A method and device for processing vein images

Abstract

The present invention discloses a method and device for processing vein images. By extracting surface texture features from vein images, the method effectively removes interference caused by these surface texture features, thereby improving the accuracy of vein recognition. The method comprises: obtaining a transmitted vein image of a vein region to be captured using transmitted light, and obtaining a reflected texture image of the vein region to be captured using reflected light; generating a first denoised image containing the surface texture features in the reflected texture image based on the surface texture features; and determining a vein image of the vein region to be captured based on the first denoised image and the transmitted vein image.

Description

Technical Field

[0001] The present invention relates to the technical field of biometric identification, and in particular to a method and device for processing vein images. Background Art

[0002] Finger veins, as a biometric characteristic of internal finger information, are widely used in biometric identification. They offer uniqueness, high security, and high anti-counterfeiting properties. Furthermore, as a vital characteristic, veins inherently resist counterfeiting. Finger vein recognition is considered the most secure biometric technology. However, in practice, it has been found that near-infrared light not only captures vein information through the finger, but also captures surface texture information such as fingerprints, knuckle lines, and scars when a finger presses against the vein collector's window. This interference can affect vein recognition accuracy.

[0003] Existing vein scanner manufacturers instruct users in their user manuals to gently place their finger on the vein collection window to avoid this problem. However, this approach doesn't fundamentally address the impact of the finger's surface information on vein recognition. It can only prevent interference from shallow lines on the finger's surface, but it can't address the interference caused by deeper scars on some users' fingers due to occupational characteristics. This not only affects the user experience, but also still doesn't solve the problem of interference affecting vein recognition accuracy. Summary of the Invention

[0004] The present invention provides a method and device for processing vein images, which effectively removes interference caused by surface texture features in the vein images by extracting surface texture features in the vein images, thereby improving the accuracy of vein recognition.

[0005] In a first aspect, an embodiment of the present invention provides a method for processing a vein image, comprising:

[0006] Acquire a transmitted vein image of the vein region to be collected by using transmitted light, and acquire a reflected vein image of the vein region to be collected by using reflected light;

[0007] generating a first denoised image including the surface texture features according to the surface texture features in the reflection texture image;

[0008] A vein image of the vein area to be acquired is determined according to the first denoised image and the transmitted vein image.

[0009] As an optional implementation manner, generating a first denoised image including the surface texture features according to the surface texture features in the reflective texture image includes:

[0010] Reversing the grayscale value of the reflective texture image to obtain a grayscale inverted image;

[0011] The grayscale inverted image is binarized to obtain a first denoised image.

[0012] As an optional implementation manner, the binarization processing of the grayscale inverted image to obtain the first denoised image includes:

[0013] performing binarization processing on the grayscale inverted image to obtain an initial denoised image;

[0014] Perform inverse binarization processing on the initial denoised image to obtain the first denoised image.

[0015] As an optional implementation manner, before binarizing the grayscale inverted image to obtain the first denoised image, the method further includes:

[0016] Acquire a second denoised image containing background noise information of the reflective texture image, and use the second denoised image to perform denoising on the grayscale inverted image to obtain the grayscale inverted image after denoising; or

[0017] A second denoised image containing background noise information of the transmitted vein image is acquired, and the grayscale inverted image is subjected to denoising processing using the second denoised image to obtain the grayscale inverted image after denoising processing.

[0018] As an optional implementation manner, determining the vein image of the vein area to be acquired based on the first denoised image and the transmitted vein image includes:

[0019] performing binarization processing on the transmitted vein image to obtain a grayscale transmitted vein image;

[0020] A vein image of the vein area to be acquired is determined according to the grayscale transmission vein image and the first noise reduction image.

[0021] As an optional implementation, before binarizing the transmitted vein image to obtain a grayscale transmitted vein image, the method further includes:

[0022] Acquire a second noise-reduced image containing background noise information of the transmitted vein image;

[0023] The transmitted vein image is subjected to noise reduction processing using the second noise reduction image to obtain the transmitted vein image after noise reduction processing.

[0024] As an optional implementation manner, determining the vein image of the vein area to be acquired based on the first denoised image and the transmitted vein image includes:

[0025] Acquiring a second denoised image containing background noise information of the transmitted vein image, or acquiring a second denoised image containing background noise information of the reflected pattern image;

[0026] A vein image of the vein area to be acquired is determined according to the first denoised image, the second denoised image and the transmitted vein image.

[0027] As an optional implementation manner, determining the vein image of the vein area to be acquired based on the first denoised image, the second denoised image, and the transmitted vein image includes:

[0028] determining a third denoised image based on the first denoised image and the second denoised image;

[0029] The vein image is determined according to the transmitted vein image and the third noise reduction image.

[0030] As an optional implementation manner, determining a third denoised image according to the first denoised image and the second denoised image includes:

[0031] Determining, based on a preset first coefficient of the first denoised image and a preset second coefficient of the second denoised image, a first product value of the first coefficient and the first denoised image, and a second product value of the second coefficient and the second denoised image;

[0032] The third denoised image is determined according to the sum of the first product value and the second product value.

[0033] In a second aspect, an embodiment of the present invention provides a vein image processing device, comprising: a processor and a memory, wherein the memory is used to store a program executable by the processor, and the processor is used to read the program in the memory and perform the following steps:

[0034] Acquire a transmitted vein image of the vein region to be collected by using transmitted light, and acquire a reflected vein image of the vein region to be collected by using reflected light;

[0035] generating a first denoised image including the surface texture features according to the surface texture features in the reflection texture image;

[0036] A vein image of the vein area to be acquired is determined according to the first denoised image and the transmitted vein image.

