Apparatus and method of ridge digital enhancement in fingerprint images

Abstract

A digital enhancement device for fingerprint ridges according to one embodiment of the present invention may include a fingerprint image acquisition unit for acquiring a fingerprint image; a pixel value extraction unit for distinguishing between a ridge-containing area and a ridge-non-containing area among the fingerprint image and extracting pixel values ​​based on a color model for each area; an outlier detection unit for detecting outliers in pixel values ​​based on a color model for each area; a correction operation unit for calculating the average and standard deviation of pixel values ​​based on a color model for each area after removing the outliers; a parameter operation unit for setting a parameter to serve as a distinguishing criterion for each area and calculating a reference value of the parameter; and a matrix operation unit for generating and performing operations on a matrix including pixel values ​​based on a color model of the fingerprint image and the reference value of the parameter.

Description

Technology Field

[0001] Embodiments of the present invention relate to a digital enhancement device and method for fingerprint ridges. Background Technology

[0002] A fingerprint refers to the pattern of skin on the inside of the fingertips or the traces left behind. In criminal cases, fingerprint analysis plays a crucial role in solving crimes by identifying suspects and reconstructing the crime scene.

[0003] Fingerprints can be largely composed of ridges, which are raised lines representing the openings of sweat glands in the skin at the fingertips, and valleys, which are the indented areas between the ridges.

[0004] The ridges of a fingerprint remaining on an object (paper, plastic, metal, etc.) appear darker compared to the valleys. The ridges are depicted as distinct or faint, allowing for a distinction in the degree of clarity. If the ridges of a fingerprint remaining on an object are depicted faintly and indistinctly, it is difficult to discern the shape of the ridges. Additionally, there is a subtle difference in color between the parts of the object where the ridges are visible and where they are not.

[0005] Therefore, a method to enhance the shape of ridges can be studied by distinguishing between areas containing ridges and areas not containing ridges in a fingerprint image using color differences. The problem to be solved

[0006] Embodiments of the present invention aim to provide a device and method for digitally enhancing fingerprint ridges. Specifically, the invention aims to perform digital enhancement of fingerprint ridges by distinguishing between ridge-containing regions and ridge-non-containing regions in a fingerprint image, extracting pixel values ​​based on a color model, and setting parameters necessary for region distinction according to the distribution.

[0007] Embodiments of the present invention can contribute to the proper resolution of criminal cases by more clearly expressing the shape of ridges in fingerprint images.

[0008] Furthermore, embodiments of the present invention aim to provide an apparatus and method that reduce processing time by performing matrix-unit operations rather than pixel-unit operations during fingerprint ridge enhancement operations. means of solving the problem

[0009] A digital enhancement device for fingerprint ridges according to one embodiment of the present invention may include a fingerprint image acquisition unit for acquiring a fingerprint image; a pixel value extraction unit for distinguishing between a ridge-containing area and a ridge-non-containing area among the fingerprint image and extracting pixel values ​​based on a color model for each area; an outlier detection unit for detecting outliers in pixel values ​​based on a color model for each area; a correction operation unit for calculating the average and standard deviation of pixel values ​​based on a color model for each area after removing the outliers; a parameter operation unit for setting a parameter to serve as a distinguishing criterion for each area and calculating a reference value of the parameter; and a matrix operation unit for generating and performing operations on a matrix including pixel values ​​based on a color model of the fingerprint image and the reference value of the parameter.

[0010] In one embodiment of the present invention, the color model may include an RGB model and an HSV model.

[0011] In one embodiment of the present invention, the outlier detection unit calculates the Z-Score of pixel values ​​based on a color model for each region and can detect Z-Scores within a certain range by determining them as outliers.

[0012] A digital enhancement method for fingerprint ridges according to one embodiment of the present invention may include the steps of: acquiring a fingerprint image; distinguishing between a ridge-containing area and a ridge-non-containing area among the fingerprint image and extracting pixel values ​​based on a color model for each area; detecting outliers in the pixel values ​​based on the color model for each area; calculating the mean and standard deviation of the pixel values ​​based on the color model for each area after removing the outliers; setting a parameter to serve as a distinguishing criterion for each area and calculating a reference value of the parameter; and generating and performing calculations on a matrix including pixel values ​​based on the color model of the fingerprint image and the reference value of the parameter.

