WO2005086091A1 - 指紋掌紋画像処理システムおよび指紋掌紋画像処理方法 - Google Patents
指紋掌紋画像処理システムおよび指紋掌紋画像処理方法 Download PDFInfo
- Publication number
- WO2005086091A1 WO2005086091A1 PCT/JP2005/001236 JP2005001236W WO2005086091A1 WO 2005086091 A1 WO2005086091 A1 WO 2005086091A1 JP 2005001236 W JP2005001236 W JP 2005001236W WO 2005086091 A1 WO2005086091 A1 WO 2005086091A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- finger
- image processing
- fingerprint
- frequency
- frequency component
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
- G06V40/1359—Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
- G06V10/993—Evaluation of the quality of the acquired pattern
Definitions
- Fingerprint palm print image processing system and fingerprint palm print image processing method are fingerprint palm print image processing system and fingerprint palm print image processing method
- the present invention relates to a fingerprint / palmprint image processing system and a fingerprint / palmprint image processing method, and more particularly
- the present invention relates to a fingerprint / palmprint image processing system and a fingerprint / palmprint image processing method with an improved image processing function of fingerprint / palmprint.
- a finger / palm-print image processing technology which recognizes a finger / palm-print by applying predetermined image processing to an image including a fingerprint / palm-print (hereinafter referred to as "finger-palm-print").
- the image processing method of this technology removes noise from the input image to restore the original image.
- the process of dividing the input image into a plurality of blocks, the process of Fourier transforming the image of each block obtained by the block dividing means, and the power of the original image at each frequency and the power of the noise are estimated.
- the gain is set to have a smaller value as the relative magnitude of the noise power at the frequency is larger using the estimated value of the power, and the gain is multiplied by the amplitude of the corresponding frequency of the Fourier component information.
- the process of suppressing the power of the spectrum, the process of inverse Fourier transform of the Fourier component whose amplitude has been changed, and the image of each block transformed by the inverse Fourier transform means are combined to construct the whole image after restoration. And the process of
- this technique reduces noise components using a function that neglects minute components in image data after Fourier transform, and then inverse Fourier transform to restore the original image. It is stated that the noise can be reduced to emphasize the ridges. In addition, check the direction of each pixel or area and check the size of the small block, which is the unit to divide the image. Also, it is stated that there is no adverse effect that the measurement of directionality does not go well in the area of narrow stripes and stripes.
- JP-A-2003-44856 JP-A-8-1 10949, and JP-A-8-129644 disclose such methods.
- the input finger / palm-print image is blurred by Gauss conversion and then binarized to form a black pixel as a finger-palm-printed area. It is determined that a certain area or an area that has become a white pixel is a background area.
- the image quality determination method of the finger / palm-print image is obtained by binarizing the input image and the ratio of black pixels becoming 0.4. If it is the interval, the input image is judged to have good image quality.
- an input image is binarized and thinned, and end points and branch points are extracted, and the density of the end points and branch points falls within a predetermined range. If there is, it determines that the image quality is good.
- the input image is subjected to frequency analysis for each small area, and a plurality of ridge candidates are extracted.
- a ridge image is extracted by selecting one representing the correct ridge from among the ridge candidates from the continuity with the ridge candidate in the peripheral region for each region.
- the above-described technique for determining the area of the finger / palmprint image may reduce the accuracy of the area determination if there is some shade of light such as dirt or noise in the background.
- the above-described technique for extracting ridges of the finger / palmprint may not be able to extract the correct ridge and to extract the fine structure of the finger / palm ridge if wrinkles or flaws exist in the finger / palmprint. .
- Patent Document 1 Japanese Patent Application Laid-Open No. 2002-99912
- Patent Document 2 Japanese Patent Application Laid-Open No. 2003-44856
- Patent Document 3 JP-A-8-110949
- Patent Document 4 JP-A-8-129644
- Patent Document 5 JP-A-8-110945
- Patent Document 6 Japanese Patent Application Laid-Open No. 9-167230
- Patent Document 7 Japanese Patent Application Laid-Open No. 2002-288641
- Patent Document 8 Japanese Patent Application Laid-Open No. 2002-288672
- Non-patent literature 1 Otsu Nobuyuki, "Automatic thresholding based on discrimination and least squares criteria, value selection method", Transactions of the Institute of Electronics, Information and Communication Engineers, Vol. J63_D, No. 4, pp. 349-356
- An object of the present invention is to provide an area (hereinafter referred to as "finger / palm print area”) with a finger / palm print correctly even if there is a shade other than fingerprint / palm print (hereinafter referred to as “finger / palm print”) in the background.
- Finger / palm print area an area with a finger / palm print correctly even if there is a shade other than fingerprint / palm print (hereinafter referred to as "finger / palm print”) in the background.
- Abstract A fingerprint / palmprint image processing system and a fingerprint / palmprint image processing method that can be determined.
