TWI650712B - Fingerprint capture method and fingerprint capture module - Google Patents

Abstract

A fingerprint extraction method is executed by a processing unit of a fingerprint extraction module. The method includes: generating a first image; generating a second image after a predetermined time from the generation of the first image; Compare the difference between the first image and the second image to produce a comparison result; determine whether the comparison result meets a first predetermined condition, and when the judgment result is yes, compare the first image and One of the second images is used as a target image; a calculation result related to the contrast of the target image is generated according to the target image; it is determined whether the calculation result meets a second predetermined condition, and the result is determined When so, it sends a capture completion notification to a control host.

Description

Fingerprint capturing method and fingerprint capturing module

The invention relates to a biometrics extraction method, in particular to a fingerprint extraction method for a fingerprint extraction module.

In recent years, fingerprint recognition technology has been gradually applied to portable electronic devices to ensure the safety of users 'data. With the popularity of fingerprint recognition technology, users' requirements for accuracy and fluency in fingerprint recognition have also continuously increased .

The existing fingerprint recognition technology is usually divided into two stages: the first is the "fingerprint retrieval" stage, which is to scan the user's fingerprint and convert it into a fingerprint image; and after the "fingerprint retrieval" stage is a The "recognition" stage is to analyze, compare and identify fingerprint feature points of the captured fingerprint image.

In order to improve the accuracy of the "fingerprint recognition" stage, it is crucial to ensure the accuracy and quality of the fingerprint image in the "fingerprint extraction" stage. Subject.

Therefore, one of the objects of the present invention is to provide a fingerprint capturing method that can improve the reliability of fingerprint capturing.

Therefore, the fingerprint retrieval method of the present invention is executed by a fingerprint retrieval module electrically connected to a control host. The fingerprint retrieval module includes a sensing unit and a processing unit electrically connected to the sensing unit; the fingerprint retrieval The method includes the following steps: (A) The processing unit controls the sensing unit to perform fingerprint detection to generate a first image; (B) The processing unit controls the sensing unit to capture the first image After a predetermined time, control the sensing unit to perform fingerprint detection again to generate a second image; (C) the processing unit compares the difference between the first image and the second image to generate a comparison Results; (D) The processing unit determines whether the comparison result meets a first predetermined condition, and when it is determined that the comparison result meets the first predetermined condition, the first image and the second image One as a target image; (E) the processing unit generates a calculation result related to the contrast of the target image based on the target image; and (F) the processing unit determines whether the calculation result meets a second predetermined Condition and determine the calculation result If the second predetermined condition is met, an acquisition completion notification is sent to the control host.

In some implementation aspects of the fingerprint extraction method of the present invention, in step (C), the method for the processing unit to generate the comparison result is to first multiple the first reference pixels in the first image, respectively Compare with multiple second reference pixels in the second image to generate multiple pixel comparison values, and then calculate the comparison result according to the pixel comparison values. The first reference pixels respectively correspond to the positions of the second reference pixels. Each pixel comparison value is related to the degree of difference in color depth between one of the first reference pixels and one of the corresponding second reference pixels.

In some implementation aspects of the fingerprint capturing method of the present invention, in step (A), the first image includes a plurality of first pixels and a first reference area. In step (B), the second image includes a plurality of second pixels and a second reference area corresponding to the position of the first reference area. In step (C), the first reference pixels are those of which the first pixels are partially located in the first reference area, and the second reference pixels are the portions of the second pixels that are located in the second reference area Insider.

In some implementation aspects of the fingerprint extraction method of the present invention, in step (C), the processing unit takes the sum or standard deviation of all the pixel comparison values as the comparison result. In step (D), the first predetermined condition includes that the comparison result is less than a first predetermined threshold.

In some embodiments of the fingerprint capturing method of the present invention, in step (D), the target image includes a plurality of target pixels, and each target pixel includes a target pixel value related to the color depth of the target pixel, The calculation result is related to the difference or ratio between the largest and the smallest of the target pixel values.

In some implementation aspects of the fingerprint capture method of the present invention, in step (E), the processing unit generates the calculation result by first performing a normalized processing procedure on the target pixel values to obtain more Conversion pixel values corresponding to the target pixel values respectively, and then, the processing unit takes the difference or ratio between the largest and the smallest of the converted pixel values as the calculation result. In step (F), the second predetermined condition includes that the calculation result is greater than a second predetermined threshold.

