Electronic device and method for processing fingerprint image

Abstract

A method for processing a fingerprint image in an electronic device, the method comprising: obtaining an original fingerprint image by sensing a user's fingerprint; estimating a spatial change trend of an original contrast value in the original fingerprint image; generating a reference contrast map based on the estimated spatial change trend; normalizing the contrast distribution of the original fingerprint image based on the reference contrast map, and generating a normalized fingerprint image with a normalized contrast distribution.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the priority of Korean Patent Application No. 10-2019-0105002 filed on August 27, 2019, in the Korean Intellectual Property Office, the disclosure of which is incorporated herein by reference in its entirety. Technical Field

[0003] Apparatuses and methods consistent with example embodiments relate to processing a fingerprint image in an electronic device. Background Art

[0004] The demand for performing personal authentication based on personal characteristics such as fingerprints, voice, face, hand or iris is gradually increasing. The personal authentication function is mainly used in financial equipment, access control equipment, mobile devices, laptops, etc. Recently, as mobile devices such as smart phones have become popular, fingerprint recognition technology for personal authentication has been widely adopted to protect a large amount of security information stored in smart phones. Summary of the invention

[0005] An electronic device and a method for processing a fingerprint image in the electronic device are provided. The technical objectives of the presented embodiments are not limited to the above technical objectives, and other technical objectives can be derived from the following embodiments.

[0006] Additional aspects will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the embodiments presented in the disclosure.

[0007] According to an aspect of an embodiment, a method for processing a fingerprint image in an electronic device is provided, comprising: obtaining an original fingerprint image by sensing a user fingerprint; estimating a spatial change trend of an original contrast value from the original fingerprint image based on a contrast distribution of original contrast values ​​of pixels of the original fingerprint image; generating a reference contrast map indicating reference contrast values ​​of pixels determined based on the estimated spatial change trend; normalizing the contrast distribution of the original fingerprint image by comparing the original contrast values ​​of the original fingerprint image with reference contrast values ​​of the reference contrast map; and generating a normalized fingerprint image having a normalized contrast distribution.

[0008] According to an aspect of another embodiment, a non-transitory computer-readable recording medium is included, the non-transitory computer-readable recording medium including a recording medium having recorded thereon at least one program including instructions for executing the method.

[0009] According to an aspect of another embodiment, an electronic device for processing a fingerprint image includes: a fingerprint sensor configured to obtain an original fingerprint image by sensing a user's fingerprint; and a processor configured to estimate a spatial change trend of an original contrast value from the original fingerprint image based on a contrast distribution of the original contrast values ​​of pixels of the original fingerprint image; generate a reference contrast map indicating reference contrast values ​​of pixels determined based on the estimated spatial change trend; normalize the contrast distribution of the original fingerprint image by comparing the original contrast values ​​of the original fingerprint image with reference contrast values ​​of the reference contrast map; and generate a normalized fingerprint image with a normalized contrast distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and / or other aspects will become more apparent by describing certain example embodiments with reference to the accompanying drawings, in which:

[0011] Figure 1 An example of a fingerprint sensor installed in an electronic device according to an embodiment is shown;

[0012] Figure 2 shows hardware components of an electronic device according to an embodiment;

[0013] Figure 3 conceptually illustrates mutual capacitance corresponding to each node of a touch panel according to an embodiment;

[0014] Figure 4 is a diagram for describing fingerprint images corresponding to different pressure intensities of a user's finger contacting a fingerprint sensor according to an embodiment;

[0015] Figure 5 is a diagram for describing a situation in which the pressure of a finger contacting a fingerprint sensor is not uniformly distributed in the fingerprint sensor according to an embodiment;

[0016] Figure 6 is a diagram for describing a process of performing fingerprint authentication in a processor of an electronic device according to an embodiment;

[0017] Figure 7 is a diagram for describing a process of performing normalization on a fingerprint image according to an embodiment;

[0018] Figure 8 is a diagram for describing contrast data of a fingerprint image adjusted by normalization of contrast distribution according to an embodiment;

[0019] Fig. 9 is a flow chart of a method for processing a fingerprint image in an electronic device according to an embodiment;

[0020] Fig.10is a diagram for describing a normalized result of contrast distribution of a fingerprint image according to an embodiment; and

[0021] Fig.11 is a graph for comparing fingerprint recognition rates of image processing results according to the related art and the present embodiment for an original fingerprint image with uneven contrast distribution according to the embodiment. DETAILED DESCRIPTION

[0022] Example embodiments are described in more detail below with reference to the accompanying drawings.