[0013] In one embodiment of the present invention, the step of generating and performing operations on the matrix may include: generating a matrix (fingerprint image matrix, M1) containing pixel values ​​according to the color model of the fingerprint image; generating a matrix (reference value matrix, M2) containing reference values ​​of the parameters; generating an operation matrix (X) by performing operations based on the fingerprint image matrix (M1) and the reference value matrix (M2); converting the components of the operation matrix (X) into integers; calculating a discrimination value by performing operations based on the parameter-related components of the operation matrix (X); and enhancing the ridges of the fingerprint image to a specific color by performing operations based on the discrimination value and the pixel values ​​of a specific color.

[0014] A computer-readable recording medium may be provided on which a program for executing a digital enhancement method of fingerprint ridges according to one embodiment of the present invention is recorded.

[0015] Other aspects, features, and advantages other than those described above will become clear from the following drawings, claims, and description of the invention. Effects of the invention

[0016] According to one embodiment of the present invention, digital enhancement of fingerprint ridges can be performed by distinguishing between ridge-containing areas and ridge-non-containing areas in a fingerprint image, extracting pixel values ​​based on a color model, and setting parameters necessary for area distinction according to the distribution.

[0017] In addition, according to one embodiment of the present invention, the shape of the ridges in a fingerprint image is expressed more clearly, thereby effectively reconstructing the crime scene and contributing to the proper resolution of the crime case.

[0018] In addition, according to one embodiment of the present invention, processing time can be reduced by performing matrix-level operations rather than pixel-level operations during fingerprint ridge enhancement operations. Brief explanation of the drawing

[0019] FIG. 1 is a schematic diagram showing a digital enhancement system for fingerprint ridges according to one embodiment of the present invention. Figure 2 is a block diagram schematically illustrating a digital enhancement device for fingerprint ridges of Figure 1. Figure 3 is a diagram exemplarily showing a portion of the ridge-containing area and the ridge-non-containing area in a fingerprint image. FIGS. 4 and FIGS. 5 are flowcharts schematically illustrating a method for digitally enhancing fingerprint ridges according to an embodiment of the present invention. Figure 6 is a table showing the pixel values ​​of the colors constituting the ridge-containing area of ​​the fingerprint image of Figure 3. Figure 7 is a table showing the pixel values ​​of colors constituting the ridge-excluded area of ​​the fingerprint image of Figure 3. Figure 8 is a table showing the calculated Z-Score of the pixel values ​​in Figure 6. Figure 9 is a table showing the calculated Z-Score of the pixel values ​​in Figure 7. Figure 10 is a table showing the mean and standard deviation calculated after removing outliers from the pixel values ​​of Figure 6. Figure 11 is a table showing the mean and standard deviation after removing outliers from the pixel values ​​of Figure 7. Figure 12 is a diagram showing the fingerprint image of Figure 3 before and after digital enhancement. Specific details for implementing the invention

[0020] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings. When describing with reference to the drawings, identical or corresponding components are given the same reference numerals, and redundant descriptions thereof will be omitted.

[0021] In the following embodiments, terms such as first, second, etc. are used not in a limiting sense, but for the purpose of distinguishing one component from another component.

[0022] In the following examples, singular expressions include plural expressions unless the context clearly indicates otherwise.

[0023] In the following embodiments, terms such as 'include' or 'have' mean that the features or components described in the specification are present, and do not preclude the possibility that one or more other features or components may be added.

[0024] In the following embodiments, when a part such as a film, region, or component is described as being on or above another part, it includes not only cases where it is directly on top of another part, but also cases where another film, region, or component is interposed in between.

[0025] In the drawings, the size of components may be exaggerated or reduced for convenience of explanation. For example, the size and thickness of each component shown in the drawings are depicted arbitrarily for convenience of explanation, so the present invention is not necessarily limited to what is illustrated.

[0026] Where an embodiment can be implemented differently, a specific process sequence may be performed differently from the order described. For example, two processes described consecutively may be performed substantially simultaneously or proceed in the reverse order of the description.

[0027] FIG. 1 is a schematic diagram showing a digital enhancement system for fingerprint ridges according to one embodiment of the present invention.

[0028] Referring to FIG. 1, a digital enhancement system for fingerprint ridges according to one embodiment of the present invention may include a digital enhancement device for fingerprint ridges (100), a server (300), and a network (500) connecting the same.

