TW202008210A - Fingerprint image processing device and method - Google Patents

Abstract

A fingerprint image processing device is provided in the invention. The fingerprint image processing device comprises a fingerprint sensing device, a processor, and a storage device. The fingerprint sensing device generates a plurality of fingerprint image data. When the processor generates a register data, the processor compares the gray value of each pixel of each fingerprint image data with a first threshold and a second threshold to generate a first filtering result first. Then, the processor calculates a standard deviation corresponding to the plurality of fingerprint image data according to the first filtering result, and generates a second filtering result according to the standard deviation. Finally, the processor generates the register data according to the second filtering result.

Description

Fingerprint image processing device and method

The specification of the present invention mainly relates to a fingerprint image processing technology, and particularly relates to a fingerprint image processing technology that improves the success rate of fingerprint recognition (matching).

In recent years, with the advancement of biometrics technology, fingerprint identification technology has also received more and more attention. Due to the uniqueness and variability of fingerprints and the availability of fingerprint images, fingerprint identification has good security and stability.

In the current process of fingerprint identification enrolled and matched, the components used often generate serious noise. These noises may come from other components (for example: power adapter) or other factors. Noise will cause the fingerprint features obtained by the fingerprint sensor to be poor, or affect the interpretation of the fingerprint features, thus affecting the success rate of fingerprint recognition.

In view of the above-mentioned problems of the prior art, the present invention provides a fingerprint image processing technology, and particularly relates to a fingerprint image processing device and method for improving the success rate of fingerprint recognition (matching).

According to one embodiment of the present invention, a fingerprint image processing device is provided. The fingerprint image processing device includes a fingerprint sensing device, a processing device, and a storage device. The fingerprint sensing device will generate multiple fingerprint image data. The processing device is coupled to the fingerprint sensing device and generates registered fingerprint data. The storage device is coupled to the processing device and stores the registered fingerprint data. When the processing device generates the registered fingerprint data, the processing device first compares the grayscale value of each pixel of each of the complex fingerprint image data with a first critical value and a second critical value to generate A first filter result. Then, the processing device calculates a standard deviation corresponding to the complex fingerprint image data according to the first filtering result, and generates a second filtering result according to the standard deviation. Finally, the processing device generates the registered fingerprint data according to the second filtering result.

In some embodiments, when the processing device generates the first filtering result, the processing device deletes pixel data corresponding to pixels whose gray level value is greater than the first critical value and less than the second critical value to generate the foregoing First filter results.

In some embodiments, when the processing device generates the second filtering result, the processing device calculates the average grayscale value of each pixel according to the first filtering result, and based on the average grayscale of each pixel The order value calculates the standard deviation corresponding to the complex fingerprint image data. In addition, the processing device generates a gray scale value range according to the standard deviation, and the processing device deletes pixel data of pixels whose gray scale value is not within the gray scale value range according to the gray scale value range to generate the above Second filter results.

In some embodiments, the processing device synthesizes the plurality of fingerprint image data based on the second filtering result to generate the registered fingerprint data.

According to one embodiment of the present invention, a fingerprint image processing method is provided. The above-mentioned fingerprint image processing method includes: generating a plurality of fingerprint image data by a fingerprint sensing device; and using a processing device to compare the grayscale value of each pixel of each of the plurality of fingerprint image data with a first threshold value and a The second threshold value is compared to generate a first filtering result; the processing device calculates a standard deviation corresponding to the complex fingerprint image data according to the first filtering result; the processing device generates a standard deviation according to the standard deviation The second filtering result; generating a registered fingerprint data according to the second filtering result by the processing device; and storing the registered fingerprint data in a storage device.

Regarding other additional features and advantages of the present invention, those skilled in the art can make some changes and modifications based on the fingerprint image processing device and method disclosed in the implementation method of the present invention without departing from the spirit and scope of the present invention. Get retouched.

This section describes the best way to implement the present invention, the purpose is to illustrate the spirit of the present invention and not to limit the scope of protection of the present invention, the scope of protection of the present invention shall be subject to the scope of the attached patent application shall prevail .

FIG. 1 is a block diagram of a fingerprint image processing device 100 according to an embodiment of the invention. According to an embodiment of the present invention, the fingerprint image processing device 100 may refer to an electronic device with a fingerprint recognition function, such as an electronic device such as a mobile phone, a smart phone, a tablet computer, or a notebook computer. As shown in FIG. 1, the fingerprint image processing device 100 may include a fingerprint sensing device 110, a processing device 120, and a storage device 130. It should be noted that the block diagram shown in FIG. 1 is only for the convenience of describing the embodiments of the present invention, but the present invention is not limited thereto. The fingerprint image processing device 100 may also include other components.