[0023] In the following description, similar reference numerals are used for similar elements, even in different drawings. The contents defined in the description, such as detailed construction and elements, are provided to assist in a comprehensive understanding of the exemplary embodiments. However, it is apparent that the exemplary embodiments can be practiced without these specifically defined contents. In addition, well-known functions or constructions are not described in detail because they would obscure the description with unnecessary details.

[0024] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items. Expressions such as "at least one of...", when following a list of elements, modify the entire list of elements rather than modifying the individual elements in the list. For example, the expression "at least one of a, b, and c" should be understood to include only a, only b, only c, both a and b, both a and c, both b and c, all of a, b, and c, or any variation of the above examples.

[0025] In the embodiments described herein, if possible, common terms that are widely used today are selected, but non-common terms can be selected according to the intentions, precedents, or new technologies of those skilled in the art. Some terms can be selected arbitrarily by the applicant. In this case, the meaning of these terms will be explained in detail in the corresponding parts of this disclosure. Therefore, the terms used herein should not be defined based on their names, but should be defined based on the entire context of their meanings and embodiments.

[0026] The terms “comprising,” “including,” “include,” and “comprising” used herein should not be interpreted as necessarily including all the various elements or operations described herein, and it should be understood that some elements or operations may be omitted or additional elements or operations may be further provided.

[0027] Hereinafter, the embodiments will be described in detail with reference to the accompanying drawings. However, the embodiments may be embodied in many different forms and should not be construed as limited to the examples set forth herein.

[0028] Figure 1An example of a fingerprint sensor installed in an electronic device according to an embodiment is shown.

[0029] refer to Figure 1 The fingerprint sensor 10 of the electronic device 1 may include a plurality of layers, including a passivation layer 102, an insulating layer 104, and a substrate 106. The fingerprint sensor 10 may further include a detection electrode Rx 103 located between the passivation layer 102 and the insulating layer 104, and a driving electrode Tx 105 located between the insulating layer 104 and the substrate 106.

[0030] The touch display panel 11 may be provided on the front surface of the electronic device 1, and the touch display panel 11 may correspond to a touch input interface for manipulating the electronic device 1. A portion of the entire area of ​​the touch display panel 11 may be used as a fingerprint sensor 10 for sensing a fingerprint of a user's fingertip 101. The fingerprint sensor 10 may recognize a fingerprint pattern of the user by acquiring a fingerprint image of the user, and recognize the fingerprint of the user by detecting different mutual capacitances of ridges and valleys (i.e., differences in the amount of change in mutual capacitance).

[0031] Meanwhile, for ease of description, the fingerprint sensor 10 is shown as corresponding to a portion of the touch display panel 11 on the front surface of the electronic device 1. However, the present disclosure is not limited thereto, and the fingerprint sensor 10 according to the present embodiment may be implemented in various locations, for example, on the rear surface or side surface of the electronic device 1, or in another area different from the touch display panel 11.

[0032] The electronic device 1 is a computing device including a fingerprint sensor 10, and may be, for example, a personal computer (PC), a laptop computer, a mobile device, etc., or may also be an autonomous vehicle, a robot, a smart phone, a tablet device, an augmented reality (AR) device, an Internet of Things (IoT) device, but is not limited thereto and may be various types of devices.

[0033] Figure 2 Hardware components of an electronic device according to an embodiment are shown.

[0034] refer to Figure 2 , the electronic device 1 may include a fingerprint sensor 10, a processor 130, and a memory 140, wherein the fingerprint sensor 10 includes a transmitting circuit 110, a touch panel 115, and a receiving circuit 120. Figure 2 The constituent elements of the fingerprint sensing system 10 are shown, but it will be appreciated by those skilled in the art that additional elements may be included therein.

[0035] The processor 130 may be implemented by an array of multiple logic gates, or by a combination of a general-purpose microprocessor and a memory in which a program executable by the microprocessor is stored. The processor 130 may include at least one processor (or processing unit). In addition, it should be understood by those skilled in the art that the processor 130 may be implemented by any other arbitrary form of hardware configuration.

[0036] The touch panel 115 may include a plurality of driving electrodes Tx and a plurality of detecting electrodes Rx formed in a direction intersecting the plurality of driving electrodes Tx. Although for ease of explanation, Figure 2 It is shown that the number of each of the plurality of driving electrodes Tx and the plurality of detecting electrodes Rx is ten, but the present disclosure is not limited thereto, and the numbers of the plurality of driving electrodes Tx and the plurality of detecting electrodes Rx may vary.

[0037] The transmission circuit 110 may include a module that applies a driving signal to a plurality of driving electrodes Tx, and the reception circuit 120 may include a module that measures an electrical signal from a plurality of detection electrodes Rx.