[0029] A digital enhancement system for fingerprint ridges according to one embodiment of the present invention provides a digital enhancement service for fingerprint ridges. Specifically, the digital enhancement system for fingerprint ridges provided according to one embodiment allows a user to upload data obtained by a digital enhancement method (200) for fingerprint ridges being tested, and to share the uploaded data with other users. For example, a user can upload data regarding a fingerprint image obtained at a specific crime scene. The digital enhancement system for fingerprint ridges according to one embodiment registers the data uploaded by the user to a server (300) and can provide an interface that allows other users to view the data registered to the server (300).

[0030] A digital enhancement device (100) for fingerprint ridges can be connected to a server (300) via a network (500). Here, the digital enhancement device (100) for fingerprint ridges to which the present invention is applied may be various types of information processing devices used by a user, such as a PC (Personal Computer), a laptop computer, a mobile phone, a tablet PC, a smartphone, a PDA (Personal Digital Assistant), etc. Of course, this is merely an example, and should be interpreted as a concept that includes all communication-capable devices currently developed and commercialized or to be developed in the future, in addition to the examples described above. The digital enhancement method (200) for fingerprint ridges provided by an embodiment of the present invention may be adopted without limitation as long as it is capable of carrying a programmed application.

[0031] The network (500) serves to connect the digital enhancement device (100) of the fingerprint ridges and the server (300). For example, the network (500) provides a connection path so that the digital enhancement device (100) of the fingerprint ridges can transmit and receive packet data after connecting to the server (300).

[0032] Although not illustrated in the drawings, a server (300) according to one embodiment of the present invention may include a memory, an input / output unit, a program storage unit, a control unit, etc.

[0033] FIG. 2 is a block diagram schematically illustrating a digital enhancement device (100) of the fingerprint ridges of FIG. 1.

[0034] A digital enhancement device (100) for fingerprint ridges according to one embodiment of the present invention may correspond to at least one processor or may include at least one processor. Accordingly, the digital enhancement device (100) for fingerprint ridges may be operated in a form included in a hardware device such as a microprocessor or a general-purpose computer system.

[0035] The digital enhancement device (100) for fingerprint ridges shown in FIG. 2 illustrates only the components related to the present embodiment to prevent the features of the present embodiment from being obscured. Therefore, it will be understood by those skilled in the art related to the present embodiment that other general components may be included in addition to the components shown in FIG. 2.

[0036] Referring to FIG. 2, a digital enhancement device (100) for fingerprint ridges according to one embodiment of the present invention may include a fingerprint image acquisition unit (110), a pixel value extraction unit (120), an outlier detection unit (130), a correction operation unit (140), a parameter operation unit (150), and a matrix operation unit (160).

[0037] The fingerprint image acquisition unit (110) can acquire a fingerprint image.

[0038] The fingerprint image acquisition unit (110) can acquire an image by directly capturing a fingerprint left on an object. Additionally, the fingerprint image acquisition unit (110) may receive an image through transmission from another imaging device or server (300).

[0039] For example, the fingerprint image acquisition unit (110) may include a camera including a lens and an image sensor. The image sensor may convert an image input by the lens into an electrical signal and may be a semiconductor device such as a CCD (Charge-Coupled Device) or CMOS (Complementary Metal Oxide Semiconductor).

[0040] In this case, the fingerprint image may be an image of the fingerprint itself left on the object. Additionally, the fingerprint image may be a fingerprint image developed by applying reagents, etc., according to a fingerprint development technique.

[0041] FIG. 3 is a diagram exemplarily showing a portion of the ridge-containing area and the ridge-non-containing area in a fingerprint image. The fingerprint image acquired by the fingerprint image acquisition unit (110) may be composed of pixels.

[0042] The pixel value extraction unit (120) can distinguish between ridge-containing areas and ridge-non-containing areas in the fingerprint image and extract pixel values ​​based on a color model for each area.

[0043] A fingerprint image can be divided into ridge-containing areas and ridge-free areas. The colors constituting the ridge-containing areas and ridge-free areas differ, even if only slightly.

[0044] For example, the color model applied by the pixel value extraction unit (120) may include RGB, HSV, Gray, or YCbCr models.

