Finger vein recognition system

Abstract

The present disclosure relates to a finger vein recognition system. The finger vein recognition system includes an IR camera, a handle having a sensor and an array of IR LEDs, and a microprocessor for controlling the array of LEDs and processing image signals received from the camera. The emission of each LED in the array of LEDs can be varied based on the position of the user's finger and the environment, which improves the quality of the image captured by the IR camera. The sensor detects the proximity of the user and activates the system.

Description

TECHNICAL FIELD

[0001] The present invention relates generally to image acquisition systems, and more particularly, to an apparatus for finger vein image acquisition and recognition. BACKGROUND

[0002] Biometric recognition, or simply biometrics, involves the use of unique anatomical and behavioral characteristics such as fingerprints, palm prints, faces, irises, voices, and gaits for personal identification. Biometrics is used not only for identification, but also in security systems to allow access to secure areas such as computer files and databases, laboratories and offices, and even homes and cars, because biometrics is more convenient than traditional methods (like keys or ID cards or passwords and PINs) in which physical objects need to be carried or phrases or codes need to be memorized.

[0003] In biometrics, finger vein recognition is becoming more popular because it is more secure than other recognition systems (fingerprint or palm print, face, and iris). In a finger vein recognition system, invisible light passes through a finger and a camera is used to capture an image of the veins illuminated by the light. The captured image is then compared to known patterns for identification. Unlike other biometrics, the vein pattern is hidden under the skin, which makes it more difficult to alter or spoof.

[0004] Therefore, it would be advantageous to have an accurate and reliable finger vein recognition system. BRIEF DESCRIPTION OF DRAWINGS

[0005] The following detailed description of the preferred embodiments of the present invention will be better understood when read in conjunction with the appended drawings. The present invention is illustrated by way of example and not limitation in the figures of the accompanying drawings in which like references indicate similar elements. FIG. 1 shows an example of a finger vein recognition system in which the image sensor of the system is mounted in a car door, and

[0006] Figure 1A An example of a finger vein recognition system is shown in which the image sensor of the system is mounted in a car door, and Figure 1B An example of a finger vein recognition system is shown in which the image sensor of the system is mounted in a car door, and Figure 1A An example of a finger vein recognition system is shown in which the image sensor of the system is mounted in a car door, and

[0007] Figure 2A An example of a finger vein recognition system is shown in which the image sensor of the system is mounted in a car door, and Figure 1A An example of a finger vein recognition system is shown in which the image sensor of the system is mounted in a car door, and Figure 2B An example of a finger vein recognition system is shown in which the image sensor of the system is mounted in a car door, and Figure 2A An example of a finger vein recognition system is shown in which the image sensor of the system is mounted in a car door, and

[0008] Figure 3A An example of a finger vein recognition system is shown in which the image sensor of the system is mounted in a car door, and Figure 1B An example of a finger vein recognition system is shown in which the image sensor of the system is mounted in a car door, and Figure 2Ba finger on a door handle of any of the systems; and Figure 3B the detected finger position is indicated;

[0009] Figure 4 is a schematic block diagram of a vein recognition system according to an embodiment of the present invention; and

[0010] Figure 5 is a flowchart of a method of recognizing finger veins according to an embodiment of the present invention. DETAILED DESCRIPTION

[0011] The detailed description of the drawings is intended as a description of the current preferred embodiment of the present invention, and is not intended to represent the only form in which the present invention can be practiced. It is understood that the same or equivalent functions can be accomplished by different embodiments that are intended to be encompassed within the spirit and scope of the invention.

[0012] In one embodiment, the present invention provides a finger vein recognition system that includes an image capture device, an array of lights, and a microprocessor. The image capture device is attached to a first surface, and the array of lights is attached to a second surface in an arrangement that faces the first surface and the image capture device. The microprocessor is electrically connected to the image capture device and the array of lights, and is configured to individually adjust the intensity of each light in the array of lights. The microprocessor receives image data from the image capture device and processes the image data to detect finger vein patterns therein.

