brightness in step S607, the process proceeds to step S608; if the average brightness of the finger is between the upper and lower limits of the target brightness in step S607, the process proceeds to step S609.
[0096] In step S608, the light source 102 is controlled to increase the light intensity when the average brightness of the finger is lower than the lower limit of the target brightness, and to decrease the light intensity when the average brightness of the finger exceeds the upper limit of the target brightness, and the process returns to step S602.
[0097] In step S609, by detecting the saturated brightness area or dark portion described in FIG. 2 or FIG. 3 from the captured image, it is detected whether the user bends the finger 111 and extends it to the blood vessel image capturing device 100, and the degree of finger bending is detected when the user bends the finger 111 and extends it to the blood vessel image capturing device 100. The degree of finger bending is detected by calculating the angle from the first joint to the fingertip and the angle from the second joint to the finger base as described in FIG.
[0098] Next, based on the degree of finger bending detected in step S609 , the deformation of the finger vein image generated when the user bends the finger and extends it toward the vein image capturing apparatus 100 is corrected (step S610 ).
[0099] Next, the finger contour is detected from the finger vein image to clarify the region of the finger 111 in the finger vein image (step S611 ), and a finger vein pattern for comparison is generated based on the finger vein image (step S612 ).
[0100] Next, the finger vein pattern 614 pre-registered in the external storage device 505 and the finger vein pattern generated from the captured image in step S612 are compared (step S613), and a score of the degree of inconsistency between the vein patterns is calculated as a comparison score. The comparison score is calculated, for example, by performing template matching to investigate whether a pattern of a certain image exists in another image, investigating the number of pixels that are consistent with the registered finger vein pattern 614 while gradually shifting the position of the investigated finger vein pattern, and calculating the number of inconsistent pixels at the position with the most consistent pixels.
[0101] Next, it is determined whether the calculated comparison score is lower than the threshold value (step S615). In step S615, if it is determined that the calculated comparison score is lower than the threshold value, it is determined that the generated finger vein pattern is consistent with the registered finger vein pattern 614, and the process proceeds to step S616 to perform post-authentication success processing and end the process.
[0102] On the other hand, if it is determined in step S615 that the calculated comparison score is not lower than the threshold, it is determined that the generated finger vein pattern does not match the registered finger vein pattern 614, and the process proceeds to step S617 to perform post-authentication failure processing and end the process.
[0103] According to the present embodiment, by detecting a brightness saturated area or a dark portion from the captured image, it is detected whether the user bends the finger 111 and extends it toward the blood vessel image capturing device 100. When the user bends the finger 111 and extends it toward the blood vessel image capturing device 100, the degree of the finger bending is detected (step S609), and the deformation of the finger blood vessel image is corrected according to the detected degree of the finger bending (step S610). Therefore, even when the user bends the finger and extends it toward the blood vessel image capturing device, personal authentication can be accurately performed.
[0104] [Example 3]
[0105] This embodiment is an example in which the arrangement of the light source is changed in the blood vessel image capturing device of the first embodiment in order to improve the accuracy of detecting the bending of the finger and the degree of the bending of the finger and to capture a clear finger blood vessel image.
[0106] Figure 7 1 is a side view showing an example of the structure of a blood vessel imaging device 100 according to the third embodiment. Figure 7 In Figure 1 The same structure is assigned the same reference numerals and the description thereof is omitted.
[0107] Figure 7 The blood vessel image capturing device 100 is Figure 1In addition to the structure of the present invention, there are also a fingertip side light source 701 and a finger base side light source 702. The fingertip side light source 701 is arranged to be tilted toward the fingertip side compared to the vertical direction downward, and irradiates the back side of the finger 111 with near infrared light 703. In addition, the finger base side light source 702 is arranged to be tilted toward the finger base side compared to the vertical direction downward, and irradiates the back side of the finger 111 with near infrared light 704.
[0108] When the finger 111 is bent and extended toward the vascular image capturing device 100, the near-infrared light 703, 704 irradiated to the fingertip and base obliquely irradiates the surface of the finger 111, so the path of the near-infrared light 703, 704 when passing through the inside of the finger 111 becomes longer, and the fingertip and base are easily reflected darker in the image captured by the camera device 110.