[0037] As an optional implementation, the processor is specifically configured to execute:

[0038] Reversing the grayscale value of the reflective texture image to obtain a grayscale inverted image;

[0039] The grayscale inverted image is binarized to obtain a first denoised image.

[0040] As an optional implementation, the processor is specifically configured to execute:

[0041] performing binarization processing on the grayscale inverted image to obtain an initial denoised image;

[0042] Perform inverse binarization processing on the initial denoised image to obtain the first denoised image.

[0043] As an optional implementation manner, before binarizing the grayscale inverted image to obtain the first denoised image, the processor is further configured to execute:

[0044] Acquire a second denoised image containing background noise information of the reflective texture image, and use the second denoised image to perform denoising on the grayscale inverted image to obtain the grayscale inverted image after denoising; or

[0045] A second denoised image containing background noise information of the transmitted vein image is acquired, and the grayscale inverted image is subjected to denoising processing using the second denoised image to obtain the grayscale inverted image after denoising processing.

[0046] As an optional implementation, the processor is specifically configured to execute:

[0047] performing binarization processing on the transmitted vein image to obtain a grayscale transmitted vein image;

[0048] A vein image of the vein area to be acquired is determined according to the grayscale transmission vein image and the first noise reduction image.

[0049] As an optional implementation manner, before binarizing the transmitted vein image to obtain the grayscale transmitted vein image, the processor is further configured to execute:

[0050] Acquire a second noise-reduced image containing background noise information of the transmitted vein image;

[0051] The transmitted vein image is subjected to noise reduction processing using the second noise reduction image to obtain the transmitted vein image after noise reduction processing.

[0052] As an optional implementation, the processor is specifically configured to execute:

[0053] Acquiring a second denoised image containing background noise information of the transmitted vein image, or acquiring a second denoised image containing background noise information of the reflected pattern image;

[0054] A vein image of the vein area to be acquired is determined according to the first denoised image, the second denoised image and the transmitted vein image.

[0055] As an optional implementation, the processor is specifically configured to execute:

[0056] determining a third denoised image based on the first denoised image and the second denoised image;

[0057] The vein image is determined according to the transmitted vein image and the third noise reduction image.

[0058] As an optional implementation, the processor is specifically configured to execute:

[0059] Determining, based on a preset first coefficient of the first denoised image and a preset second coefficient of the second denoised image, a first product value of the first coefficient and the first denoised image, and a second product value of the second coefficient and the second denoised image;

[0060] The third denoised image is determined according to the sum of the first product value and the second product value.

[0061] In a third aspect, an embodiment of the present invention further provides a device for processing a vein image, the device comprising:

[0062] An image acquisition unit, configured to acquire a transmitted vein image of the vein region to be acquired by using transmitted light, and to acquire a reflected vein image of the vein region to be acquired by using reflected light;

[0063] A noise reduction unit is configured to generate a first noise reduction image including the surface texture features according to the surface texture features in the reflection texture image;

[0064] The image determining unit is configured to determine a vein image of the vein area to be acquired based on the first denoised image and the transmitted vein image.

[0065] As an optional implementation manner, the noise reduction generating unit is specifically configured to:

[0066] Reversing the grayscale value of the reflective texture image to obtain a grayscale inverted image;

[0067] The grayscale inverted image is binarized to obtain a first denoised image.

[0068] As an optional implementation manner, the noise reduction generating unit is specifically configured to:

[0069] performing binarization processing on the grayscale inverted image to obtain an initial denoised image;

[0070] Perform inverse binarization processing on the initial denoised image to obtain the first denoised image.

[0071] As an optional implementation manner, before the grayscale inverted image is binarized to obtain the first denoised image, the method further includes a first denoising processing unit specifically configured to:

[0072] Acquire a second denoised image containing background noise information of the reflective texture image, and use the second denoised image to perform denoising on the grayscale inverted image to obtain the grayscale inverted image after denoising; or

[0073] A second denoised image containing background noise information of the transmitted vein image is acquired, and the grayscale inverted image is subjected to denoising processing using the second denoised image to obtain the grayscale inverted image after denoising processing.

[0074] As an optional implementation manner, the image determination unit is specifically configured to:

[0075] performing binarization processing on the transmitted vein image to obtain a grayscale transmitted vein image;

[0076] A vein image of the vein area to be acquired is determined according to the grayscale transmission vein image and the first noise reduction image.

[0077] As an optional embodiment, before the transmissive vein image is binarized to obtain a grayscale transmissive vein image, a second noise reduction processing unit is further included to:

[0078] Acquire a second noise-reduced image containing background noise information of the transmitted vein image;

[0079] The transmitted vein image is subjected to noise reduction processing using the second noise reduction image to obtain the transmitted vein image after noise reduction processing.

[0080] As an optional implementation manner, the image determination unit is specifically configured to:

[0081] Acquiring a second denoised image containing background noise information of the transmitted vein image, or acquiring a second denoised image containing background noise information of the reflected pattern image;

[0082] A vein image of the vein area to be acquired is determined according to the first denoised image, the second denoised image and the transmitted vein image.