In some implementation aspects of the fingerprint capturing method of the present invention, in step (E), the processing unit further performs a process on the target image before performing the normalization process on the target pixel values Back handler.

In some implementation aspects of the fingerprint extraction method of the present invention, in step (D), when the processing unit determines that the comparison result does not meet the first predetermined condition, the following steps are performed: (G) The processing unit controls The sensing unit performs fingerprint detection again to generate a third image, compares the difference between the second image and the third image to regenerate the comparison result, and the processing unit determines the regenerated ratio When the result meets the first predetermined condition, one of the second image and the third image is used as the target image, and step (E) is performed.

In some implementation aspects of the fingerprint extraction method of the present invention, in step (D), when the processing unit determines that the comparison result does not meet the first predetermined condition, steps (A) to (C) are performed again.

In some implementation aspects of the fingerprint capture method of the present invention, the fingerprint capture module further includes a storage unit electrically connected to the processing unit, the storage unit stores a contrast parameter related to the first image And the contrast when the second image is generated. In step (A), the processing unit controls the sensing unit to perform fingerprint detection based on the value of the contrast parameter to generate the first image. In step (B), the processing unit controls the sensing unit to perform fingerprint detection based on the value of the contrast parameter to generate the second image. In step (F), when the processing unit determines that the calculation result does not meet the second predetermined condition, the processing unit updates the value of the contrast parameter in a manner of enhancing contrast, and controls the sensing unit to perform fingerprint detection again Measure to generate an adjusted image, and directly use the adjusted image as the target image, and then perform step (E) again.

Another object of the present invention is to provide a fingerprint retrieval module that implements the fingerprint retrieval method.

The fingerprint capture module of the present invention includes a sensing unit and a processing unit electrically connected to the sensing unit. The processing unit is adapted to be electrically connected to a control host. The processing unit controls the sensing unit to perform fingerprint detection to generate a first image. After controlling the sensing unit to capture the first image for a predetermined time, the processing unit controls the sensing unit to perform fingerprint detection again to generate a second image. The processing unit compares the difference between the first image and the second image to generate a comparison result. The processing unit determines whether the comparison result meets a first predetermined condition, and when determining that the comparison result meets the first predetermined condition, uses one of the first image and the second image as a target image. The processing unit generates a calculation result related to the contrast of the target image according to the target image. The processing unit determines whether the calculation result meets a second predetermined condition, and when it determines that the calculation result meets the second predetermined condition, sends a capture completion notification to the control host.

In some embodiments of the fingerprint capture module of the present invention, the processing unit generates the comparison result by first combining the first reference pixels in the first image with the second image Multiple second reference pixels in the comparison to generate multiple pixel comparison values, and then calculate the comparison result according to the pixel comparison values. The first reference pixels respectively correspond to the positions of the second reference pixels. Each pixel comparison value is related to the degree of difference in color depth between one of the first reference pixels and one of the corresponding second reference pixels.

In some embodiments of the fingerprint capture module of the present invention, the first image includes a plurality of first pixels and a first reference area. The second image includes a plurality of second pixels, and a second reference area corresponding to the position of the first reference area. The first reference pixels are those in which the first pixels are partially located in the first reference area, and the second reference pixels are those in which the second pixels are partially located in the second reference area.

In some implementation aspects of the fingerprint capture module of the present invention, the processing unit takes the sum or standard deviation of all the pixel comparison values as the comparison result. The first predetermined condition includes that the comparison result is less than a first predetermined threshold.

In some embodiments of the fingerprint capture module of the present invention, the target image includes a plurality of target pixels, each target pixel includes a target pixel value related to the color depth of the target pixel, and the calculation result is related to the The difference or ratio between the largest one and the smallest one of the target pixel values.

In some embodiments of the fingerprint capture module of the present invention, the processing unit generates the calculation result by first performing a normalized processing procedure on the target pixel values to obtain multiple corresponding targets respectively The converted pixel value of the pixel value, and then, the processing unit takes the difference or ratio between the largest one and the smallest one of the converted pixel values as the calculation result. The second predetermined condition includes that the calculation result is greater than a second predetermined threshold.

In some implementation aspects of the fingerprint capture module of the present invention, before performing the normalization processing procedure on the target pixel values, the processing unit further performs a de-backing processing procedure on the target image.

In some implementation aspects of the fingerprint capture module of the present invention, when the processing unit determines that the comparison result does not meet the first predetermined condition, the processing unit controls the sensing unit to perform fingerprint detection again to generate a first Three images, compare the difference between the second image and the third image to regenerate the comparison result, and the processing unit determines that the regenerated comparison result meets the first predetermined condition, One of the two images and the third image is used as the target image, and the calculation result is generated according to the target image.