[0109] Thus, when the finger 111 is extended and extended toward the vascular image capturing device 100, and when the finger 111 is bent and extended toward the vascular image capturing device 100, the difference in brightness between the fingertip side and the finger base side is large, and the accuracy of detecting the finger bending and the degree of the finger bending can be improved.
[0110] The fingertip side light source 701 is preferably arranged so that the optical axis angle 705 from the vertical direction is within the range of 10 to 80 degrees on the fingertip side. The finger base side light source 702 is preferably arranged so that the optical axis angle 706 from the vertical direction is within the range of 10 to 80 degrees on the finger base side.
[0111] according to Figure 7 In the example of FIG. 1 , since the fingertip side light source 701 and the finger base side light source 702 are also provided, the difference in brightness between the fingertip side and the finger base side is large when the finger 111 is extended and extended toward the vascular image capturing device 100 and when the finger 111 is bent and extended toward the vascular image capturing device 100, the accuracy of detecting the bending of the finger and the degree of the bending of the finger can be improved, and the user can be accurately authenticated even when the user bends the finger and extends it toward the vascular image capturing device.
[0112] Figure 8 FIG. 1 is a side view showing another example of the structure of the blood vessel imaging device 100 according to the third embodiment. Figure 8 In Figure 1 The same structure is assigned the same reference numerals and the description thereof is omitted.
[0113] Figure 8 The blood vessel image capturing device 100 is Figure 1In addition to the structure of the present invention, there are also a fingertip side light source 801 and a finger base side light source 802. The fingertip side light source 801 is arranged to be tilted toward the finger base side compared to the vertical direction downward, and irradiates the back side of the finger 111 with near infrared light 804. In addition, the finger base side light source 802 is arranged to be tilted toward the fingertip side compared to the vertical direction downward, and irradiates the back side of the finger 111 with near infrared light 803.
[0114] and Figure 7 Compared with the fingertip side light source 701 and the finger base side light source 702, the fingertip side light source 701 and the finger base side light source 702 are tilted more from the vertical direction. Therefore, when the finger 111 is bent to a small extent, the near infrared light 803 and 804 irradiated to the fingertip and the finger base also irradiates the surface of the finger obliquely, so the path of the near infrared light 803 and 804 passing through the inside of the finger 111 becomes longer, and the fingertip and the finger base are easily reflected darker in the image captured by the camera device 110.
[0115] Thus, when the finger 111 is extended and extended toward the vascular image capturing device 100, and when the finger 111 is bent and extended toward the vascular image capturing device 100, the difference in brightness between the fingertip side and the finger base side is large, and the accuracy of detecting the finger bending and the degree of the finger bending can be improved.
[0116] The fingertip side light source 801 is preferably arranged so that the optical axis angle 805 from the vertical direction is within the range of 10 to 80 degrees on the finger base side. In addition, the finger base side light source 802 is preferably arranged so that the optical axis angle 706 from the vertical direction is within the range of 10 to 80 degrees on the fingertip side.
[0117] according to Figure 8 In the example of , since there are also a fingertip side light source 801 and a finger base side light source 802, when the degree of bending of the finger 111 is small, the difference in brightness between the fingertip side and the finger base side is large when the finger 111 is stretched and extended toward the vascular image capturing device 100, and when the finger 111 is bent and extended toward the vascular image capturing device 100. This can improve the accuracy of detecting the bending of the finger and the degree of bending of the finger, and can accurately perform self-authentication even when the user bends his finger and extends it toward the vascular image capturing device.
[0118] Fig. 9 FIG. 1 is a side view showing another example of the structure of the blood vessel imaging device 100 according to the third embodiment. Fig. 9 In Figure 1 The same structure is assigned the same reference numerals and the description thereof is omitted.
[0119] Fig. 9 The blood vessel image capturing device 100 is Figure 1In addition to the structure of the present invention, there are also fingertip side additional light sources 901 and finger base side additional light sources 902. The fingertip side additional light sources 901 are arranged to be tilted toward the finger base side compared to the vertical direction downward, and irradiate the back side of the finger 111 with near infrared light 903. In addition, the finger base side additional light sources 902 are arranged to be tilted toward the fingertip side compared to the vertical direction downward, and irradiate the back side of the finger 111 with near infrared light 904.
[0120] Thus, when the user bends the finger 111 and extends it toward the blood vessel image capturing device 100 , it is possible to prevent the finger tip and the base from becoming dark, thereby obscuring the finger vein image and failing to extract an accurate finger vein pattern.