According to an embodiment of the invention, the fingerprint sensing device 110 may be a swipe sensor or a push sensor. In other words, the fingerprint sensing device 110 can capture the user's swiping action to generate fingerprint image data, or can capture the user's pressing action to generate fingerprint image data.

According to the embodiment of the present invention, before fingerprint recognition is performed, the user will first press or swipe his finger on the fingerprint sensor 110 to generate one or more fingerprint image data. Next, the processing device 120 generates registered fingerprint data according to one or more fingerprint image data generated by the fingerprint sensor 110 to provide fingerprint identification. In addition, the processing device 120 stores the generated registered fingerprint data in the storage device 130. The process of generating the registered fingerprint data by the processing device 120 will be described in more detail below.

According to an embodiment of the present invention, after the processing device 120 obtains a plurality of fingerprint image data from the fingerprint sensor 110, the processing device 120 compares the grayscale value of each pixel of each fingerprint image data with a first threshold value and A second threshold is compared to delete pixel data that is too dark or too white. More specifically, when the grayscale value of a pixel is greater than the first threshold, the processing device 120 determines that the pixel data of the pixel is too white, and when the sum of the grayscale value of a pixel is less than the second threshold When the value is set, the processing device 120 determines that the pixel data of this pixel is too dark. Then, the processing device 120 regards the black or white pixel data (that is, generating the first filtering result) as noise interference, and deletes the black or white pixel data. The illustrations in Figures 2 and 3A will be used below.

According to an embodiment of the present invention, the first threshold can be set to the gray level value 255 minus a preset threshold (255-preset threshold), and the second threshold can be set to the preset threshold, but the present invention does not This is the limit. For example, when the preset threshold is 5, when the gray level value of a pixel is greater than 250 (the first threshold), the processing device 120 determines that the pixel data of the pixel is too white, and when a When the sum of the gray scale values of the pixels is less than 5 (the second critical value), the processing device 120 determines that the pixel data of this pixel is too dark. In particular, the preset threshold can be adjusted and set according to different situations. For example, when the noise is high, the value of the preset threshold can be adjusted higher.

FIG. 2 is a schematic diagram showing the grayscale values of the retelling pixels according to an embodiment of the invention. As shown in FIG. 2, when the processing device 120 compares the grayscale value of each pixel of the fingerprint image data A, B, C, and D with the first critical value and the second critical value, the processing device 120 determines The pixel data of the first pixel of the fingerprint image data B is too black, and the pixel data of the eighth pixel is too white, and the processing device 120 determines that the pixel data of all pixels of the fingerprint image data D is too black. Therefore, the processing device 120 deletes these pixel data that are too black or too white. It should be noted that the schematic diagram shown in FIG. 2 is only for the convenience of describing the embodiments of the present invention, but the present invention is not limited thereto.

FIG. 3A is a schematic diagram showing a first filtering result according to an embodiment of the invention. In Figure 3A, the X axis represents time, and the Y axis represents gray scale values. As shown in FIG. 3A, pixel data (over-black or over-white) corresponding to pixels with gray levels greater than the first threshold and less than the second threshold are filtered by the processing device 120 as noise.

According to an embodiment of the present invention, after the processing device 120 deletes the pixel data that is too black or too white, the processing device 120 calculates to calculate the average grayscale value of each pixel. More specifically, the processing device 120 calculates a set of average grayscale values according to the grayscale values of each pixel corresponding to all fingerprint image data after the black or white pixel data is deleted. Taking FIG. 2 as an example, the processing device 120 calculates the average grayscale values of the first pixels A1, B1, C1, and D1 of the fingerprint image data A, B, C, and D (that is, the average grayscale of the first pixels Value = (A1 grayscale value + C1 grayscale value)/2), calculate the average grayscale value of the second pixels A2, B2, C3 and D4 (that is, the average grayscale value of the second pixel = (A2 grayscale value Value + B2 gray scale value + C2 gray scale value)/3). By analogy, the processing device 120 can calculate the average gray level value of each pixel corresponding to the fingerprint image data A, B, C and D.

According to an embodiment of the present invention, after the processing device 120 obtains the average grayscale value of each pixel, the processing device 120 calculates a standard deviation corresponding to the complex fingerprint image data according to the average grayscale value of each pixel . Then, the processing device 120 generates a gray scale value range according to the calculated standard deviation, and deletes the pixel data of the pixel whose gray scale value is not within the gray scale value range according to the gray scale value range (that is, generates the second Filter results). For example, if the standard deviation is 10, the processing device 120 will add 10 to the center value 128 of the gray scale value and minus 10 to the center value 128 as a range of gray scale values. That is to say, the pixel data of the pixels whose gray-scale value is not within the gray-scale value range (ie 118-138) will be deleted by the processing device 120. The following will be illustrated with Figure 3B.