[0038] The driving electrodes Tx and the detecting electrodes Rx of the touch panel 115 may extend in directions intersecting each other. Figure 2 An embodiment in which the driving electrodes Tx and the detecting electrodes Rx are orthogonal to each other is shown, but the present disclosure is not limited thereto. In other words, the angle between the direction in which the driving electrodes Tx extend and the direction in which the detecting electrodes Rx extend may be greater than or less than 90°.

[0039] When the user's finger approaches the touch panel 115, the mutual capacitance between each of the driving electrodes Tx and the detecting electrodes Rx of the touch panel 115 may vary. For example, the mutual capacitance at each node where the driving electrodes Tx and the detecting electrodes Rx intersect each other in the touch panel 115 may be different from each other based on the characteristics of the fingerprint pattern of the user's finger. As the intervals between the driving electrodes Tx and the intervals between the detecting electrodes Rx decrease, the sensing resolution for sensing the fingerprint area may increase.

[0040] The driving electrode Tx and the detection electrode Rx may be set as line electrodes. In addition, each driving electrode Tx may also include a pattern arranged between nodes where the driving electrode Tx and the detection electrode Rx intersect each other. The pattern may have various shapes, such as a polygon or a circle. Similarly, each detection electrode Rx may also include a pattern arranged between nodes.

[0041] The transmitting circuit 110 may apply a driving signal to the driving electrode Tx. For example, the transmitting circuit 110 may apply a voltage pulse to each driving electrode Tx. The receiving circuit 120 may obtain an electrical signal from the detection electrode Rx. In this state, the receiving circuit 120 may obtain a current flowing in each detection electrode Rx or measure the potential of each detection electrode Rx.

[0042] The processor 130 may control the overall operation of the transmission circuit 110 and the reception circuit 120 included in the fingerprint sensor 10. For example, the processor 130 may control the amplitude and duration of the voltage pulse applied to each driving electrode Tx by the transmission circuit 110. In addition, the processor 130 may control the transmission circuit 110 so that the voltage pulse may be applied to some driving electrodes Tx.

[0043] The processor 130 may generate and process fingerprint image data related to the user's fingerprint or the user's detail data by using the current or potential received by the receiving circuit 120. For example, the processor 130 may obtain and process fingerprint image data corresponding to a fingerprint area by using the current or potential received by the receiving circuit 120, and process user authentication by analyzing pixel values ​​included in the fingerprint image data.

[0044] The memory 140 may store computer programs required for the operation of the processor 130. For example, the processor 130 may read the computer program stored in the memory 140 and perform operations based on instructions in the computer program stored in the memory 140. In addition, the memory 140 may store data and information generated based on the operations of the touch panel 115, the transmission circuit 110, the reception circuit 120, and the processor 130. Figure 2 It is illustrated that the electronic device 1 includes one memory as the memory 140 , but the present disclosure is not limited thereto, and the electronic device 1 may include two or more memories as necessary.

[0045] Figure 3 Mutual capacitance corresponding to each node of a touch panel according to an embodiment is conceptually illustrated.

[0046] refer to Figure 3 , the mutual capacitance between the driving electrode Tx and the detecting electrode Rx may correspond to the capacitance at a node where the driving electrode Tx and the detecting electrode Rx intersect each other.

[0047] For example, the mutual capacitance C between the first driving electrode Tx1 and the first detecting electrode Rx1 is 11 The node N may correspond to a node where the first driving electrode Tx1 and the first detecting electrode Rx1 intersect each other. 11Similarly, the mutual capacitance C between the mth driving electrode Txm (where m is a natural number) and the nth detecting electrode Rxn (where n is a natural number) is mn The node N may correspond to a node where the m-th driving electrode Txm and the n-th detecting electrode Rxn intersect each other. mn In the following description, the node N mn The mutual capacitance at represents the mutual capacitance between the m-th driving electrode Txm and the n-th detecting electrode Rxn.

[0048] A plurality of channels may be defined in the touch panel 115 by the driving electrodes Tx and the detecting electrodes Rx. For example, a channel may correspond to a node defined by the driving electrodes Tx and the detecting electrodes Rx intersecting each other. 11 Can correspond to node N 11 .

[0049] Different driving signals may be sequentially applied to each driving electrode Tx to obtain mutual capacitance at each of the plurality of nodes. In addition, electrical signals may be obtained separately at each detection electrode Rx. For example, when mutual capacitance C is to be obtained, 11 When the mutual capacitance C is obtained, the driving signal can be applied only to the first driving electrode Tx1, and the electrical signal can be obtained at the first detection electrode Rx1. mn When the driving signal is applied only to the mth driving electrode Txm, an electrical signal can be obtained at the nth detecting electrode Rxn.