[0013] In another embodiment, a touch sensor is associated with at least one of the second surface and the array of lights. The touch sensor senses the presence of a user and transmits a touch signal to the microprocessor that indicates the presence of the user. The microprocessor then generates and sends a wake-up signal to the image capture device and the array of lights in response to the touch signal. The wake-up signal turns on the array of lights and the image capture device.

[0014] In yet another embodiment, the present invention provides a method of recognizing veins in one or more fingers of a user. The method includes the step of turning on an entire array of lights, where the array of lights is located on an inside of a door handle and illuminates the one or more fingers of the user; and the method includes turning on an image capture device, where the image capture device is located on a door associated with the door handle and is in facing relationship with the array of lights. The image capture device then captures an image of the one or more fingers. The captured image is analyzed to determine a position of the one or more fingers, and in response to determining the position of the one or more fingers, the brightness of individual lights in the array of lights is adjusted. An additional image of the one or more fingers is captured after the brightness is adjusted, and the additional image is analyzed to determine a finger vein pattern of the one or more fingers. The determined finger vein pattern is compared to one or more known finger vein patterns stored in a database. If the patterns match, the door can be opened, and if there is no match, the door will remain closed.

[0015] Various embodiments of the present invention provide a finger vein recognition system that includes a sensor, such as a touch or motion sensor, that wakes up an image capture device and an array of lights. The intensity of the individual lights of the array of lights can be adjusted by a microprocessor, which allows the image capture device to obtain high quality finger vein images.

[0016] Reference is now made to Figure 1A , which shows an example of a finger vein recognition system 10 integrated with an automobile door 12 and door handle 14. Figure 1A The image capture device 16 of the system 10 is shown mounted in the door 12 so that the image capture device 16 is focused on the backside of the door handle 14. In the presently preferred embodiment, the image capture device 16 includes a charge-coupled device (CCD).

[0017] Figure 1B The lighting system 18 of the finger vein recognition system 10 is shown disposed on the backside of the door handle 14 so that the lighting system 18 is in a facing relationship with the image capture device 16. In the presently preferred embodiment, the lighting system 18 includes an array of light-emitting diodes (LEDs) that emit near-infrared light. The finger vein recognition system 10 uses the near-infrared light emitted by the array of LEDs to illuminate one or more fingers of a person, where the light from the LEDs penetrates the fingers and is absorbed by the hemoglobin in the blood. And because the hemoglobin is located in the veins, an image of the veins is captured by the image capture device 16. The light from the LEDs can have a wavelength of between 740 nm and 960 nm, and is preferably about 850 nm. However, as will be appreciated by those skilled in the art, far-infrared light can also be used. Accordingly, the image capture device 16 includes a filter that is configured to only allow light having a particular wavelength (e.g., 850 nm) that is incident from the lighting system 18. Both the image capture device 16 and the lighting system 18 receive power using an existing wiring harness disposed within the door 12. And as will be discussed in greater detail below, the image capture device 16 and the lighting system 18 can also communicate with a microprocessor using the existing wiring harness.

[0018] Figure 2A An example of the finger vein recognition system 10 is shown in Figure 1A , where the image capture device 16 is mounted on a door 20 of an office, room, laboratory or building, and Figure 2B The lighting system 18 is shown attached to a door knob or handle 22 associated with the door 20.

[0019] Figure 3A Four fingers 30 are shown placed on a door handle 32, which can be one of the door handles 12 or 22 shown in Figure 1B and Figure 2B , and Figure 3BThe finger position detected by the image capture device is noted, and then a specific LED 34 is illuminated in order to capture the image of the veins in the finger 30. The LEDs are individually controlled to allow sufficient brightness to capture a high quality image of the veins in one or more fingers.

[0020] Figure 4 is a schematic block diagram of a finger vein recognition system 40 according to an embodiment of the present application. The system 40 includes a CCD 42, a touch sensor 44, an LED array 46, and a microprocessor 48. As Figure 1A and Figure 2A shown in FIGS. 1 and 2, the CCD 42 is disposed in facing relationship with the back side of the door handle, and the LED array 46 is disposed on the back side of the door handle so that when a user wraps his or her finger around the door handle, the finger traverses the LED array 46. The LED array 46 illuminates the finger veins, and the CCD 42 captures an image of the finger veins.