In some implementation aspects of the fingerprint capture module of the present invention, when the processing unit determines that the comparison result does not meet the first predetermined condition, the sensing unit is again controlled to perform fingerprint detection to generate the first image 5. After the predetermined time, control the sensing unit to perform fingerprint detection again to generate the second image, and compare the difference between the first image and the second image to generate the comparison result.

In some implementation aspects of the fingerprint capture module of the present invention, the fingerprint capture module further includes a storage unit electrically connected to the processing unit, the storage unit stores a contrast parameter, and the contrast parameter is related to the first image The image and the contrast at the time the second image is generated. The processing unit controls the sensing unit to perform fingerprint detection based on the value of the contrast parameter to generate the first image. The processing unit controls the sensing unit to perform fingerprint detection based on the value of the contrast parameter to generate the second image. When the processing unit determines that the calculation result does not meet the second predetermined condition, the processing unit updates the value of the contrast parameter in a manner of enhancing contrast, and controls the sensing unit to perform fingerprint detection again to generate an adjusted image , And directly use the adjusted image as the target image, and then generate the calculation result based on the target image again.

The effect of the present invention is that the fingerprint capturing module can determine the comparison between the first image and the second image when the user presses a finger on the sensing unit by implementing the fingerprint capturing method Whether the result meets the first predetermined condition, and it is ensured that the area where the sensing unit is pressed by the finger is in a stable state. Further, the fingerprint extraction module can also determine whether the calculation result generated according to the target image meets the second predetermined condition, and ensure that the contrast of the target image is high enough, which is conducive to subsequent fingerprint identification procedures. By implementing the fingerprint capture method, the fingerprint capture module of this embodiment can capture a stable and clear fingerprint image, ensuring the accuracy and quality of the fingerprint image, and indeed improving the fingerprint recognition technology. Reliability at the "Fingerprint Retrieval" stage.

Referring to FIG. 1, an embodiment of the fingerprint capture module 1 of the present invention is suitable for scanning the fingerprint of a user's finger and converting it into a grayscale fingerprint image. The fingerprint extraction module 1 includes a sensing unit 11, a storage unit 12, and a processing unit 13 electrically connected to the sensing unit 11 and the storage unit 12.

The storage unit 12 stores a contrast parameter. In this embodiment, the contrast parameter may represent, for example, a gain compensation value in a compensation analog circuit, which is related to the contrast when the fingerprint image is generated. For example, the higher the value of the contrast parameter, the higher the contrast of the fingerprint image generated by the fingerprint retrieval module 1; conversely, the lower the value of the contrast parameter, the generated by the fingerprint retrieval module 1 The contrast of the fingerprint image is also lower, but not limited to this.

In this embodiment, the processing unit 13 is suitable for electrically connecting a control host 50 with a fingerprint identification function, but it is not limited thereto.

Referring to FIGS. 1 and 2 at the same time, the following describes in detail a fingerprint capturing method implemented by the fingerprint capturing module 1 of this embodiment.

First, in step S1, when the sensing unit 11 is pressed by a user's finger, for example, the sensing unit 11 generates and transmits an operation notification to the processing unit 13. Then, step S2 is executed.

In step S2, when the processing unit 13 receives the operation notification, the processing unit 13 controls the sensing unit 11 to perform fingerprint detection with the value of the contrast parameter to generate a first image. In this embodiment, the first image includes a plurality of first pixels and a first reference area. The first pixels are arranged in a matrix, and partial fingerprints of the user's fingers are presented in different shades of gray. The first reference area may be, for example, a closed area formed in the geometric center of the first image, and the shape of the first reference area may be, for example, a rectangle or a circle, but it is not limited thereto. For convenience of description, the first pixels are defined as a plurality of first reference pixels, some of which are located in the first reference area. Then, step S3 is executed.

In step S3, after controlling the sensing unit 11 to capture the first image for a predetermined time, the processing unit 13 controls the sensing unit 11 to perform fingerprint detection again to generate a second image. Similar to the first image, the second image includes multiple second pixels and a second reference area. For the convenience of description, the second pixels are defined herein as part of the second reference area being a plurality of second reference pixels. The second pixels also present partial fingerprints of the user's fingers in different shades of gray, and the positions of the second reference area and the first reference area correspond to each other. More precisely, the first reference area and the second reference area have the same shape, size, and center point position. Therefore, the number of the first reference pixels and the second reference pixels are the same, and the first A reference pixel also corresponds in position to the second reference pixels, respectively. The predetermined time may be 500 milliseconds, for example, but not limited to this.