[0050] Figure 4 is a diagram for describing fingerprint images corresponding to different pressure intensities of a user's finger contacting a fingerprint sensor according to an embodiment.

[0051] Fingerprint sensor 10 ( Figure 1 ) by detecting the difference ΔC in the mutual capacitance change between the ridges and valleys of the user’s fingerprint M To generate fingerprint images. Figure 4 , based on a situation where the user contacts the fingerprint sensor 10 with a normal pressure intensity (for example, when the user applies a pressure that is higher than a predetermined low pressure threshold and lower than a predetermined high pressure threshold), the following situations are shown: a situation where the finger is contacted with a pressure intensity higher than normal pressure intensity (for example, when the user applies a pressure that is higher than a predetermined high pressure threshold); and a situation where the finger is contacted with a pressure intensity lower than normal pressure intensity (for example, when the user applies a pressure that is lower than a predetermined low pressure threshold).

[0052] When the finger is brought into contact with the fingerprint sensor 10 with normal pressure intensity, a normal difference ΔC based on the amount of change in mutual capacitance may be generated. MIn contrast, when the finger is brought into contact with the fingerprint sensor 10 with a pressure intensity higher than normal, a large difference ΔC based on the amount of change in mutual capacitance may be generated. M The fingerprint image 401 is a fingerprint image of a structure having a larger overall contrast than the fingerprint image 402. In contrast, when the finger is brought into contact with the fingerprint sensor 10 with a pressure intensity lower than normal, a small difference ΔC based on the amount of change in mutual capacitance may be generated. M The fingerprint image 403 has an overall contrast lower than that of the fingerprint image 402.

[0053] That is, the contrast distribution of the fingerprint image may vary according to the pressure intensity with which the user contacts the fingerprint sensor 10 with the finger. This is because the height difference between the ridges and valleys in the fingerprint varies according to the pressure intensity. Therefore, even when the same finger is contacted, fingerprint images of different qualities may be obtained depending on the pressure intensity of the finger contact, and such fingerprint images of different qualities may affect the fingerprint authentication of the user.

[0054] Figure 5 is a diagram for describing a case where pressure of a finger contacting a fingerprint sensor is not uniformly distributed in the fingerprint sensor according to an embodiment.

[0055] refer to Figure 5 , when the user puts his finger into contact with the fingerprint sensor 10 ( Figure 1 ), the force of the finger may be unevenly distributed on the fingerprint sensor 10, and thus, fingerprint images 501, 502, and 503 with uneven contrast distribution may be obtained. For example, a fingerprint image 501 with a contrast distribution in which the lower portion is dark and the upper portion is bright may be obtained, or a fingerprint image 502 or 503 with different contrast between the left and right may be obtained. When the contrast distribution is uneven, accurate fingerprint pattern information cannot be extracted when processing the fingerprint image, and thus, the performance of fingerprint authentication may be degraded.

[0056] According to the related art, contrast stretching technology, histogram equalization technology, etc. have been proposed as preprocessing to improve the uneven contrast distribution in the fingerprint image. In these technologies, the contrast value concentrated on a specific area in the fingerprint image is normalized to the distribution of the entire fingerprint image. However, the subtle difference is that in the contrast stretching technology, normalization is performed by using the ratio of the minimum value to the maximum value among the pixel values ​​in the fingerprint image, while the histogram equalization technology is performed by equalizing the original pixel value to a pixel value of 0 to 255. However, when the image has an irregular contrast distribution and its contrast value is within a wide range, the normalization effect of the contrast stretching technology or the histogram equalization technology according to the related art may be small. Therefore, regardless of the uneven contrast distribution of the fingerprint image, a method for effectively normalizing the contrast distribution of the fingerprint image is required.

[0057] Figure 6 is a diagram for describing a process of performing fingerprint authentication in a processor of an electronic device according to an embodiment.

[0058] refer to Figure 6 In operation 601 , the processor 130 obtains a fingerprint image according to a fingerprint of a user sensed using the fingerprint sensor 10 .

[0059] In operation 602, the processor 130 performs image normalization processing on the fingerprint image as preprocessing to improve the image quality of the obtained fingerprint image. For example, the image normalization processing may include normalizing the contrast distribution of the fingerprint image and other image quality improvement processing, such as noise filtering processing.

[0060] In operation 603, the processor 130 extracts fingerprint pattern information, such as ridges, valleys, minutiae points, etc., from the preprocessed fingerprint image. In detail, first, the processor 130 may binarize the fingerprint image by bandpass filtering the preprocessed fingerprint image, and extract fingerprint pattern information related to ridges, valleys, minutiae points, etc. from the binarized fingerprint image.