[0083] As an optional implementation manner, the image determination unit is specifically configured to:

[0084] determining a third denoised image based on the first denoised image and the second denoised image;

[0085] The vein image is determined according to the transmitted vein image and the third noise reduction image.

[0086] As an optional implementation manner, the image determination unit is specifically configured to:

[0087] Determining, based on a preset first coefficient of the first denoised image and a preset second coefficient of the second denoised image, a first product value of the first coefficient and the first denoised image, and a second product value of the second coefficient and the second denoised image;

[0088] The third denoised image is determined according to the sum of the first product value and the second product value.

[0089] In a fourth aspect, an embodiment of the present invention further provides a computer storage medium on which a computer program is stored, and when the program is executed by a processor, it is used to implement the steps of the method described in the first aspect above.

[0090] These and other aspects of the present application will be more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0092] Figure 1 A schematic diagram of a transmission fingerprint imaging method provided by an embodiment of the present invention;

[0093] Figure 2 A transmission fingerprint image based on the transmission fingerprint imaging principle provided by an embodiment of the present invention;

[0094] Figure 3A A schematic diagram of a projected light passing through an interface provided by an embodiment of the present invention;

[0095] Figure 3B A schematic diagram of a projected light passing through an interface provided by an embodiment of the present invention;

[0096] Figure 3C A schematic diagram of a projected light passing through an interface provided by an embodiment of the present invention;

[0097] Figure 4 A schematic diagram of a reflective fingerprint imaging principle provided by an embodiment of the present invention;

[0098] Figure 5 A reflective fingerprint image based on the reflective fingerprint imaging principle provided by an embodiment of the present invention;

[0099] Figure 6 A flow chart of a method for processing a vein image provided by an embodiment of the present invention;

[0100] Figure 7 A first vein image processing method provided by an embodiment of the present invention;

[0101] Figure 8 A second vein image processing method provided by an embodiment of the present invention;

[0102] Figure 9 A third method for processing a vein image provided by an embodiment of the present invention;

[0103] Figure 10 A fourth vein image processing method provided by an embodiment of the present invention;

[0104] Figure 11 A fifth vein image processing method provided by an embodiment of the present invention;

[0105] Figure 12 A schematic diagram of a vein image processing device provided by an embodiment of the present invention;

[0106] Figure 13 A schematic diagram of a vein image processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0107] To make the objectives, technical solutions, and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings. It is apparent that the embodiments described are only some, not all, of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort are intended to fall within the scope of protection of the present invention.

[0108] In embodiments of the present invention, the term "and / or" describes the association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally indicates that the associated objects are in an "or" relationship.

[0109] The application scenarios described in the embodiments of the present invention are intended to more clearly illustrate the technical solutions of the embodiments of the present invention and do not constitute a limitation on the technical solutions provided by the embodiments of the present invention. Persons skilled in the art will appreciate that as new application scenarios emerge, the technical solutions provided by the embodiments of the present invention will also be applicable to similar technical problems. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0110] Example 1. Finger veins, as a biometric characteristic of internal finger information, are widely used in biometric identification. They are unique, highly secure, and highly anti-counterfeit. At the same time, as a living feature, veins naturally have anti-counterfeiting functions. Finger vein recognition is considered to be the safest biometric identification technology. However, in actual applications, it has been found that near-infrared light can not only obtain vein information through the finger, but when the finger presses the collection window of the vein collector, the texture information on the surface of the finger, such as fingerprints, knuckle lines, scars, etc., will also be collected at the same time, forming interference information, affecting the accuracy of vein recognition. Existing vein manufacturers will remind users in the user manual to place their fingers lightly on the vein collection window to avoid this problem. However, this method cannot fundamentally solve the impact of finger surface information on vein recognition. It can only avoid the interference information formed by the shallow lines on the finger surface, and cannot solve the interference effect of deep scars on some users' fingers due to their occupational characteristics. Not only does it affect the user experience, but it still cannot solve the problem of interference information affecting the accuracy of vein recognition.

[0111] In some embodiments, as Figure 1 As shown in FIG, this embodiment provides a principle diagram of transmission fingerprint imaging, wherein a finger 100 is pressed on the collection window cover 101 of the vein collector. When the transmitted light 102 passes through the ridge (the concave part in the figure), more projected light enters the vein collector. When the transmitted light 102 reaches the valley (the convex part in the figure), it first enters the air and then enters the vein collector through the air / cover 101 interface. Ultimately, the transmission fingerprint image obtained by the transmitted light exhibits the characteristics of bright ridges and dark valleys, as shown in FIG. Figure 2 As shown in FIG, this embodiment provides a transmission fingerprint image based on the transmission fingerprint imaging principle. It should be noted that in this process, as Figure 3A 、 Figure 3B 、 Figure 3C As shown, this embodiment provides a schematic diagram of a projected light passing through interfaces, namely, a finger / air interface, an air / glass (plastic) (i.e., air / cover) interface, and a finger / glass (plastic) (finger / cover) interface.

[0112] The refractive index n1 of human skin is between 1.4 and 1.5, the refractive index n0 of air is 1, and the refractive index n2 of the cover plate (using glass as an example) is between 1.5 and 1.6. According to the Fresnel formula, the reflectivities of the finger / air interface (R1), air / cover plate (R2), and finger / cover plate (R3) can be calculated as follows:

[0113]

[0114]

[0115]

[0116] Wherein, θ0 is the angle between the incident or refracted light and the normal line at the R1 interface, θ1 is the angle between the incident or refracted light and the normal line at the R2 interface, and θ2 is the angle between the incident or refracted light and the normal line at the R3 interface.