In particular, from when the user's finger touches the sensing unit 11 to when the user fully presses the finger on the sensing unit 11, the area where the sensing unit 11 is pressed by the finger is From small to large, that is to say, in the aforementioned process, the area of the sensing unit 11 that is pressed by the finger is in an unstable state. Therefore, even if the first image and the second image both show partial fingerprints of the same finger, the shape and range of the partial fingerprints presented by the first image and the second image are still possible different. Then, step S4 is executed.

In step S4, the processing unit 13 compares the difference between the first image and the second image to generate a comparison result. Specifically, in this embodiment, the processing unit 13 generates the comparison result by first comparing the first reference pixels in the first image with the multiple reference pixels in the second image. The second reference pixel is compared to generate multiple pixel comparison values, and then the equal pixel comparison values are added together to calculate the comparison result.

Each pixel comparison value is related to the degree of difference in color depth between one of the first reference pixels and one of the corresponding second reference pixels. For an 8-bit grayscale image, each pixel in the image represents a color shade with a value between 0 and 255, where 0 represents black, and 255 represents white, for example. Assuming that the pixel value of one of the first reference pixels is X ₁ and the pixel value of _{one of the} corresponding second reference pixels is Y ₁ , then the pixel ratio of the first reference pixel to the second reference pixel The pair value may be, for example, an absolute value of the difference between X ₁ and Y ₁ , but not limited thereto. Therefore, if the pixel comparison value is larger, it means that the color difference between the first reference pixel and the second reference pixel is greater.

According to the foregoing description, the comparison result indicates the degree of difference between the first image and the second image. If the value of the comparison result is greater, the greater the difference between the first image and the second image, and conversely, if the value of the comparison result is smaller, it represents the first image and the The higher the similarity of the second image.

It is added that in other embodiments, the processing unit 13 may also use the standard deviation of all pixel comparison values (or "mean square deviation", English as Standard Deviation) as the comparison result, but it does not use This is limited.

Then, step S5 is executed.

In step S5, the processing unit 13 determines whether the comparison result meets a first predetermined condition. In this embodiment, the first predetermined condition includes that the comparison result is less than a first predetermined threshold. When the judgment result of the processing unit 13 is yes, the processing unit 13 uses the second image as a target image, and executes step S7. When the judgment result of the processing unit 13 is NO, step S6 is executed. It is added that in other embodiments, when the judgment result of the processing unit 13 is yes, the processing unit 13 may also use the first image as the target image, not limited to this embodiment .

In step S6, when the processing unit 13 determines that the comparison result does not meet the first predetermined condition, the processing unit 13 controls the sensing unit 11 to perform fingerprint detection again to generate a third image. Similar to the first image and the second image, the third image includes a plurality of third pixels and a third reference area, and defines a portion of the third pixels in the third reference area These are multiple third reference pixels. The processing unit 13 compares the difference between the second image and the third image in the same way as in step S4 to regenerate the comparison result. Then, the processing unit 13 judges whether the regenerated comparison result meets the first predetermined condition, and when the judgment result is yes, the third image is used as the target image. However, in other embodiments, when the judgment result of the processing unit 13 is yes, the processing unit 13 may also use the second image as the target image, and is not limited to this embodiment.

It is added that if in step S6, the processing unit 13 determines that the regenerated comparison result still does not meet the first predetermined condition, it will continue to control the sensing unit 11 to perform fingerprint detection to generate a frame The new image is compared with the last two generated images until it is judged that the final comparison result meets the first predetermined condition and the target image is selected. Then, step S7 is executed.

In step S7, the processing unit 13 generates a calculation result related to the contrast of the target image according to the target image. In this embodiment, the target image contains multiple target pixels. For example, if in step S5, the processing unit 13 uses the second image as the target image, then the second pixels included in the second image are the same as described in step S7 Wait for the target pixel. Each target pixel includes a target pixel value related to the color depth of the target pixel (that is, for example, a value between 0 and 255 is used to represent the color depth).