[0121] The fingertip additional light source 901 is preferably arranged so that the optical axis angle 905 from the vertical direction is within the range of 10 to 80 degrees on the finger base side. The finger base additional light source 902 is preferably arranged so that the optical axis angle 906 from the vertical direction is within the range of 10 to 80 degrees on the fingertip side.
[0122] according to Fig. 9 For example, by also providing an additional light source 901 on the fingertip side and an additional light source 902 on the finger base side, when the user bends the finger 111 and extends it toward the blood vessel image capturing device 100, it is possible to prevent the finger vein image from becoming unclear due to the darkening of the fingertip and the finger base, and prevent the accurate finger vein pattern from being extracted. Even when the user bends the finger and extends it toward the blood vessel image capturing device, it is possible to accurately perform self-authentication.
[0123] [Example 4]
[0124] This embodiment is an example of reducing the search range for position alignment of finger blood vessel patterns and shortening the processing time required for matching finger blood vessel patterns by using the positions of the first and second joints of the finger acquired together when detecting finger bending.
[0125] Fig. 10A FIG. 1 is a diagram for explaining comparison of finger blood vessel patterns without using joint position additional information in the blood vessel image capturing device of the fourth embodiment. Fig. 10B This is a diagram for explaining the comparison of finger blood vessel patterns using joint position additional information in the blood vessel image capturing device of the fourth embodiment.
[0126] Fig. 10A In the embodiment, the registered blood vessel pattern 1001 registered in the external storage device 505 is compared with the input blood vessel pattern 1002 generated from the captured image by the blood vessel image capturing device 100.
[0127] Regarding the comparison between the registered blood vessel pattern 1001 and the input blood vessel pattern 1002, for example, a template matching is performed to investigate whether a certain image pattern exists in another image, and the position of the investigated image pattern is gradually shifted in the front, back, left, and right directions while investigating the number of pixels that are consistent with the other image. The number of inconsistent pixels is calculated at the position with the most consistent pixels, thereby calculating a comparison score, and the comparison is performed by finding the lowest comparison score.
[0128] The search range 1003 is a range in which the position of the input vein pattern 1002 is gradually shifted in the front-back and left-right directions relative to the registered vein pattern 1001 while overlapping with it, and the position with the minimum matching score is searched.
[0129] then, Fig. 10B In the embodiment, the registered blood vessel pattern 1004 registered in the external storage device 505 is compared with the input blood vessel pattern 1007 generated from the captured image by the blood vessel image capturing device 100.
[0130] As shown in FIG. 2 , when detecting the bending of a finger, the position of the first joint and the position of the second joint of the finger 111 can be detected by detecting the position of a strip-shaped saturated brightness region of the captured image. Fig. 10B In the example of , information indicating the position of the first joint and the position of the second joint is added to the finger blood vessel pattern as first joint position additional information and second joint position additional information.
[0131] The registered blood vessel pattern 1004 is added with first joint position additional information indicating a first joint position 1005 and second joint position additional information indicating a second joint position 1006. Furthermore, the input blood vessel pattern 1007 is added with first joint position additional information indicating a first joint position 1008 and second joint additional information indicating a second joint position 1009.
[0132] When comparing the registered vein pattern 1004 with the input vein pattern 1007 by template matching, first, the positions of the registered vein pattern 1004 and the input vein pattern 1007 in the length direction of the finger 111 are aligned so that the first joint positions 1005 and 1008 and the second joint positions 1006 and 1009 coincide with each other.
[0133] Specifically, the positions in the longitudinal direction of the finger 111 of the registered blood vessel pattern 1004 and the input blood vessel pattern 1007 are aligned so that the first joint position 1005 and the first joint position 1008 and the second joint position 1006 and the second joint position 1009 coincide with each other.
[0134] Therefore, it is not necessary to align the lengthwise position of the finger 111 of the registered vein pattern 1004 and the input vein pattern 1007, and it is sufficient to align the widthwise position of the finger 111. Fig. 10A The search range 1003 is smaller, which can shorten the processing time of the personal authentication process.