[0061] In operation 604, the processor 130 performs user authentication based on fingerprint pattern information extracted from the fingerprint image.

[0062] Meanwhile, in the image quality processing of operation 602, the processor 130 according to the present embodiment analyzes the spatial change trend of the contrast in the acquired fingerprint image, and normalizes the contrast distribution of the fingerprint image according to the analyzed change trend of the contrast. Hereinafter, the method for processing the fingerprint image according to the present embodiment will be described in detail.

[0063] Figure 7is a diagram for describing a process of performing normalization on a fingerprint image according to an embodiment.

[0064] According to the present embodiment, normalization of the fingerprint image may refer to a process of adjusting contrast values ​​of pixels of the fingerprint image to have an overall uniform distribution in the fingerprint image.

[0065] refer to Figure 7 , the original fingerprint image 701 is an image of the user's fingerprint obtained from the fingerprint sensor 10 without additional image processing, such as pre-processing or post-processing. As described above, due to the characteristics of the user's finger or the pressure intensity of the contact finger, the fingerprint area of ​​the original fingerprint image 701 may have an uneven contrast distribution.

[0066] Processor 130 ( Figure 2 ) estimates the spatial change trend of the original contrast value from the original fingerprint image 701, and generates a reference contrast map 702 based on the estimated spatial change trend.

[0067] The reference contrast map 702 is information indicating a spatial change tendency estimated based on the characteristics of the probability contrast distribution of the original fingerprint image 701. The pixels of the reference contrast map 702 may have a reference contrast value indicating the estimated spatial change tendency, and each pixel of the reference contrast map 702 may correspond to each pixel of the original fingerprint image 701 based on a one-to-one correspondence. The reference contrast map 702 may represent the distribution of contrast values ​​over a region of the original fingerprint image 701. The reference contrast map 702 may be provided in a three-dimensional space with x, y, and z parameters, wherein the x and y parameters indicate pixel coordinates of the original fingerprint image 701, and the z parameter indicates a contrast value of the original fingerprint image 701.

[0068] The processor 130 generates a normalized fingerprint image 703 having a uniform contrast distribution by removing the influence of the contrast change according to the contrast change trend (or the spatial change trend of the contrast) of the reference contrast map 702 from the contrast distribution of the original fingerprint image 701 .

[0069] According to this method, even if the fingerprint image has different uneven contrast distributions (such as the original fingerprint image 711), a normalized fingerprint image 713 with uniform contrast distribution can be generated by removing the influence of contrast changes according to the contrast change trend (or the spatial change trend of contrast) in the reference contrast map 712 analyzed based on the original fingerprint image 711.

[0070] Figure 8 is a diagram for describing contrast data of a fingerprint image adjusted by normalization of contrast distribution according to an embodiment.

[0071] refer to Figure 8 , the original contrast map 801 is contrast data in which the contrast values ​​of the local area of ​​the original fingerprint image are plotted on a three-dimensional (x, y, z) map. In the original contrast map 801, the x-axis and the y-axis refer to the pixel coordinates in the original fingerprint image, and the z-axis refers to the relative contrast value. According to the original contrast map 801, the z values ​​(i.e., contrast values) of the uneven ridges and the z values ​​(i.e., contrast values) of the valleys caused by the uneven contrast distribution in the original fingerprint image can be identified.

[0072] The reference contrast map 802 is contrast data having a spatial change trend estimated by a feature based on a probability contrast distribution of an original fingerprint image. In the reference contrast map 802, the x-axis and the y-axis represent pixel coordinates corresponding to the pixel coordinates in the original fingerprint image, and the z-axis represents an estimated contrast value indicating the estimated spatial change trend.

[0073] The contrast data of the reference contrast value of the reference contrast map 802 can be obtained by performing kernel density estimation (KDE) on the contrast distribution of the original fingerprint image using a kernel function. As the kernel function, various types of functions can be used, such as a uniform function, a trigonometric function, an Epanechnikov function, a quartic function, a triple function (Triweight), a Gaussian function, a cosine function, etc.

[0074] In the process of calculating the reference contrast value of any one pixel of the reference contrast map 802, the probability distribution characteristics of the contrast value of the pixel may be estimated as expressed in the following Equation 1. That is, Equation 1 may indicate a calculation for obtaining a result value of smoothing performed on a pixel value of the pixel.

[0075] [Equation 1]

[0076]

[0077] Referring to Equation 1, x represents a pixel value (contrast value), K represents a kernel function, and n represents the number of multiple sample data (the number of pixels around a pixel). The number n of multiple sample data can be modified according to various factors, such as the processing performance of the processor 130, smoothness, the type of kernel function, etc.