Specifically, in this embodiment, the manner in which the processing unit 13 generates the calculation result includes the following sub-steps: I. The processing unit 13 performs a de-backing process on the target image to remove the target image Noise or noise in the background. II. The processing unit 13 performs a normalized processing procedure on the target pixel values to convert into a plurality of converted pixel values corresponding to the target pixel values, respectively. More specifically, the value range of each target pixel value is, for example, between 0 and 255, and the value range of each converted pixel value obtained by the normalization process is between 0 and 255 Between 1, and the sum of all the converted pixel values is 1, so that the processing unit 13 can perform subsequent operations with the converted pixel values, but not limited to this. III. The processing unit 13 uses the ratio between the largest one and the smallest one of the target pixel values as the calculation result. However, in other embodiments, the processing unit 13 may also use the difference between the maximum converted pixel value and the minimum converted pixel value as the calculation result, and is not limited to this embodiment.

Specifically, the larger the value of the calculation result, the higher the contrast of the target image, that is, the clearer the target image.

It is added that in other embodiments, the target image further includes a target reference area corresponding to the positions of the first reference area and the second reference area, and the processing unit 13 may be referenced by the target, for example A plurality of target reference pixels in the area perform the de-backing processing procedure, the normalization processing procedure and generate the calculation result, which is not limited to this embodiment.

Then, step S8 is executed.

In step S8, the processing unit 13 determines whether the calculation result meets a second predetermined condition. In this embodiment, the second predetermined condition includes that the calculation result is greater than a second predetermined threshold. When the judgment result of the processing unit 13 is YES, step S10 is executed. When the judgment result of the processing unit 13 is NO, step S9 is executed.

In step S9, when the processing unit 13 determines that the calculation result does not meet the second predetermined condition, it means that the contrast of the target image is insufficient, and is not suitable for subsequent fingerprint recognition. At this time, the processing unit 13 updates the value of the contrast parameter in a way to enhance the contrast. For example, the processing unit 13 may set the converted pixel values into a prediction formula to calculate a prediction result, and according to The estimation result increases the contrast parameter, but not limited to this. It is added that since the converted pixel values are obtained through the normalization process, the value range is between 0 and 1. In addition, the estimation formula is also for the value range between 0 and 1. The sample value between 1 and 1 is set, so that the processing unit 13 can quickly obtain the estimated result according to the estimated formula. With this, the processing unit 13 can regenerate a new image with higher contrast. Then, the processing unit 13 controls the sensing unit 11 to perform fingerprint detection again to generate an adjusted image with the updated contrast parameter, and directly uses the adjusted image as the target image, and then restarts from step S7 Begin execution. However, in other embodiments, the processing unit 13 may also execute the step S2 again after updating the value of the contrast parameter, and is not limited to this embodiment.

In step S10, the processing unit 13 generates and sends a capture completion notification to the control host 50. Then, step S11 is executed.

In step S11, when the processing unit 13 receives an image request from the control host 50, the processing unit 13 transmits the target image to the control host 50 in response to the image request for the control The host 50 performs a subsequent fingerprint recognition process on the target image.

In summary, the fingerprint capturing module 1 of this embodiment can determine the first image and the second image when the user presses a finger on the sensing unit 11 by implementing the fingerprint capturing method Whether the comparison result of the image meets the first predetermined condition, while ensuring that the area where the sensing unit 11 is pressed by the finger is in a stable state. Further, the fingerprint extraction module 1 can also determine whether the calculation result generated according to the target image meets the second predetermined condition, and ensure that the contrast of the target image is high enough, which is conducive to the subsequent fingerprint identification process . By implementing the fingerprint capture method, the fingerprint capture module 1 of this embodiment can capture a stable and clear fingerprint image, ensuring the accuracy and quality of the fingerprint image, and indeed improving the fingerprint recognition technology The reliability of the "fingerprint extraction" stage can indeed achieve the purpose of cost invention.

However, the above are only examples of the present invention, and should not be used to limit the scope of implementation of the present invention, any simple equivalent changes and modifications made according to the scope of the patent application of the present invention and the content of the patent specification are still considered as Within the scope of the invention patent.

1‧‧‧ fingerprint capture module

11‧‧‧sensing unit

12‧‧‧Storage unit

13‧‧‧Processing unit

50‧‧‧Control host

S1 ~ S11‧‧‧Step

Other features and functions of the present invention will be clearly presented in the embodiment with reference to the drawings, in which: FIG. 1 is a block diagram illustrating an embodiment of the fingerprint capture module of the present invention electrically connected to a control host ; And FIG. 2 is a flowchart illustrating how to implement a fingerprint extraction method in this embodiment.