[0021] The microprocessor 48 is electrically connected to the CCD 42 and the LED array 46 and controls the intensity of each light of the light array. The microprocessor 48 receives image data from the CCD and processes the image data to detect the finger vein pattern therein. The microprocessor 48 can be an S32OR I.MX series microcontroller available from NXP Semiconductors of Eindhoven, Netherlands. In one embodiment, the microprocessor 48 includes an MCIMX8QXP MPU, which is commonly used in automotive applications. As will be discussed in greater detail with reference to Figure 5 The microprocessor 48 includes local memory for storing known image data for comparison with the image data captured by the CCD 42 to detect a match condition. If the captured image data matches the pre-stored image data, the door can be opened by the user. The local memory should be large enough to store the known finger vein image of at least one authorized user, but in most embodiments, the finger vein image data of multiple users can be stored in the memory. That is, the memory includes a database of user image data. Those skilled in the art will appreciate that the stored image data can be in the form of a mathematical template or vector representing the image, and the size of the vector is set to an appropriate size, such as 256 or 512 bytes, which can efficiently utilize memory space if the memory size is limited.

[0022] While it is preferred that the image data of authorized users be stored in the local memory of the microprocessor 48, those skilled in the art will appreciate that the microprocessor 48 can be connected to a network to access image data stored in non-local memory, such as in the cloud. In one embodiment, the match condition causes the microprocessor 48 to transmit an unlock signal to the door, which is then unlocked.

[0023] The finger vein recognition system 40 also includes a sensor 44 proximate to the door handle. In one embodiment, the sensor 44 includes a touch sensor that sends a touch signal to the microprocessor 48 when the touch sensor is touched (by a user). In other embodiments, other types of sensors can be used, such as a motion sensor or an RFID sensor that detects RFID signals transmitted from a keychain (e.g., an IOT device worn by the user) or the like. If the microprocessor 48 is in a sleep, idle, or low power mode, the touch signal is used to wake up the processor 48. The processor 48 then sends a wake-up signal to the CCD 42 and LED array 46 to activate the CCD 42 and LED array 46. The sensor 44 is preferably associated with at least one of the door handle and the LED array 46 for detecting the presence of a user's hand.

[0024] Figure 5 is a flowchart of a method 50 of recognizing finger veins according to an embodiment of the present application. Beginning in an idle or standby state 52, the system is awakened by a sensor (e.g., a touch sensor) that detects the presence of a user, as described above. At step 54, if the touch sensor detects the presence of a user, then step 56 is performed, otherwise the system maintains the standby state. At step 56, the microprocessor sends a wake-up signal to the CCD and LED array. At step 58, the LED array is turned on, and at step 60, the CCD captures an image of the finger and sends this initial image data to the microprocessor when the user places his or her finger over the LED array.

[0025] At step 62, the microprocessor analyzes the initial image data to determine the finger position relative to the LED array, and then at step 64, the microprocessor adjusts the brightness of the diodes located under the finger (as shown in FIG. 3). In this way, the user's finger and thus the finger veins will be well illuminated so that the CCD can capture high quality image data. Furthermore, by individually adjusting the LED brightness, those veins in the finger that are deeper as well as the veins closer to the skin can be captured, resulting in a very secure system. Figure 3B

[0026] At step 66, the CCD captures an image of the veins of two or more fingers of the user. At steps 70 and 72, the image data captured by the CCD is processed by the microprocessor to convert the data into a form that can be compared to image data pre-stored in a database. That is, the CCD continuously collects N frames of images at step 66, and simultaneously adjusts the brightness of the individual LEDs at step 68 so that the gray scale histogram of the finger region is evenly distributed. The images with higher quality are then averaged, and the average image is processed using an AND operation with the finger position data to obtain the acquired image.

[0027] ​At step 74, the processed image data is compared to one or more images stored in the database. For example, for a car, there can only be 2 or 3 authorized users, so the microprocessor only needs to store the finger vein data for 2 or 3 different users. Thus, the comparison can be made very quickly. In the presently preferred embodiment, the system captures images of two or more fingers and then compares the captured data to known images of two or more fingers. For example, the system can use data from the index finger and the middle finger, which will make the system more secure than using data from only the index finger. Alternatively, images of two fingers can be captured and compared, but the match can only require one of the captured finger vein images for the match. If there is a match, at step 76, the door is unlocked (i.e., the microprocessor sends an unlock signal to the door lock module), and if there is no match, the door will remain locked and the system will continue to collect image to improve picture quality or will time out and return to the standby state.