FIG. 3B is a schematic diagram showing a second filtering result according to an embodiment of the invention. In Figure 3B, the X axis represents time, and the Y axis represents gray scale values. As shown in FIG. 3B, the processing device 120 determines a gray scale value range according to the standard deviation corresponding to the complex fingerprint image data. The pixel data of the pixels of the complex fingerprint image data whose gray scale value is not within the gray scale value range will be deleted by the processing device 120.

According to an embodiment of the present invention, when the pixel data of each pixel of each fingerprint image data whose gray level value is not within the gray level value range is also deleted, the processing device 120 will synthesize all fingerprint image data to generate A registered fingerprint data, and the processing device 120 will store the registered fingerprint data in the processing device 130. If the user wants to generate other pen registration data, the operation described in the above embodiment can be repeated.

When fingerprint recognition is to be performed, the user will press or swipe their finger on the fingerprint sensor 110 to generate fingerprint data to be recognized. Then, the processing device 120 matches the fingerprint data to be recognized with the registration data stored in the processing device 130. If the fingerprint data to be recognized matches a registration data, the processing device 120 determines that the fingerprint recognition is successful. If the fingerprint data to be recognized cannot match the registration data, the processing device 120 determines that the fingerprint recognition has failed.

FIG. 4 is a flowchart 400 of a fingerprint image processing method according to an embodiment of the invention. This fingerprint image processing method can be applied to the fingerprint image processing device 100 of the present invention. In step S410, a fingerprint sensing device of the fingerprint image processing device 100 generates plural fingerprint image data. In step S420, the processing device of the fingerprint image processing device 100 compares the gray level value of each pixel of each complex fingerprint image data with a first critical value and a second critical value to generate a first filtering result. In step S430, the processing device of the fingerprint image processing device 100 calculates a standard deviation of the corresponding plural fingerprint image data according to the first filtering result. In step S440, the processing device of the fingerprint image processing device 100 generates a second filtered result according to the standard deviation. In step S450, the processing device of the fingerprint image processing device 100 generates a registered fingerprint data according to the second filtering result. In step S460, the registered fingerprint data is stored in the storage device of the fingerprint image processing device 100.

According to an embodiment of the present invention, the step of generating the first filtering result further includes that the processing device of the fingerprint image processing device 100 compares the pixel data corresponding to pixels whose gray level value is greater than the first critical value and less than the second critical value Delete to produce the first filtering result.

According to an embodiment of the present invention, the step of generating the second filtering result further includes that the processing device of the fingerprint image processing device 100 calculates the average gray level value of each pixel according to the first filtering result, and the average value of each pixel Gray scale value, calculate the standard deviation of the complex fingerprint image data. In addition, the processing device of the fingerprint image processing device 100 generates a gray scale value range according to the standard deviation, and deletes pixel data of pixels whose gray scale value is not within the gray scale value range according to the gray scale value range to generate a second Filter results.

According to an embodiment of the invention, the fingerprint image processing method further includes that the processing device of the fingerprint image processing device 100 synthesizes a plurality of fingerprint image data based on the second filtering result to generate registered fingerprint data.

According to the fingerprint image processing method proposed in the embodiment of the present invention, the fingerprint image processing device 100 performs two-stage filtering on the pixel data of the pixels of the plurality of fingerprint image data. The fingerprint image processing device 100 will first delete the pixel data that are too black and too white. Then, the fingerprint image processing device 100 generates a gray scale value range according to the standard deviation of the complex fingerprint image data, and performs a second filtering on the pixel data of the pixel data of the complex fingerprint image data according to the gray scale value range. Therefore, the fingerprint image processing method according to the embodiments of the present invention can reduce the influence of noise and increase the success rate of fingerprint recognition.

The serial numbers in this specification and in the scope of the patent application, such as "first", "second", etc., are for convenience of description only, and there is no sequential relationship between them.

The method and algorithm steps disclosed in the specification of the present invention can be directly applied to hardware and software modules or a combination of both by executing a processor. A software module (including execution instructions and related data) and other data can be stored in data memory, such as random access memory (RAM), flash memory (flash memory), read-only memory (ROM) , Erasable and programmable read-only memory (EPROM), electronically erasable and programmable read-only memory (EEPROM), registers, hard drives, portable applications, CD-ROM (CD- ROM), DVD, or any other computer-readable storage media format in this field. A storage medium can be coupled to a machine device, for example, like a computer/processor (for the convenience of description, it is represented by a processor in this manual), the above processor can read information (such as a program) Code), and write information to storage media. A storage medium can integrate a processor. An application specific integrated circuit (ASIC) includes a processor and a storage medium. A user equipment includes a special application integrated circuit. In other words, the processor and the storage medium are included in the user equipment in a manner that does not directly connect to the user equipment. In addition, in some embodiments, any product suitable for a computer program includes a readable storage medium, where the readable storage medium includes code related to one or more disclosed embodiments. In some embodiments, the computer program product may include packaging materials.