[0117] It's easy to understand that the greater the difference in refractive index between the two materials forming the interface, the greater the reflectivity, and vice versa. In other words, the reflectivity at the finger / air interface and the air / cover interface is greater than that at the finger / cover interface. This is the basis of transmission fingerprint imaging.

[0118] Based on the same principle, the reflective fingerprint imaging principle is as follows Figure 4 As shown, the finger 100 is pressed on the collection window cover 101 of the vein collector. Under the irradiation of reflected light 103, the reflected fingerprint image obtained based on the reflection fingerprint imaging principle is opposite to the transmission fingerprint image, showing the characteristics of bright valleys and dark ridges, as shown in FIG. Figure 5 As shown in FIG. , an embodiment of the present invention provides a reflective fingerprint image based on the reflective fingerprint imaging principle. It should be noted that although the two imaging methods exhibit inversion characteristics, in actual use, the intensity and optical path of the emitting light source and the projecting light source are difficult to maintain consistency, resulting in an inaccurate one-to-one correspondence between the brightness and position of the target in the reflected image and the transmitted image. This leads to significant difficulties in specific implementation. Simply inverting the grayscale values of the reflected image cannot produce a finger surface image corresponding to the transmitted image, and this lacks universal applicability.

[0119] While eliminating interference information through optical complementarity is difficult, the positional information of all veins in the reflected image corresponds one-to-one with that in the transmitted image. Therefore, embodiments of the present invention propose multiple approaches to obtain a denoising template that incorporates vein features, effectively removing interference information from vein images and obtaining a pure vein image.

[0120] The core idea of the design of the embodiment of the present invention is to photograph the same object (vein) to obtain a reflected vein image and a transmitted vein image, obtain the surface texture features of the object based on the reflected vein image, and use the first denoised image generated by the surface texture features to remove interference information in the projected vein image, thereby improving the accuracy of vein recognition.

[0121] In some embodiments, this embodiment obtains the reflected pattern image of the vein collected by the vein collector through a reflected signal light source (such as a visible light source). Since only one reflected signal light source needs to be added to the existing vein collector, it can ensure that the upgrade processing of the vein image can be completed on the existing vein collection product with almost no increase in cost, thereby improving the accuracy of vein recognition.

[0122] Generally speaking, near-infrared light (700-1100nm) can pass through the finger to form a vein image, while visible light (380-700nm) cannot capture vein image information within the finger. This embodiment addresses the problem that when capturing a vein image, near-infrared light passing through the finger not only carries the vein image information but also, depending on the contact between the finger surface and the collector surface, the sensor also captures surface texture information, which interferes with the vein image. Currently, while vein image capture requires lightly touching the collector surface, rather than pressing, as pressing makes the surface texture information more prominent, even a light touch cannot eliminate the presence of surface texture information in the vein image. This embodiment, based on the fact that visible reflected light only captures fingerprint pattern information formed by the contact between the finger surface and the collector surface, it does not capture vein image information. Therefore, by leveraging the distinction between transmission imaging and emission imaging, this embodiment can reduce noise and eliminate interference generated by surface texture information in transmission vein images.

[0123] like Figure 6 As shown, an embodiment of the present invention provides a method for processing a vein image, and the specific implementation process of the method is as follows:

[0124] Step 600: Acquire a transmitted vein image of the vein region to be captured by transmitted light, and acquire a reflected vein image of the vein region to be captured by reflected light;

[0125] It should be noted that the emission vein image and the transmission vein image in this embodiment are both grayscale images.

[0126] In some embodiments, the transmitted light is emitted by the vein collector itself, which may be a near-infrared light source or other light source with transmission characteristics, and this embodiment does not impose any further restrictions on this. The reflected light is a reflected light source installed above the vein collector's collection window, which may be visible light or other light source with reflection characteristics, and this embodiment does not impose any further restrictions on this.

[0127] During implementation, the collected transmissive vein images and reflective pattern images are both images of the same vein. During implementation, images of the same vein can be collected simultaneously, or the transmissive vein images and reflective pattern images of the same vein can be collected sequentially in a preset order. This embodiment does not impose too many restrictions on the specific methods of collecting transmissive vein images and reflective pattern images.

[0128] Step 601: Generate a first denoised image containing the surface texture features according to the surface texture features in the reflection texture image;

[0129] During implementation, since surface texture features are inevitably acquired when acquiring a vein image, the collected reflection texture image can be used to extract the surface texture features in the reflection texture image, thereby generating a first denoised image related to the surface texture features, so as to use the first denoised image to denoise the transmission vein image.

[0130] In some embodiments, this embodiment generates a first denoised image through the following steps:

[0131] Step (1), inverting the grayscale value of the reflective texture image to obtain a grayscale inverted image;

[0132] In practice, the reflective texture image is subjected to grayscale value inversion processing to obtain a grayscale inverted image, which is a negative of the reflective texture image.

[0133] In some embodiments, after obtaining the grayscale inverted image, in order to ensure that the interference of background noise is removed when subsequently collecting surface texture features, the grayscale inverted image can also be subjected to noise reduction processing after obtaining the grayscale inverted image and before binarization processing to remove the interference caused by background noise in the grayscale inverted image.