[0045] The RGB model is the most basic color model, representing color as a combination of three components: red, green, and blue. The HSV model represents color using three components: hue, saturation, and value. The Gray model represents color using only intensity information, without using color information. Additionally, the YCbCr model separates the brightness component (Y) and color difference information (Cb, Cr) from the RGB color.

[0046] The color model applied by the pixel value extraction unit (120) can be selected by considering the characteristics of the colors constituting the fingerprint image. For example, the pixel value extraction unit (120) can apply an RGB model and an HSV model.

[0047] The outlier detection unit (130) can detect outliers in pixel values ​​based on the color model for each region.

[0048] An outlier refers to a value that deviates from the usual range of observed data. If the collected data deviates excessively from a specific range, accurate analysis cannot be performed. Therefore, analysis must be conducted after detecting and removing outliers from the collected data. The detection of outliers in the collected data can be carried out using various methods that can be considered from the perspective of a person skilled in the art in the relevant field.

[0049] For example, outliers can be detected for each individual color component value among the pixel values ​​based on the color model for each region.

[0050] In addition, Z-Scores can be utilized as outliers; Z-Scores of pixel values ​​are calculated based on color models for each region, and Z-Scores within a certain range are determined and detected as outliers.

[0051] The correction calculation unit (140) can calculate the average and standard deviation of pixel values ​​based on the color model for each region from which outliers have been removed.

[0052] The mean is a mathematical measure that indicates the central tendency of collected data. The arithmetic mean refers to the simple average calculated by dividing the total sum of the data by the number of data points.

[0053] Standard deviation is a value that shows the dispersion of data, indicating how far it is from the mean (central value). Standard deviation is defined as the positive square root of variance, and variance is the average of the squared deviations (measurements - mean).

[0054] The mean and standard deviation are representative values ​​that indicate the distribution of data, and they are the values ​​that can most effectively represent the characteristics of the group of interest.

[0055] Therefore, by calculating the mean and standard deviation of pixel values ​​based on the color model for each region, the trend of the pixel value distribution can be identified.

[0056] The parameter calculation unit (150) can set a parameter for distinguishing between a ridge-containing area and a ridge-non-containing area in a fingerprint image and calculate a reference value of the parameter.

[0057] The parameter calculation unit (150) can determine the parameter to distinguish between the ridge-included / non-ridge-included area and the reference value of the parameter through the calculation result of the correction calculation unit (140).

[0058] In one embodiment, the parameter may be set among the individual color components of the color model applied to the fingerprint image, and the reference value of the parameter may be calculated as the pixel value of the individual color components of the applied color model.

[0059] For example, if the color model applied to the fingerprint image is an RGB and HSV model, parameters can be set among the individual color components R, G, B, H, S, and V, and reference values ​​can be calculated using the pixel values ​​(R value, G value, B value, H value, S value, and V value) of the set parameters.

[0060] The matrix operation unit (160) can generate and operate a matrix containing pixel values ​​and reference values ​​of parameters based on the color model for each region.

[0061] To enhance the ridges of a fingerprint image, performing matrix-level operations rather than pixel-level operations can reduce processing time.

[0062] In addition, the digital enhancement device (100) for fingerprint ridges may include a communication unit, a storage unit, a display unit, an input unit, etc.

[0063] The communication unit may provide an interface for communication with other systems or devices, and the storage unit may store data such as a basic program, application program, and setting information for the operation of the digital enhancement device (100) of the fingerprint ridges. The display unit may perform functions for outputting information in the form of numbers, characters, images, graphics, etc. The input unit may detect input from the outside (e.g., user) and provide data corresponding to the input to the processor.

[0064] A more detailed description of the digital enhancement device (100) for fingerprint ridges according to an embodiment of the present invention will be provided below with reference to FIGS. 4 to 12.

[0065] Hereinafter, a digital enhancement method (200) of fingerprint ridges according to an embodiment of the present invention will be described with reference to FIGS. 4 to 12.

[0066] FIGS. 4 and 5 are flowcharts illustrating a digital enhancement method for fingerprint ridges according to an embodiment of the present invention. FIGS. 6 to 12 are drawings illustrating measurement results derived according to a digital enhancement method for fingerprint ridges according to an embodiment of the present invention.

[0067] Step 210 is a step of acquiring a fingerprint image. Step 210 can be performed by a fingerprint image acquisition unit (110).