[0028] The system 100 provides the advantage of sleeping or idling until activated by the sensor signal. Another advantage is configuring the microprocessor to individually adjust the brightness of the LEDs to obtain high quality images where the deeper veins under the skin can be imaged, not just the veins near the surface of the skin, which results in a secure and accurate system.

[0029] While various embodiments of the application have been illustrated and described, it will be clear to a person skilled in the art that the application is not limited to these embodiments. Many modifications, changes, variations, substitutions and equivalents will be apparent to a person skilled in the art without departing from the spirit and scope of the application as described in the claims.

Claims

1. A finger vein recognition system, comprising: An image capturing device attached to a first surface; An array of lamps is attached to a second surface, which is arranged facing the first surface and the image capturing device; A microprocessor is electrically connected to the image capture device and the lamp array, wherein the intensity of each lamp in the lamp array can be adjusted by the microprocessor; and A touch sensor, associated with at least one of the second surface and the lamp array, wherein: the touch sensor is electrically connected to the microprocessor and transmits a touch signal to the microprocessor, the microprocessor generates a wake-up signal in response to the touch signal and sends the wake-up signal to the image capture device and the lamp array, and the wake-up signal turns on the lamp array and the image capture device; The microprocessor is configured to receive image data from the image capture device and process the image data to detect finger vein patterns therein by: Receive initial image data from the image capture device; Analyze the initial image data to determine the position of the one or more fingers; In response to determining the position of the one or more fingers, the brightness of the lights in the light array associated with the determined one or more fingers is adjusted; After adjusting the brightness, multiple image frames of the one or more fingers are received from the image capturing device. While the image capturing device is capturing multiple image frames, the brightness of the lamps in the lamp array is adjusted so that the grayscale histogram of the finger area is evenly distributed. The plurality of image frames are averaged to produce a processed image signal.

2. The finger vein recognition system according to claim 1, wherein, The image capture device includes a CCD camera.

3. The finger vein recognition system according to claim 2, wherein, The image capture device includes a filter configured to allow only light of a specific wavelength incident from the lamp array to pass through.

4. The finger vein recognition system according to claim 3, wherein, The lamp array includes an array of light-emitting diodes (LEDs) that emit near-infrared light.

5. The finger vein recognition system according to claim 1, wherein, The first surface includes a door, and the second surface includes a door handle or a knob.

6. A method for identifying veins in one or more fingers of a user, comprising the steps of: Turn on all the lights in the light array, which is located inside the door handle and illuminates the user's one or more fingers; The image capture device is activated, wherein the image capture device is located on the door associated with the door handle and is facing the light array and captures images of the one or more fingers; Analyze the captured initial image to determine the position of the one or more fingers; In response to determining the position of the one or more fingers, the brightness of the lights in the light array associated with the determined one or more fingers is adjusted; After adjusting the brightness, an additional image of the one or more fingers is captured, wherein the brightness of the lights in the light array is adjusted so that the grayscale histogram of the finger region in the additional image is uniformly distributed. Analyzing the additional images to determine the finger vein patterns of the user's one or more fingers, the analysis of the additional images including averaging the additional images; The determined finger vein pattern is compared with one or more known finger vein patterns stored in a database; and In response to comparison, prevent or allow the door to open.

7. The method according to claim 6, further comprising the following step: The sensor detects the user's presence and generates a touch signal; The microprocessor receives the touch signal from the sensor and generates a wake-up signal; as well as The image capture device and the light array receive the wake-up signal and are activated in response.

8. The method according to claim 6, wherein, The image capture device captures images of veins in two or more of the user's fingers, and the microprocessor compares the captured images of the two or more fingers with finger vein images stored in a database.

9. The method according to claim 6, wherein, The database includes image data stored in the microprocessor's local memory.

Images