[0134] In practice, the grayscale inverted image is subjected to noise reduction processing by any of the following methods:

[0135] Method 1) obtaining a second denoised image containing background noise information of the reflective texture image, and performing denoising processing on the grayscale inverted image using the second denoised image to obtain the grayscale inverted image after denoising;

[0136] In implementation, Gaussian filtering is performed on the grayscale inverted image to obtain a second denoised image;

[0137] The difference between the grayscale inverted image and the second denoised image is determined as the grayscale inverted image after denoising.

[0138] Method 2) Acquire a second denoised image containing background noise information of the transmitted vein image, and use the second denoised image to perform denoising on the grayscale inverted image to obtain the grayscale inverted image after denoising.

[0139] In implementation, Gaussian filtering is performed on the transmitted vein image to obtain a second noise-reduced image;

[0140] The difference between the grayscale inverted image and the second denoised image is determined as the grayscale inverted image after denoising.

[0141] After the grayscale inverted image is subjected to noise reduction processing, the following steps are continued to be performed on the grayscale inverted image after the noise reduction processing.

[0142] Step (2): binarize the grayscale inverted image to obtain a first denoised image.

[0143] In some embodiments, an image obtained by binarizing the grayscale inverted image is used as the first denoised image.

[0144] In some embodiments, since the initial denoised image obtained after binarization processing is relatively sharp, in order to be closer to the real image, this embodiment performs inverse binarization processing on the initial denoised image, that is, the inverse processing of the binarization processing. During implementation, the grayscale inverted image is binarized to obtain the initial denoised image; the initial denoised image is inversely binarized to obtain the first denoised image.

[0145] Optionally, interpolation processing is performed between adjacent pixels of the initial denoised image based on Poisson distribution or Gaussian distribution, and a suitable threshold C is selected to ensure the degree of grayscale gradient between pixels, thereby processing the sharp binary image into a first denoised image close to the real gradient feature.

[0146] Step 602: Determine the vein image of the vein area to be acquired based on the first denoised image and the transmitted vein image.

[0147] In some embodiments, this embodiment provides any of the following methods for determining a vein image of a vein area to be captured, as shown below:

[0148] Method 1: determining based on the first denoised image and the transmitted vein image.

[0149] In some embodiments, first, the transmitted vein image is binarized to obtain a grayscale transmitted vein image;

[0150] In some embodiments, in order to ensure that background noise interference is removed during the process of determining the vein image, this embodiment further performs noise reduction processing on the transmitted vein image before binarizing the transmitted vein image to obtain the grayscale transmitted vein image, specifically, as follows:

[0151] Acquire a second denoised image containing background noise information of the transmitted vein image; optionally, perform Gaussian filtering on the transmitted vein image to obtain the second denoised image;

[0152] The transmitted vein image is subjected to denoising using the second denoised image to obtain the denoised transmitted vein image. Optionally, the difference between the transmitted vein image and the second denoised image is determined as the denoised transmitted vein image.

[0153] Secondly, the vein image of the vein area to be collected is determined based on the grayscale transmission vein image and the first noise reduction image. In implementation, the difference between the grayscale transmission vein image and the first noise reduction image is determined as the vein image of the vein area to be collected.

[0154] In this method, the first noise reduction image can be obtained by using the methods in steps (1) to (2) above.

[0155] Method 2: determining based on the first denoised image, the second denoised image and the transmitted vein image.

[0156] In some embodiments, the present embodiment may further obtain a second noise reduction image, specifically by any of the following methods:

[0157] 1) performing Gaussian filtering on the transmitted vein image to obtain a second denoised image containing background noise information of the transmitted vein image;

[0158] 2) Gaussian filtering is performed on the grayscale inverted image obtained after grayscale value inversion processing is performed on the reflective texture image to obtain a second denoised image containing background noise information of the reflective texture image.

[0159] After acquiring the second denoised image, this embodiment may further perform denoising on the transmitted vein image based on the first denoised image and the second denoised image. The specific processing process is as follows:

[0160] The first process is:

[0161] Acquire a second noise-reduced image containing background noise information of the transmitted vein image;

[0162] In implementation, Gaussian filtering is performed on the transmitted vein image to obtain a second denoised image containing background noise information of the transmitted vein image;

[0163] A vein image of the vein area to be acquired is determined according to the first denoised image, the second denoised image and the transmitted vein image.

[0164] In some embodiments, a third denoised image is determined based on the first denoised image and the second denoised image. In implementation, a first product value of the first coefficient a and the first denoised image, and a second product value of the second coefficient b and the second denoised image are determined based on a predetermined first coefficient a of the first denoised image and a second coefficient b of the second denoised image. The third denoised image is determined based on the sum of the first product value and the second product value.

[0165] The vein image is determined based on the transmitted vein image and the third denoised image. In an implementation, the difference between the transmitted vein image and the third denoised image is determined as the vein image.

[0166] In this process, the first noise reduction image can be obtained by using the methods in steps (1) to (2) above.

[0167] The second process is:

[0168] Acquire a second denoised image containing background noise information of the reflective texture image;

[0169] In implementation, a grayscale inverted image obtained by performing grayscale value inversion processing on the reflective texture image is subjected to Gaussian filtering to obtain a second denoised image containing background noise information of the reflective texture image.

[0170] A vein image of the vein area to be acquired is determined according to the first denoised image, the second denoised image and the transmitted vein image.