[0135] According to this embodiment, since the registered blood vessel pattern 1004 and the position of the finger 111 of the input blood vessel pattern 1007 in the longitudinal direction are aligned so that the first joint positions 1005 and 1008 and the second joint positions 1006 and 1009 coincide with each other, the search range 1010 is reduced, and the processing time of the personal authentication process can be shortened.
[0136] [Example 5]
[0137] This embodiment is an example of a finger vein image capturing device that, when a bent finger is detected, notifies the user of the bent finger and prompts the user to stretch the finger, thereby enabling accurate user authentication.
[0138] Fig.11A FIG. 1 is a diagram showing an example of a display screen when a finger is extended in the blood vessel image capturing apparatus 100 according to the fifth embodiment. Fig. 11B 1 is a diagram showing an example of a display screen when a bent finger is extended to the blood vessel image capturing apparatus 100 of the fifth embodiment.
[0139] Fig.11A and Fig. 11B In Figure 1 The same structure is assigned the same reference numerals and the description thereof is omitted.
[0140] Fig.11A and Fig. 11B The blood vessel image capturing device 100 is Figure 1 In addition to the structure, it also has a display device 1101.
[0141] like Fig.11A As shown, when the user extends the extended finger 111 to the blood vessel image capturing device 100, the control device 113 detects that the finger 111 is extended to the blood vessel image capturing device 100, and lights up a display 1102 notifying that the finger 111 is extended to the blood vessel image capturing device 100, and dims a display 1103 notifying that the finger 111 is extended to the blood vessel image capturing device 100 on the display device 1101. Thus, the user is notified that the finger 111 is extended to the blood vessel image capturing device 100.
[0142] In contrast, Fig. 11BAs shown, when the user bends the finger 111 and extends it toward the blood vessel image capturing device 100, the control device 113 detects that the finger 111 is bent and extended toward the blood vessel image capturing device 100, and dims the display 1102 notifying that the finger 111 is extended toward the blood vessel image capturing device 100, and brightens the display 1103 notifying that the finger 111 is extended toward the blood vessel image capturing device 100 on the display device 1101. Thus, the user can be notified that the finger 111 is bent and extended toward the blood vessel image capturing device 100, and the user can be prompted to extend the finger 111.
[0143] 11, an example is described in which the display device 1101 of the blood vessel image capturing device 100 displays the finger 111 stretched out to the blood vessel image capturing device 100 or the finger 111 bent to the blood vessel image capturing device 100 under the control of the control device 113, but it is also possible to Figure 5 The display device 508 of the authentication device 500 is displayed according to the control of the CPU 506.
[0144] According to this embodiment, the user is informed that the finger 111 is bent and extended toward the blood vessel imaging device 100, and the user is prompted to extend the finger 111. Therefore, the user extends the finger 111 and extends it toward the blood vessel imaging device 100 again, thereby enabling accurate authentication.
[0145] In addition, the present invention is not limited to the above-mentioned embodiments, and includes various modified examples. For example, the above-mentioned embodiments are described in detail in order to explain the present invention in an easy-to-understand manner, and are not limited to all structures that must be described. In addition, a part of the structure of a certain embodiment can be replaced with the structure of other embodiments, and the structure of other embodiments can be added to the structure of a certain embodiment. In addition, for a part of the structure of each embodiment, other structures can be added, deleted, or replaced.
[0146] Description of Reference Numerals
[0147] 100 Blood vessel image capturing device
[0148] 102 Light Source
[0149] 103 Near infrared light
[0150] 110 Camera Device
[0151] 111 fingers
[0152] 113 Control device.
Claims
1. A blood vessel image capturing device for capturing a blood vessel image of a user's finger, characterized in that: include: a light source for irradiating light to the back side of the finger; an imaging unit configured to capture an image of the finger irradiated with the light from the ventral side of the finger; and A control unit detects the bending of the finger by detecting a band-shaped area where brightness saturation occurs, which is generated by light passing through a joint portion of the finger, from the captured blood vessel image.
2. The blood vessel image capturing device according to claim 1, wherein: It also has a reflected light source for irradiating light to the ventral side of the finger, The imaging unit captures an image of the finger irradiated with light from the reflected light source from the ventral side of the finger. The control unit detects the bending of the finger by detecting a linear dark portion caused by joint wrinkles of the finger from the captured blood vessel image.