[0078] The reference contrast value of each pixel of the reference contrast map 802 can be obtained by performing a calculation using Equation 1 on each pixel of the original contrast map 801 of the original fingerprint image. The contrast data of the reference contrast map 802 with the estimated reference contrast value can ultimately indicate the spatial contrast change trend of the original fingerprint image (or the original contrast map 801).

[0079] Normalized contrast map 803 indicates contrast data of a normalized fingerprint image. Normalized contrast map 803 may be generated according to the difference between original contrast map 801 and reference contrast map 802. In detail, contrast normalization of the fingerprint image may be performed by calculating the difference (▽) of pixel contrast values ​​between contrast data of original contrast map 801 and contrast data of reference contrast map 802. Therefore, contrast data of normalized contrast map 803 may include contrast values ​​(z-axis values) having a generally uniform contrast distribution, and thus, a normalized fingerprint image having a uniform contrast distribution may be generated.

[0080] Fig. 9 is a flowchart of a method for processing a fingerprint image in an electronic device according to an embodiment.

[0081] refer to Fig. 9 , the method for processing a fingerprint image in an electronic device includes the operations of processing in the electronic device 1 in a time sequence as described above. Therefore, the description provided above with reference to the accompanying drawings but omitted here may also be applicable to Fig. 9 method.

[0082] In operation 901, the processor 130 obtains an original fingerprint image by sensing a fingerprint of a user. The fingerprint of the user may be sensed using the fingerprint sensor 10, and the fingerprint sensor 10 may be implemented by a sensor that senses the entire area of ​​the user's fingerprint using an on-screen method, but is not limited thereto, and may also be implemented using a fingerprint sensor using other methods other than the on-screen method.

[0083] In operation 902, the processor 130 estimates a spatial change trend of original contrast values ​​in the original fingerprint image based on contrast distribution of original contrast values ​​of pixels of the original fingerprint image.

[0084] In detail, the processor 130 can perform the estimation of the change trend by estimating the characteristics of the probability contrast distribution of all pixels of the original fingerprint image according to the contrast distribution of the original contrast value. Here, the characteristics of the probability contrast distribution can be obtained using KDE through a kernel function. As described above, various types of functions can be used as kernel functions, such as uniform functions, trigonometric functions, Epanechnikov functions, quartic functions, triple functions, Gaussian functions, and cosine functions.

[0085] The characteristics of the probability contrast distribution may be estimated based on the average of the original contrast values ​​of the peripheral pixels of each pixel of the original fingerprint image, and the corresponding reference contrast value may be calculated by using the above equation 1. The peripheral pixels may correspond to pixels surrounding a pixel located at the center of the peripheral pixels.

[0086] In operation 903, the processor 130 generates a reference contrast map indicating a reference contrast value of a pixel determined based on the estimated spatial change trend. In detail, the result value of Equation 1 calculated in operation 902 is a reference contrast value of the pixel, and the reference contrast map includes information on a spatial change trend corresponding to an estimated feature of a probability contrast distribution (i.e., contrast data of all reference contrast values).

[0087] In operation 904, the processor 130 normalizes the contrast distribution of the original fingerprint image by comparing the original contrast value of the original fingerprint image with the reference contrast value of the reference contrast map. Normalization of the contrast distribution refers to the following process: uniformizing the contrast distribution by removing the influence of the contrast change according to the previously estimated spatial change trend from the original fingerprint image, thereby obtaining a uniform contrast distribution of the original fingerprint image. Figure 8 As described in the normalized contrast map 803 , the normalization of the contrast distribution can be performed by calculating the contrast difference between the original contrast value and the reference contrast value of the respective corresponding pixels in the original fingerprint image (original contrast map 801 ) and the reference contrast map 802 .

[0088] In operation 905, the processor 130 generates a normalized fingerprint image having a normalized contrast distribution. That is, the normalized fingerprint image may be an image reconstructed so that each pixel in the original fingerprint image has a contrast value corresponding to the above-mentioned contrast difference (▽).

[0089] Meanwhile, the processor 130 may additionally perform smoothing on the normalized fingerprint image to remove noise.

[0090] When a normalized fingerprint image is generated (or when noise removal processing of the generated normalized fingerprint image is completed), the processor 130 may additionally perform fingerprint image processing to extract fingerprint pattern information such as ridges, valleys, minutiae points, etc. from the normalized fingerprint image for user fingerprint authentication.

[0091] As described above, the fingerprint image processing subsequently performed may be a process of binarizing the fingerprint image by performing bandpass filtering on the normalized fingerprint image, and extracting fingerprint pattern information related to ridges, valleys, minutiae, etc. from the binarized fingerprint image. For example, the binarization of the fingerprint image may be performed using a short-time Fourier transform (STFT) method or other various methods without limitation.