[0068] As shown in Fig. 3, the fingerprint image can be divided into a ridge-containing area and a ridge-free area.

[0069] Step 220 is a step of distinguishing between ridge-containing areas and ridge-non-containing areas in a fingerprint image and extracting pixel values ​​based on a color model for each area. Step 220 can be performed by a pixel value extraction unit (120).

[0070] FIG. 6 is a table showing the pixel values ​​of colors constituting the ridge-included area of ​​the fingerprint image of FIG. 3, and FIG. 7 is a table showing the pixel values ​​of colors constituting the ridge-excluded area of ​​the fingerprint image of FIG. 3.

[0071] Referring to Figures 6 and 7, the R, G, B, H, S, and V values ​​according to the RGB and HSV models of the colors included in each area are shown.

[0072] Step 230 is a step of detecting outliers in pixel values ​​by a color model for each region. Step 230 can be performed by an outlier detection unit (130).

[0073] For example, a Z-Score can be calculated for pixel values ​​based on a color model for each region, and outlier detection can be performed based on a certain range of Z-Score values.

[0074] The Z-score is a value obtained by dividing the distance between a measurement and the mean by the population standard deviation. The Z-score indicates the relative position of the measurement within the overall population distribution. It can be expressed as shown in the following mathematical formula 1.

[0075]

[0076] Here, x represents the measured value, μ represents the mean, and σ represents the standard deviation.

[0077] Figure 8 is a table showing the calculated Z-Score of the pixel values ​​in Figure 6, and Figure 9 is a table showing the calculated Z-Score of the pixel values ​​in Figure 7.

[0078] In Figures 8 and 9, Z-Scores (z) were calculated for each R, G, B, H, S, and V value of the colors included in the ridge-included and ridge-excluded regions, and values ​​where z < -1 or z > 1 were detected and displayed as outliers. Each Z-Score (z) indicates the relative position of each measurement within the entire group.

[0079] Step 240 is a step of calculating the average and standard deviation of pixel values ​​based on the color model for each region from which the above-mentioned outliers have been removed. Step 240 can be performed by the correction operation unit (140).

[0080] Figure 10 is a table showing the mean and standard deviation after removing outliers from the pixel values ​​of Figure 6, and Figure 11 is a table showing the mean and standard deviation after removing outliers from the pixel values ​​of Figure 7.

[0081] Referring to Figures 10 and 11, values ​​where z < -1 or z > 1 were detected as outliers, and the mean and standard deviation of pixel values ​​within the range from which outliers were removed were calculated.

[0082] In summary, Figures 10 and 11 show the mean and standard deviation of the R, G, B, H, S, and V values ​​of the colors in the ridge-included / non-ridge-included regions, respectively, after removing outliers. Thus, the distribution of the R, G, B, H, S, and V values ​​of the colors included in each region can be determined.

[0083] Step 250 is a step of setting a parameter that serves as a criterion for distinguishing each region (a region including a ridge and a region not including a ridge) and calculating a reference value of the parameter. Step 250 can be performed by the parameter calculation unit (150).

[0084] For example, if the color model applied to the fingerprint image is an RGB and HSV model, parameters can be set among the individual color components R, G, B, H, S, and V, and reference values ​​can be calculated using the pixel values ​​(R value, G value, B value, H value, S value, and V value) of the set parameters.

[0085] Referring to Figures 10 and 11, the average difference between the R and H values ​​in the ridge-included and ridge-excluded regions is large, and the standard deviation between the R and H values ​​in the ridge-included region is small, so the R and H components can be used as parameters to distinguish between the ridge-included and ridge-excluded regions.

[0086] For example, the reference value of the parameter can be calculated according to the following mathematical formula 2 based on the Z-Score (z') calculated using the ridge-exclusion area after removing outliers as shown in Fig. 11 as the population.

[0087]

[0088] Here, the reference value of the parameter can be calculated based on the criterion z' = |±0.5|. For example, within the ridge-excluded region, the R and H values ​​in the region corresponding to the distribution within -0.5 < z' < 0.5 (including approximately 38.2% of the population values) may have values ​​greater than or equal to the reference value. Additionally, the ridge-excluded region corresponds to the case where both the R and H values ​​are greater than or equal to the reference value.