Claims (11)

A fingerprint retrieval method is executed by a fingerprint retrieval module electrically connected to a control host, the fingerprint retrieval module includes a sensing unit, and a processing unit electrically connected to the sensing unit; the fingerprint retrieval method It includes the following steps: (A) The processing unit controls the sensing unit to perform fingerprint detection to generate a first image; (B) The processing unit controls the sensing unit to capture a predetermined image from the first image After time, control the sensing unit to perform fingerprint detection again to generate a second image; (C) the processing unit compares the difference between the first image and the second image to generate a comparison result; (D) The processing unit determines whether the comparison result meets a first predetermined condition, and when determining that the comparison result meets the first predetermined condition, the one of the first image and the second image As a target image; (E) the processing unit generates a calculation result related to the contrast of the target image based on the target image; and (F) the processing unit determines whether the calculation result meets a second predetermined condition, And judge that the calculation result is consistent When the second predetermined condition is reached, an acquisition completion notification is sent to the control host. The fingerprint extraction method according to claim 1, wherein, in step (C): the method for the processing unit to generate the comparison result is to first multiple the first reference pixels in the first image, respectively Comparing with a plurality of second reference pixels in the second image to generate a plurality of pixel comparison values, and then calculating the comparison result according to the pixel comparison values; wherein the first reference pixels are respectively The positions of the second reference pixels correspond to each other; and each pixel comparison value is related to the degree of color difference between one of the first reference pixels and one of the corresponding second reference pixels. The fingerprint extraction method according to claim 2, wherein: in step (A), the first image includes a plurality of first pixels and a first reference area; in step (B), the second The image includes a plurality of second pixels and a second reference area corresponding to the position of the first reference area; and in step (C), the first reference pixels are part of the first pixels located in the In the first reference area, the second reference pixels are those in which the second pixels are partially located in the second reference area. The fingerprint extraction method according to claim 2, wherein: in step (C), the processing unit takes the sum or standard deviation of all the pixel comparison values as the comparison result; and in step (D) In this, the first predetermined condition includes that the comparison result is less than a first predetermined threshold. The fingerprint extraction method according to claim 1, wherein in step (D), the target image includes a plurality of target pixels, and each target pixel includes a target pixel value related to the color depth of the target pixel, The calculation result is related to the difference or ratio between the largest and the smallest of the target pixel values. The fingerprint extraction method according to claim 5, wherein: In step (E), the processing unit generates the calculation result by first performing a normalization process on the target pixel values to obtain multiple Converted pixel values corresponding to the target pixel values, respectively, the processing unit then uses the difference or ratio between the largest and the smallest of the converted pixel values as the calculation result; and in step (F ), The second predetermined condition includes that the calculation result is greater than a second predetermined threshold. The fingerprint extraction method according to claim 6, wherein in step (E), the processing unit further performs a process on the target image before performing the normalization process on the target pixel values Back handler. The fingerprint extraction method according to claim 1, wherein, in step (D), when the processing unit determines that the comparison result does not meet the first predetermined condition, the following steps are performed: (G) The processing unit controls The sensing unit performs fingerprint detection again to generate a third image, compares the difference between the second image and the third image to regenerate the comparison result, and the processing unit determines the regenerated ratio When the result meets the first predetermined condition, one of the second image and the third image is used as the target image, and step (E) is performed. The fingerprint extraction method according to claim 1, wherein in step (D), when the processing unit determines that the comparison result does not meet the first predetermined condition, steps (A) to (C) are performed again. According to the fingerprint retrieval method of claim 1, the fingerprint retrieval module further includes a storage unit electrically connected to the processing unit, the storage unit stores a contrast parameter related to the first image and the Contrast when the second image is generated; wherein: in step (A), the processing unit controls the sensing unit to perform fingerprint detection with the value of the contrast parameter to generate the first image; in step (B) In the process, the processing unit controls the sensing unit to perform fingerprint detection with the value of the contrast parameter to generate the second image; and in step (F), when the processing unit determines that the calculation result does not conform to the first Under two predetermined conditions, the processing unit updates the value of the contrast parameter in a way to enhance the contrast, and controls the sensing unit to perform fingerprint detection again to generate an adjusted image, and directly uses the adjusted image as the target image Then, perform step (E) again. A fingerprint retrieval module is suitable for being electrically connected to a control host, and used to execute the fingerprint retrieval method described in any one of the request items 1 to 10.