The above paragraphs use multiple levels of description. Obviously, the teachings in this article can be implemented in many ways, and any specific architecture or function disclosed in the example is only a representative situation. According to the teaching of this article, anyone who is familiar with this skill should understand that each level disclosed in this article can be implemented independently or two or more levels can be implemented in combination.

Although this disclosure has been disclosed as above with examples, it is not intended to limit this disclosure. Anyone who is familiar with this skill can make some changes and modifications within the spirit and scope of this disclosure, so the scope of protection of the invention The scope defined in the attached patent application scope shall prevail.

100‧‧‧fingerprint image processing device 110‧‧‧fingerprint sensing device 120‧‧‧processing device 130‧‧‧‧storage device 400‧‧‧flow chart A, B, C, D‧‧‧fingerprint image data S410~S460 ‧‧‧step

FIG. 1 is a block diagram of a fingerprint image processing device 100 according to an embodiment of the invention. FIG. 2 is a schematic diagram showing the grayscale values of the retelling pixels according to an embodiment of the invention. FIG. 3A is a schematic diagram showing a first filtering result according to an embodiment of the invention. FIG. 3B is a schematic diagram showing a second filtering result according to an embodiment of the invention. FIG. 4 is a flowchart of a fingerprint image processing method according to an embodiment of the invention.

400‧‧‧Flowchart

S410~S460‧‧‧Step

Claims (10)

A fingerprint image processing device includes: a fingerprint sensing device that generates a plurality of fingerprint image data; a processing device that is coupled to the fingerprint sensing device and generates a registered fingerprint data; and a storage device that is coupled to the processing device, And storing the registered fingerprint data, wherein when the processing device generates the registered fingerprint data, the processing device compares the grayscale value of each pixel of each of the complex fingerprint image data with a first critical value and a second critical value The values are compared to generate a first filtering result, and the processing device calculates a standard deviation corresponding to the complex fingerprint image data according to the first filtering result, and generates a second filtering result according to the standard deviation, and generates a second filtering result according to the above The second filtering result generates the aforementioned registered fingerprint data. The fingerprint image processing device as described in item 1 of the patent application scope, wherein when the processing device generates the first filtering result, the processing device will correspond to a picture whose gray level value is greater than the first critical value and less than the second critical value The pixel data of the pixel is deleted to generate the first filtering result. The fingerprint image processing device as described in item 2 of the patent application scope, wherein when the processing device generates the second filtering result, the processing device calculates the average grayscale value of each pixel based on the first filtering result, and According to the average grayscale value of each pixel, the standard deviation corresponding to the complex fingerprint image data is calculated. A fingerprint image processing device as described in item 3 of the patent application range, wherein the processing device generates a gray scale value range based on the standard deviation, and the processing device sets the gray scale value out of the gray scale according to the gray scale value range The pixel data of the pixels in the value range is deleted to generate the above-mentioned second filtering result. The fingerprint image processing device as described in item 4 of the patent application scope, wherein the processing device synthesizes the plurality of fingerprint image data based on the second filtering result to generate the registered fingerprint data. A fingerprint image processing method includes: generating a plurality of fingerprint image data by a fingerprint sensing device; a gray scale value and a first critical value of each pixel of each of the plurality of fingerprint image data by a processing device and A second threshold value is compared to generate a first filtering result; the processing device calculates a standard deviation corresponding to the complex fingerprint image data according to the first filtering result; the processing device generates the standard deviation according to the standard deviation A second filtering result; generating a registered fingerprint data according to the second filtering result by the processing device; and storing the registered fingerprint data in a storage device. The fingerprint image processing method as described in item 6 of the patent application scope, wherein the step of generating the first filtering result further comprises: converting pixels corresponding to pixels whose gray level value is greater than the first critical value and less than the second critical value The data is deleted to produce the above-mentioned first filtering result. The fingerprint image processing method as described in item 7 of the patent application scope, wherein the step of generating the second filtering result further includes: calculating the average grayscale value of each pixel according to the first filtering result; and based on each of the above The above-mentioned average gray-scale value of the pixel calculates the above-mentioned standard deviation corresponding to the above-mentioned complex fingerprint image data. The fingerprint image processing method as described in item 8 of the patent application scope further includes: generating a gray scale value range based on the above standard deviation; and drawing a gray scale value out of the gray scale value range based on the gray scale value range The pixel data of the pixel is deleted to generate the above-mentioned second filtering result. The fingerprint image processing method described in item 9 of the patent application scope further includes: synthesizing the plurality of fingerprint image data according to the second filtering result to generate the registered fingerprint data.

Images