[0092] Fig.10 is a diagram for describing a normalized result of contrast distribution of a fingerprint image according to an embodiment.

[0093] refer to Fig.10, in the contrast data 1005 in the portion 1010 of the original contrast map 1001 of the original fingerprint image, there is a difference 1011 in the contrast value between a ridge and a ridge adjacent thereto. That is, the original contrast map 1001 of the original fingerprint image has an overall contrast distribution in which the contrast value increases toward a certain area of ​​the original contrast map 1001.

[0094] The reference contrast map 1002 shows the spatial contrast change trend estimated from the original contrast map 1001. The reference contrast map 1002 may represent the distribution of contrast values ​​over a region of the original fingerprint image. The reference contrast map 1002 may be provided in a three-dimensional space with x, y, and z parameters, wherein the x and y parameters indicate the pixel coordinates of the original fingerprint image, and the z parameter indicates the contrast value of the original fingerprint image.

[0095] When normalization is performed based on the difference in contrast values ​​between the original contrast map 1001 and the reference contrast map 1002, a normalized profile 1003 may be generated. In contrast data 1007 in a portion 1020 of the normalized profile 1003 corresponding to a portion 1010 of the original contrast map 1001, there is almost no difference in contrast values ​​between a ridge and another ridge adjacent thereto. That is, according to the normalized profile 1003, contrast values ​​of ridges are normalized to have almost equal contrast values, and contrast values ​​of valleys are also normalized to have almost equal contrast values.

[0096] Fig.11 is a graph for comparing fingerprint recognition rates of image processing results according to the related art and the present embodiment for an original fingerprint image with uneven contrast distribution according to the embodiment.

[0097] refer to Fig.11 , describes the reference by assuming that Figure 5 The depicted fingerprint images 501, 502, and 503 correspond to the results of simulations performed on the original fingerprint images. Fig.11 The original fingerprint images all have uneven contrast distribution, where the image becomes brighter or darker towards a certain area.

[0098] Normalized and binarized fingerprint image processing is performed on each of the fingerprint images 501, 502 and 503 according to the contrast stretching technology and the histogram equalization technology which are related technologies, and fingerprint authentication is performed on each of the fingerprint images 501, 502 and 503. As a result, the fingerprint authentication rates are measured to be 90.25% and 90.34%.

[0099] Compared with the fingerprint image processing according to the related art, the contrast distribution analysis according to the present embodiment performs normalized and binarized fingerprint image processing on each of the fingerprint images 501, 502, and 503, and performs fingerprint authentication on each of the fingerprint images 501, 502, and 503. As a result, the fingerprint authentication rate is measured to be 97.48%. That is, by performing normalized fingerprint image processing according to the contrast distribution analysis of the present embodiment, a significantly improved fingerprint authentication rate is achieved compared with other methods according to the related art.

[0100] Although not limited thereto, the example embodiments may be implemented as computer-readable code on a computer-readable recording medium. A computer-readable recording medium is any data storage device that can store data that can be read by a computer system afterwards. Examples of computer-readable recording media include read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage devices. The computer-readable recording medium may also be distributed on a networked computer system so that the computer-readable code is stored and executed in a distributed manner. In addition, the example embodiments may be written as a computer program that is transmitted via a computer-readable transmission medium (e.g., a carrier wave) and received and executed in a general-purpose or special-purpose digital computer that executes the program. In addition, it may be understood that in the example embodiments, one or more units of the above-mentioned devices and apparatuses may include circuits, processors, microprocessors, etc., and may execute a computer program stored in a computer-readable medium.

[0101] The above exemplary embodiments are merely examples and should not be construed as limiting. The present teachings can be easily applied to other types of devices. In addition, the description of the exemplary embodiments is intended to be illustrative rather than to limit the scope of the claims, and a variety of substitutions, modifications, and variations will be apparent to those skilled in the art.

Claims

1. A method for processing a fingerprint image in an electronic device, the method comprising: Obtaining an original fingerprint image by sensing a user's fingerprint, wherein pixels of the original fingerprint image include original contrast values; estimating a spatial change trend of the original contrast value based on a contrast distribution of the original contrast value, wherein the contrast distribution represents a distribution of the original contrast values ​​in the original fingerprint image, and the spatial change trend represents a change of the original contrast value across the contrast distribution; generating a reference contrast map indicating a distribution of reference contrast values ​​corresponding to each pixel of the original fingerprint image determined based on the estimated spatial change trend, wherein contrast data of the reference contrast values ​​are obtained by performing kernel density estimation on a contrast distribution of the original fingerprint image using a kernel function, the reference contrast values ​​represent the estimated spatial change trend, and each pixel of the reference contrast map corresponds to each pixel of the original fingerprint image based on a one-to-one correspondence; and The contrast distribution of the original fingerprint image is normalized by subtracting the reference contrast map from the original fingerprint image, thereby generating a normalized fingerprint image with uniform contrast distribution.