[0089] Table 1 below is a table showing parameters set with reference to FIGS. 10 and FIGS. 11 and reference values ​​of the parameters accordingly.

[0090]

[0091] Step 260 is a step of generating and operating a matrix including pixel values ​​based on the color model of the fingerprint image and reference values ​​of the parameters. Step 260 can be performed by the matrix operation unit (160).

[0092] Additionally, step 260 may include the following steps.

[0093] Step 261 is the step of generating a matrix (fingerprint image matrix, M1) containing pixel values ​​based on the color model of the fingerprint image.

[0094] For example, for pixel values ​​(R, G, B, H, S, V) appearing in a fingerprint image, a fingerprint image matrix M1 = (R, G, B, H, S, V) can be generated.

[0095] Step 262 is the step of generating a matrix (reference value matrix, M2) containing reference values ​​of parameters.

[0096] For example, the parameters set to distinguish fingerprint images into ridge-included / non-ridge-included regions are the R and H components of a color model, and the reference values ​​of each parameter can be denoted as the first reference value P1 and the second reference value P2. Here, a reference value matrix M2 = (P1,1,1,P2,1,1) containing the reference values ​​of the parameters can be generated.

[0097] Referring to Table 1, when P1=149.5 and P2=120.5, the reference value matrix (M2) can be expressed as (149.5,1,1,120.5,1,1).

[0098] At this time, steps 261 and 262 may be performed sequentially, or they may be performed in a different order or simultaneously.

[0099] Step 263 is a step of generating an operation matrix (X) by performing operations based on the fingerprint image matrix (M1) and the reference value matrix (M2).

[0100] For example, for the fingerprint image matrix (M1) and reference value matrix (M2), an operation matrix (X) can be generated by performing an operation as shown in the following mathematical formula 3.

[0101]

[0102] The operation matrix derived here can be expressed as X = (R',G',B',H',S',V'). Since M1 = (R,G,B,H,S,V) and M2 = (P1,1,1,P2,1,1), R' = R / P1 and H' = H / P2. Here, the R' and H' values ​​can be changed to 1.XXX values ​​if they are greater than the reference value, and to 0.XXX values ​​if they are less than the reference value.

[0103] Step 264 is the step of converting the components of the operation matrix (X) into integers.

[0104] For example, for components of the operation matrix (X) that include a decimal point, the decimal part may be discarded and expressed as an integer. Among the components of the operation matrix (X), the R' value and H' value associated with the parameter may be changed to 1 or 0.

[0105] Step 265 is a step of calculating a determination value by performing calculations based on the parameter-related components of the operation matrix (X).

[0106] For example, R' and H' components related to the parameters can be extracted separately, and a multiplication operation such as R'x H' can be performed. The R' and H' values ​​can be converted into integers and have a value of 1 or 0. Therefore, the result of the multiplication operation is 1 if the R and H values ​​of the fingerprint image matrix (M1) are greater than or equal to a reference value, and 0 if they are less than or equal to a reference value.

[0107] In this way, the discriminant value based on the result of the operation can be 1 or 0. Here, the area where the discriminant value is 1 represents the ridge area, and the area where the discriminant value is 0 may represent an area other than the ridge.

[0108] Step 266 is a step of augmenting the ridges to a specific color by performing calculations based on the above discrimination value and the pixel value of a specific color.

[0109] For example, an area with a discriminant value of 1 can be represented as (255, 0, 0), which represents red in the RGB model, and an area with a discriminant value of 0 can be represented as (255, 255, 255), which represents white in the RGB model. Therefore, the ridge area can be represented as red, and the area other than the ridge can be represented as white.

[0110] Figure 12 is a diagram showing the fingerprint image of Figure 3 before and after digital enhancement. Here, the ridge area after fingerprint image enhancement is represented in red, and the area other than the ridges is represented in white. When comparing the fingerprint image before and after enhancement, the shape of the ridges after enhancement is expressed more clearly than before enhancement.

[0111] Meanwhile, the device and method according to the embodiment may be implemented in the form of program instructions that can be executed by one or more processors or through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The above hardware device may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0112] As described above, the digital enhancement device (100) and method (200) of fingerprint ridges according to embodiments of the present invention can perform digital enhancement of fingerprint ridges by distinguishing between ridge-containing areas and ridge-non-containing areas in a fingerprint image, extracting pixel values ​​based on a color model, and setting parameters necessary for area distinction according to the distribution.