3. The blood vessel image capturing device according to claim 1, wherein: When the control unit detects that the finger is bent, the control unit stretches the fingertip side and the finger base side of the blood vessel image in the finger length direction, stretches the fingertip side of the blood vessel image in the finger width direction, and stretches or shrinks the finger base side of the blood vessel image in the finger width direction to correct the blood vessel image.
4. The blood vessel image capturing device according to claim 1, wherein: The light source comprises a fingertip side light source arranged on the fingertip side and a finger base side light source arranged on the finger base side. The fingertip-side light source is arranged so that the optical axis angle from the vertical direction is within a range of 10 to 80 degrees on the fingertip side. The finger base side light source is arranged so that the optical axis angle from the vertical direction is within a range of 10 to 80 degrees on the finger base side.
5. The blood vessel image capturing device according to claim 1, wherein: The light source comprises a fingertip side light source arranged on the fingertip side and a finger base side light source arranged on the finger base side. The fingertip-side light source is arranged so that the optical axis angle from the vertical direction is within a range of 10 to 80 degrees on the finger base side. The finger base side light source is arranged so that the optical axis angle from the vertical direction is within a range of 10 to 80 degrees on the finger tip side.
6. The blood vessel image capturing device according to claim 1, wherein: The control unit detects the position of the joint of the finger by detecting the position of a band-shaped area where brightness saturation occurs, which is generated by light passing through the joint of the finger, from the captured blood vessel image.
7. The blood vessel image capturing device according to claim 1, wherein: The device further includes a display unit for notifying the user that the control unit has detected the bending of the finger.
8. A user authentication system comprising a blood vessel image capturing device for capturing a blood vessel image of a user's finger, and an authentication device for performing user authentication using the blood vessel image captured by the blood vessel image capturing device, characterized in that: The blood vessel image capturing device comprises: a light source for irradiating light to the back side of the finger; An imaging unit that captures an image of the finger irradiated with the light from the ventral side of the finger; and a control unit for detecting, from the captured blood vessel image, a band-shaped area where brightness saturation occurs, which is generated by light passing through a joint portion of the finger, to detect bending of the finger; The authentication device comprises: a storage section storing a registered blood vessel pattern registered in advance; and A processing unit generates a finger vein pattern from the captured vein image, and performs user authentication by comparing the generated finger vein pattern with the registered vein pattern.
9. The personal authentication system according to claim 8, characterized in that: The blood vessel image capturing device further includes a reflected light source for irradiating light to the ventral side of the finger. The imaging unit captures an image of the finger irradiated with light from the reflected light source from the ventral side of the finger. The control unit detects the bending of the finger by detecting a linear dark portion caused by joint wrinkles of the finger from the captured blood vessel image.
10. The personal authentication system according to claim 8, characterized in that: When the control unit detects that the finger is bent, the control unit stretches the fingertip side and the finger base side of the blood vessel image in the finger length direction, stretches the fingertip side of the blood vessel image in the finger width direction, and stretches or shrinks the finger base side of the blood vessel image in the finger width direction to correct the blood vessel image.
11. The personal authentication system according to claim 8, characterized in that: The light source comprises a fingertip side light source arranged on the fingertip side and a finger base side light source arranged on the finger base side. The fingertip-side light source is arranged so that the optical axis angle from the vertical direction is within a range of 10 to 80 degrees on the fingertip side. The finger base side light source is arranged so that the optical axis angle from the vertical direction is within a range of 10 to 80 degrees on the finger base side.
12. The personal authentication system according to claim 8, characterized in that: The light source comprises a fingertip side light source arranged on the fingertip side and a finger base side light source arranged on the finger base side. The fingertip-side light source is arranged so that the optical axis angle from the vertical direction is within a range of 10 to 80 degrees on the finger base side. The finger base side light source is arranged so that the optical axis angle from the vertical direction is within a range of 10 to 80 degrees on the finger tip side.
13. The personal authentication system according to claim 8, characterized in that: The control unit detects the position of the joint of the finger by detecting the position of a band-shaped area where brightness saturation occurs, which is generated by light passing through the joint of the finger, from the captured blood vessel image. The processing unit aligns the positions of the generated finger vein pattern and the registered vein pattern using the detected joint positions, and compares the generated finger vein pattern with the registered vein pattern.
14. The personal authentication system according to claim 8, characterized in that: The authentication device further includes a display unit for notifying the user that the control unit has detected the bending of the finger.