[0171] In some embodiments, a third denoised image is determined based on the first denoised image and the second denoised image. In implementation, a first product value of the first coefficient a and the first denoised image, and a second product value of the second coefficient b and the second denoised image are determined based on a predetermined first coefficient a of the first denoised image and a second coefficient b of the second denoised image. The third denoised image is determined based on the sum of the first product value and the second product value.

[0172] The vein image is determined based on the transmitted vein image and the third denoised image. In an implementation, the difference between the transmitted vein image and the third denoised image is determined as the vein image.

[0173] In this process, the first noise reduction image can be obtained by using the methods in steps (1) to (2) above.

[0174] like Figure 7 As shown, the first method for processing vein images provided in this embodiment has a specific implementation process as follows:

[0175] Step 700: Acquire a transmitted vein image of the vein region to be captured by transmitted light, and acquire a reflected vein image of the vein region to be captured by reflected light;

[0176] Step 701: Invert the grayscale values of the reflective texture image to obtain a grayscale inverted image, binarize the grayscale inverted image to obtain an initial denoised image, inversely binarize the initial denoised image to obtain a first denoised image; and Gaussian filter the grayscale inverted image to obtain a second denoised image.

[0177] Step 702: Determine a first product value of the first coefficient and the first denoised image, and a second product value of the second coefficient and the second denoised image, based on a preset first coefficient of the first denoised image and a preset second coefficient of the second denoised image; and determine a third denoised image based on the sum of the first product value and the second product value.

[0178] Step 703: Determine the difference between the transmitted vein image and the third noise reduction image as the vein image of the vein area to be collected.

[0179] like Figure 8 As shown, the second method for processing vein images provided in this embodiment has a specific implementation process as follows:

[0180] Step 800: Acquire a transmitted vein image of a vein region to be captured by transmitted light, and acquire a reflected vein image of the vein region to be captured by reflected light;

[0181] Step 801: Invert the grayscale values of the reflective texture image to obtain a grayscale inverted image, binarize the grayscale inverted image to obtain an initial denoised image, inversely binarize the initial denoised image to obtain a first denoised image; and Gaussian filter the transmitted vein image to obtain a second denoised image.

[0182] Step 802: Determine a first product value of the first coefficient and the first denoised image, and a second product value of the second coefficient and the second denoised image, based on a preset first coefficient of the first denoised image and a second coefficient of the second denoised image; and determine a third denoised image based on the sum of the first product value and the second product value.

[0183] Step 803: Determine the difference between the transmitted vein image and the third noise reduction image as the vein image of the vein area to be collected.

[0184] like Figure 9 As shown, the third method for processing vein images provided in this embodiment has a specific implementation process as follows:

[0185] Step 900: Acquire a transmitted vein image of a vein region to be captured by transmitted light, and acquire a reflected vein image of the vein region to be captured by reflected light;

[0186] Step 901: Performing a grayscale value inversion process on the reflective texture image to obtain a grayscale inverted image and performing Gaussian filtering to obtain a second denoised image;

[0187] Step 902: Determine the difference between the grayscale inverted image and the second denoised image as the grayscale inverted image after denoising.

[0188] Step 903: binarize the grayscale inverted image after denoising to obtain an initial denoised image, and perform inverse binarization on the initial denoised image to obtain a first denoised image;

[0189] Step 904: Determine a first product value of the first coefficient and the first denoised image, and a second product value of the second coefficient and the second denoised image, based on a preset first coefficient of the first denoised image and a preset second coefficient of the second denoised image; and determine a third denoised image based on the sum of the first product value and the second product value.

[0190] Step 905: Determine the difference between the transmitted vein image and the third noise reduction image as the vein image of the vein area to be collected.

[0191] like Figure 10 As shown, the fourth method for processing vein images provided in this embodiment has a specific implementation process as follows:

[0192] Step 1000: Acquire a transmitted vein image of a vein region to be captured by transmitted light, and acquire a reflected vein image of the vein region to be captured by reflected light;

[0193] Step 1001: Performing a grayscale inversion process on the reflection texture image to obtain a grayscale inversion image, and performing Gaussian filtering to obtain a reflection noise reduction image;

[0194] Step 1002: Determine the difference between the grayscale inverted image and the reflection noise reduction image as the grayscale inverted image after noise reduction processing;

[0195] Step 1003: binarize the grayscale inverted image after denoising to obtain an initial denoised image, and perform inverse binarization on the initial denoised image to obtain a first denoised image;

[0196] Step 1004: Perform Gaussian filtering on the transmitted vein image to obtain a second noise-reduced image;

[0197] Step 1005: Determine, based on a preset first coefficient of the first denoised image and a preset second coefficient of the second denoised image, a first product value of the first coefficient and the first denoised image, and a second product value of the second coefficient and the second denoised image; and determine a third denoised image based on the sum of the first product value and the second product value.

[0198] Step 1006: Determine the difference between the transmitted vein image and the third noise reduction image as the vein image of the vein area to be collected.

[0199] like Figure 11 As shown, the fifth method for processing vein images provided in this embodiment has a specific implementation process as follows:

[0200] Step 1100: Acquire a transmitted vein image of a vein region to be captured by transmitted light, and acquire a reflected vein image of the vein region to be captured by reflected light;

[0201] Step 1101: Performing a grayscale value inversion process on the reflection texture image, and performing Gaussian filtering on the grayscale inverted image obtained to obtain a reflection noise reduction image;

[0202] Step 1102: Determine the difference between the grayscale inverted image and the reflection noise reduction image as the grayscale inverted image after noise reduction processing;

[0203] Step 1103: binarize the grayscale inverted image after the noise reduction process to obtain a first noise reduction image.