2. The method according to claim 1, wherein: Normalizing the contrast distribution includes normalizing the contrast distribution by calculating a contrast difference between an original contrast value and a reference contrast value of each corresponding pixel in the original fingerprint image and the reference contrast map.

3. The method according to claim 2, wherein: The normalized fingerprint image includes an image reconstructed so that each pixel of the original fingerprint image has a contrast value corresponding to the calculated contrast difference.

4. The method according to claim 1, wherein: Estimating the spatial change trend includes: estimating features of probability contrast distribution of all pixels of the original fingerprint image according to the contrast distribution of the original contrast values.

5. The method according to claim 4, wherein: Estimating the spatial change trend includes estimating a feature of the probability contrast distribution based on a kernel density estimation (KDE) by using a kernel function.

6. The method according to claim 4, wherein: Estimating the spatial change trend comprises: estimating the characteristics of the probability contrast distribution based on the average value of the original contrast values ​​of the peripheral pixels of each pixel of the original fingerprint image to obtain a corresponding reference contrast value, Therein, the reference contrast map includes information about spatial change trends corresponding to features of the estimated probability contrast distribution.

7. The method according to claim 1, further comprising: Smoothing is performed on the generated normalized fingerprint image to remove noise.

8. The method according to claim 1, further comprising: Image processing is performed on the normalized fingerprint image to extract at least one of ridges, valleys, and minutiae points from the normalized fingerprint image. 9 . A non-transitory computer-readable storage medium storing a program executable by a computer to perform the method according to claim 1 .

10. An electronic device for processing a fingerprint image, the electronic device comprising: A fingerprint sensor configured to obtain an original fingerprint image by sensing a user's fingerprint, wherein pixels of the original fingerprint image include original contrast values; and The processor is configured as: estimating a spatial change trend of the original contrast value based on a contrast distribution of the original contrast value, wherein the contrast distribution represents a distribution of the original contrast values ​​in the original fingerprint image, and the spatial change trend represents a variation of the original contrast value across the contrast distribution, generating a reference contrast map indicating a distribution of reference contrast values ​​corresponding to each pixel of the original fingerprint image determined based on the estimated spatial change tendency, wherein contrast data of the reference contrast values ​​are obtained by performing kernel density estimation on a contrast distribution of the original fingerprint image using a kernel function, the reference contrast values ​​represent the estimated spatial change tendency, and each pixel of the reference contrast map corresponds to each pixel of the original fingerprint image based on a one-to-one correspondence, and The contrast distribution of the original fingerprint image is normalized by subtracting the reference contrast map from the original fingerprint image, thereby generating a normalized fingerprint image with uniform contrast distribution.

11. The electronic device according to claim 10, wherein: The processor is further configured to normalize the contrast distribution by calculating a contrast difference between an original contrast value and a reference contrast value of each corresponding pixel in the original fingerprint image and the reference contrast map.

12. The electronic device according to claim 11, wherein: The normalized fingerprint image includes an image reconstructed so that each pixel of the original fingerprint image has a contrast value corresponding to the calculated contrast difference.

13. The electronic device according to claim 10, wherein: The processor is further configured to estimate the spatial change tendency by estimating a feature of a probability contrast distribution of all pixels of the original fingerprint image according to the contrast distribution of the original contrast values.

14. The electronic device according to claim 13, wherein: The features of the probability contrast distribution are obtained based on kernel density estimation (KDE) using a kernel function.

15. The electronic device according to claim 13, wherein: estimating the characteristics of the probability contrast distribution based on the average value of the original contrast values ​​of the peripheral pixels of each pixel of the original fingerprint image to obtain a corresponding reference contrast value, Therein, the reference contrast map includes information about spatial change trends corresponding to features of the estimated probability contrast distribution.

16. The electronic device according to claim 10, wherein: The processor is further configured to further perform smoothing on the generated normalized fingerprint image to remove noise.

17. The electronic device according to claim 10, wherein: The processor is also configured to further perform image processing to extract at least one of ridges, valleys, and minutiae points from the normalized fingerprint image.

18. The electronic device according to claim 10, wherein: The fingerprint sensor includes a sensor configured to sense all areas of a user's fingerprint by using an on-screen method.

Images