[0113] In addition, embodiments of the present invention can contribute to the proper resolution of criminal cases by more clearly expressing the shape of ridges in fingerprint images.

[0114] Furthermore, embodiments of the present invention can reduce processing time by performing matrix-level operations rather than pixel-level operations during fingerprint ridge enhancement operations.

[0115] Although the embodiments have been described above with reference to limited examples and drawings, those skilled in the art can make various modifications and variations from the description above. For example, suitable results can be achieved even if the described techniques are performed in a different order than described, and / or the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0116] Accordingly, the embodiments disclosed in this invention are intended to illustrate, not limit, the technical concept of the invention, and the scope of the technical concept of the invention is not limited by these embodiments. The scope of protection of this invention shall be interpreted by the claims below, and all technical concepts within an equivalent scope shall be interpreted as being included within the scope of rights of this invention. Explanation of the symbols

[0117] 100: Digital enhancement device for fingerprint ridges 110: Fingerprint image acquisition unit 120 : Pixel value extraction unit 130 : Outlier detection unit 140 : Correction calculation unit 150 : Parameter operation unit 160 : Matrix operation part

Claims

Claim 1 A fingerprint image acquisition unit for acquiring a fingerprint image; a pixel value extraction unit for distinguishing between ridge-containing and ridge-non-containing regions among the fingerprint image and extracting pixel values ​​based on a color model for each region; an outlier detection unit for detecting outliers in pixel values ​​based on a color model for each region; a correction calculation unit for calculating the mean and standard deviation of pixel values ​​based on a color model for each region after removing the outliers; and a parameter calculation unit for setting parameters to serve as distinction criteria for each region and calculating reference values ​​for the parameters. A digital enhancement device for fingerprint ridges, comprising: a matrix operation unit that generates and performs operations on a matrix including pixel values ​​based on a color model of the fingerprint image and reference values ​​of the parameters; wherein the matrix operation unit generates a matrix (fingerprint image matrix, M1) including pixel values ​​based on a color model of the fingerprint image and generates a matrix (reference value matrix, M2) including reference values ​​of the parameters, generates an operation matrix (X) by performing operations based on the fingerprint image matrix (M1) and the reference value matrix (M2), integerizes the components of the operation matrix (X), calculates a discrimination value by performing operations based on the parameter-related components of the operation matrix (X), and enhances the ridges of the fingerprint image to a specific color by performing operations based on the discrimination value and pixel values ​​of a specific color. Claim 2 A digital enhancement device for fingerprint ridges according to claim 1, wherein the color model includes an RGB model and an HSV model. Claim 3 A digital enhancement device for fingerprint ridges according to claim 1, wherein the outlier detection unit calculates the Z-Score of pixel values ​​based on a color model for each region and detects Z-Scores within a certain range as outliers. Claim 4 The method comprises the steps of: acquiring a fingerprint image; distinguishing between ridge-containing and ridge-non-containing regions among the fingerprint image and extracting pixel values ​​based on a color model for each region; detecting outliers in the pixel values ​​based on the color model for each region; calculating the mean and standard deviation of the pixel values ​​based on the color model for each region after removing the outliers; setting parameters to serve as distinction criteria for each region and calculating the reference values ​​of the parameters; and generating and performing operations on a matrix containing pixel values ​​based on the color model of the fingerprint image and the reference values ​​of the parameters; wherein the step of generating and performing operations on the matrix comprises: generating a matrix (fingerprint image matrix, M1) containing pixel values ​​based on the color model of the fingerprint image; generating a matrix (reference value matrix, M2) containing the reference values ​​of the parameters; generating an operation matrix (X) by performing operations based on the fingerprint image matrix (M1) and the reference value matrix (M2); converting the components of the operation matrix (X) into integers; and calculating a discrimination value by performing operations based on the parameter-related components of the operation matrix (X). A digital enhancement method for fingerprint ridges, comprising the step of enhancing the ridges of the fingerprint image to a specific color by performing calculations based on the above-mentioned discrimination value and the pixel value of a specific color. Claim 5 delete Claim 6 A computer program stored on a computer-readable storage medium to execute the method of paragraph 4 using a computer.

Images