[0204] Step 1104: Perform Gaussian filtering on the transmitted vein image to obtain a second noise-reduced image;

[0205] Step 1105: Determine the difference between the transmitted vein image and the second denoised image as the transmitted vein image after denoising.

[0206] Step 1106: binarize the denoised transmitted vein image to obtain a binary transmitted vein image.

[0207] Step 1107: Determine the difference between the binary transmission vein image and the first denoised image as the vein image of the vein area to be collected.

[0208] Example 2: Based on the same inventive concept, the embodiment of the present invention also provides a device for processing vein images. Since the device is the device in the method in the embodiment of the present invention, and the principle of solving the problem by the device is similar to that of the method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0209] like Figure 12As shown, this embodiment provides a vein image processing device, which includes: a processor 1200 and a memory 1201, wherein the memory 1201 is used to store a program executable by the processor 1200, and the processor 1200 is used to read the program in the memory 1201 and perform the following steps:

[0210] Acquire a transmitted vein image of the vein region to be collected by using transmitted light, and acquire a reflected vein image of the vein region to be collected by using reflected light;

[0211] generating a first denoised image including the surface texture features according to the surface texture features in the reflection texture image;

[0212] A vein image of the vein area to be acquired is determined according to the first denoised image and the transmitted vein image.

[0213] As an optional implementation manner, the processor 1200 is specifically configured to execute:

[0214] Reversing the grayscale value of the reflective texture image to obtain a grayscale inverted image;

[0215] The grayscale inverted image is binarized to obtain a first denoised image.

[0216] As an optional implementation manner, the processor 1200 is specifically configured to execute:

[0217] performing binarization processing on the grayscale inverted image to obtain an initial denoised image;

[0218] Perform inverse binarization processing on the initial denoised image to obtain the first denoised image.

[0219] As an optional implementation manner, before binarizing the grayscale inverted image to obtain the first denoised image, the processor 1200 is further configured to execute:

[0220] Acquire a second denoised image containing background noise information of the reflective texture image, and use the second denoised image to perform denoising on the grayscale inverted image to obtain the grayscale inverted image after denoising; or

[0221] A second denoised image containing background noise information of the transmitted vein image is acquired, and the grayscale inverted image is subjected to denoising processing using the second denoised image to obtain the grayscale inverted image after denoising processing.

[0222] As an optional implementation manner, the processor 1200 is specifically configured to execute:

[0223] performing binarization processing on the transmitted vein image to obtain a grayscale transmitted vein image;

[0224] A vein image of the vein area to be acquired is determined according to the grayscale transmission vein image and the first noise reduction image.

[0225] As an optional implementation, before binarizing the transmitted vein image to obtain the grayscale transmitted vein image, the processor 1200 is further configured to execute:

[0226] Acquire a second noise-reduced image containing background noise information of the transmitted vein image;

[0227] The transmitted vein image is subjected to noise reduction processing using the second noise reduction image to obtain the transmitted vein image after noise reduction processing.

[0228] As an optional implementation manner, the processor 1200 is specifically configured to execute:

[0229] Acquiring a second denoised image containing background noise information of the transmitted vein image, or acquiring a second denoised image containing background noise information of the reflected pattern image;

[0230] A vein image of the vein area to be acquired is determined according to the first denoised image, the second denoised image and the transmitted vein image.

[0231] As an optional implementation manner, the processor 1200 is specifically configured to execute:

[0232] determining a third denoised image based on the first denoised image and the second denoised image;

[0233] The vein image is determined according to the transmitted vein image and the third noise reduction image.

[0234] As an optional implementation manner, the processor 1200 is specifically configured to execute:

[0235] Determining, based on a preset first coefficient of the first denoised image and a preset second coefficient of the second denoised image, a first product value of the first coefficient and the first denoised image, and a second product value of the second coefficient and the second denoised image;

[0236] The third denoised image is determined according to the sum of the first product value and the second product value.

[0237] Example 3: Based on the same inventive concept, the embodiment of the present invention also provides a device for processing vein images. Since the device is the device in the method in the embodiment of the present invention, and the principle of solving the problem by the device is similar to that of the method, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0238] like Figure 13 As shown, the device includes:

[0239] The image acquisition unit 1300 is configured to acquire a transmitted vein image of the vein region to be acquired by using transmitted light, and acquire a reflected vein image of the vein region to be acquired by using reflected light;

[0240] A noise reduction unit 1301 is configured to generate a first noise reduction image including the surface texture features according to the surface texture features in the reflection texture image;

[0241] The image determining unit 1302 is configured to determine a vein image of the vein area to be acquired based on the first denoised image and the transmitted vein image.

[0242] As an optional implementation manner, the noise reduction generating unit 1301 is specifically configured to:

[0243] Reversing the grayscale value of the reflective texture image to obtain a grayscale inverted image;

[0244] The grayscale inverted image is binarized to obtain a first denoised image.

[0245] As an optional implementation manner, the noise reduction generating unit 1301 is specifically configured to:

[0246] performing binarization processing on the grayscale inverted image to obtain an initial denoised image;

[0247] Perform inverse binarization processing on the initial denoised image to obtain the first denoised image.

[0248] As an optional implementation manner, before the grayscale inverted image is binarized to obtain the first denoised image, the method further includes a first denoising processing unit specifically configured to:

[0249] Acquire a second denoised image containing background noise information of the reflective texture image, and use the second denoised image to perform denoising on the grayscale inverted image to obtain the grayscale inverted image after denoising; or

[0250] A second denoised image containing background noise information of the transmitted vein image is acquired, and the grayscale inverted image is subjected to denoising processing using the second denoised image to obtain the grayscale inverted image after denoising processing.

[0251] As an optional implementation manner, the image determination unit 1302 is specifically configured to:

[0252] performing binarization processing on the transmitted vein image to obtain a grayscale transmitted vein image;

[0253] A vein image of the vein area to be acquired is determined according to the grayscale transmission vein image and the first noise reduction image.

[0254] As an optional embodiment, before the transmissive vein image is binarized to obtain a grayscale transmissive vein image, a second noise reduction processing unit is further included to:

[0255] Acquire a second noise-reduced image containing background noise information of the transmitted vein image;

[0256] The transmitted vein image is subjected to noise reduction processing using the second noise reduction image to obtain the transmitted vein image after noise reduction processing.

[0257] As an optional implementation manner, the image determination unit 1302 is specifically configured to:

[0258] Acquiring a second denoised image containing background noise information of the transmitted vein image, or acquiring a second denoised image containing background noise information of the reflected pattern image;

[0259] A vein image of the vein area to be acquired is determined according to the first denoised image, the second denoised image and the transmitted vein image.

[0260] As an optional implementation manner, the image determination unit 1302 is specifically configured to:

[0261] determining a third denoised image based on the first denoised image and the second denoised image;

[0262] The vein image is determined according to the transmitted vein image and the third noise reduction image.

[0263] As an optional implementation manner, the image determination unit 1302 is specifically configured to:

[0264] Determining, based on a preset first coefficient of the first denoised image and a preset second coefficient of the second denoised image, a first product value of the first coefficient and the first denoised image, and a second product value of the second coefficient and the second denoised image;

[0265] The third denoised image is determined according to the sum of the first product value and the second product value.

[0266] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium having a computer program stored thereon, which, when executed by a processor, implements the following steps:

[0267] Acquire a transmitted vein image of the vein region to be collected by using transmitted light, and acquire a reflected vein image of the vein region to be collected by using reflected light;

[0268] generating a first denoised image including the surface texture features according to the surface texture features in the reflection texture image;

[0269] A vein image of the vein area to be acquired is determined according to the first denoised image and the transmitted vein image.

[0270] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0271] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that performs the functions specified in one or more boxes.

[0272] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0273] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0274] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for processing a vein image, characterized in that: The method includes: Acquire a transmitted vein image of the vein region to be collected by using transmitted light, and acquire a reflected vein image of the vein region to be collected by using reflected light; generating a first denoised image including the surface texture features according to the surface texture features in the reflection texture image; Determining the vein image of the vein area to be acquired based on the first denoised image and the transmitted vein image includes: obtaining a second denoised image containing background noise information of the transmitted vein image, or obtaining a second denoised image containing background noise information of the reflected pattern image; determining a first product value of the first coefficient and the first denoised image, and a second product value of the second coefficient and the second denoised image based on a preset first coefficient of the first denoised image and a second coefficient of the second denoised image; determining a third denoised image based on the sum of the first product value and the second product value; and determining the vein image based on the transmitted vein image and the third denoised image.

2. The method according to claim 1, characterized in that The step of generating a first denoised image including the surface texture features according to the surface texture features in the reflection texture image comprises: Reversing the grayscale value of the reflective texture image to obtain a grayscale inverted image; The grayscale inverted image is binarized to obtain a first denoised image.

3. The method according to claim 2, characterized in that The binarization process is performed on the grayscale inverted image to obtain a first denoised image, comprising: performing binarization processing on the grayscale inverted image to obtain an initial denoised image; Perform inverse binarization processing on the initial denoised image to obtain the first denoised image.

4. The method according to claim 2, characterized in that Before performing binarization processing on the grayscale inverted image to obtain the first denoised image, the method further includes: Acquire a second denoised image containing background noise information of the reflective texture image, and use the second denoised image to perform denoising on the grayscale inverted image to obtain the grayscale inverted image after denoising; or A second denoised image containing background noise information of the transmitted vein image is acquired, and the grayscale inverted image is subjected to denoising processing using the second denoised image to obtain the grayscale inverted image after denoising processing.

5. The method according to claim 1, characterized in that The step of determining the vein image of the vein area to be acquired based on the first denoised image and the transmitted vein image includes: performing binarization processing on the transmitted vein image to obtain a grayscale transmitted vein image; A vein image of the vein area to be acquired is determined according to the grayscale transmission vein image and the first noise reduction image.

6. The method according to claim 5, characterized in that Before performing binarization processing on the transmitted vein image to obtain a grayscale transmitted vein image, the method further includes: Acquire a second noise-reduced image containing background noise information of the transmitted vein image; The transmitted vein image is subjected to noise reduction processing using the second noise reduction image to obtain the transmitted vein image after noise reduction processing.

7. A vein image processing device, characterized in that: The processing device includes a processor and a memory, wherein the memory is used to store a program executable by the processor, and the processor is used to read the program in the memory and execute the steps of any one of the methods of claims 1 to 6.

8. A computer storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images