- Another object of the present invention is to provide a finger / palmprint image processing system and a fingerprint / palmprint image processing method capable of correctly recognizing even an unclear portion in the finger / palmprint region. .
- Still another object of the present invention is to perform finger / palm print image processing that can accurately extract ridges even if there are wrinkles or flaws in the finger / palm print area.
- System and method for providing fingerprint / palmprint image processing is to perform finger / palm print image processing that can accurately extract ridges even if there are wrinkles or flaws in the finger / palm print area.
- a fingerprint / palmprint image processing system of the present invention includes a frequency component analysis unit (11, 11a) and a frequency component determination unit (12, 12a).
- the frequency component analysis unit (11, 11a) performs frequency analysis on each of a plurality of small areas in the finger / palmprint image divided into a plurality of small areas, and a plurality of frequencies representative of each of the plurality of small areas. Ask for a component.
- the frequency component determination unit (12, 12a) determines the clarity of the small area corresponding to the frequency component based on the frequency component.
- the finger / palm print image should have at least a fingerprint and a palm print Also show one.
- the finger-palm-print image is divided into small regions, and a frequency component representing the small region is determined, and it is determined whether the frequency component is a frequency found in a clear ridge. Even if there are some shades or noise other than finger and palm print like this, the finger and palm print area can be judged correctly. If there is an unclear portion in the finger / palm print area due to the influence of noise or if the ridges have a fine structure, the finger / palm print area can be correctly determined.
- the frequency component analysis unit (11, 11a) uses Fourier transform as frequency analysis.
- the frequency component determination unit (12, 12a) determines the clarity of the small area corresponding to the frequency component based on the frequency component and the result of Fourier transform of the clear two-dimensional sine wave.
- the frequency component analysis unit (11, 11a) determines one point in the frequency space as the frequency component based on the result of the frequency analysis, and corresponds to the frequency component. A small area is approximated by a representative point two-dimensional sine wave as a two-dimensional sine wave corresponding to one point in frequency space.
- the frequency component determination unit (12, 12a) determines whether the amplitude of the representative point two-dimensional sine wave or the amplitude of the representative point two-dimensional sine wave is The clarity of the small area corresponding to the frequency component is determined using any one of the proportions of the sum of the amplitudes of the two-dimensional sine waves in a predetermined frequency band.
- the frequency component determination unit (12, 12a) determines whether or not the amplitude of the representative point secondary sine wave of the small area is greater than or equal to a predetermined value. Any of the cases where the value obtained by normalizing the magnitude of the amplitude of the table point secondary sine wave with the magnitude of the amplitude of the largest representative point second sine wave among a plurality of small areas is a predetermined value or more The small area that satisfies the condition is determined as the clear finger / palmprint area.
- the frequency component analysis unit (11, 11a) performs the first analysis result of frequency analysis of the central part of the small area and the frequency analysis of the small area including the peripheral area. Find the second analysis result.
- the frequency component determination unit (12, 12a) determines that the small area is an area having a fine structure, and the first analysis result and the second analysis result If there is no difference between them, the small area is determined as a monotonous flow area.
- the fingerprint / palmprint image processing system described above further includes an image quality determination unit (13) that determines the quality of the finger / palmprint image based on the determination results of all the clarity of the plurality of small areas.
- the finger / palmprint image is input from the finger / palmprint image input device.
- the image quality judgment unit (13) judges the image quality of a predetermined number of finger / palm-print images and judges the quality of the finger / palm-print image input device.
- the method of extracting ridges in the finger / palmprint image of the small area is changed based on the determination result of the smallness of the small area for each of the plurality of small areas.
- a ridge image extraction unit (15) for extracting ridges for extracting ridges.
- the frequency component analysis unit (11, 11a) sequentially inputs finger / palmprint images for each small area, and performs frequency analysis for each small area.
- the frequency component analysis unit (11, 1 la) inputs the entire fingerprint / palmprint image. Divide the frequency into small areas and analyze the frequency.
- the fingerprint / palmprint image processing method of the present invention comprises: (a) performing frequency analysis on each of a plurality of small areas in a finger / palmprint image divided into a plurality of small areas; Determining a plurality of frequency components representing each of the small regions, and (b) determining the clarity of the small regions corresponding to the frequency components based on the frequency components.
- the finger / palmprint image indicates at least one of a fingerprint and a palmprint.
- the step (a) includes the step of using a Fourier transform as (al) frequency analysis.
- the step (b) comprises the step of determining the clarity of the small area corresponding to the frequency component based on the (bl) frequency component and the result of Fourier transformation of the clear two-dimensional sine wave.
- step determines a point in the frequency space as the frequency component based on (a2) the result of the frequency analysis, and (a3) the frequency component Approximating the corresponding small area with a representative point two-dimensional sine wave as a two-dimensional sine wave corresponding to one point in the frequency space.
- the step of (b2) the amplitude of the representative point two-dimensional sine wave or the amplitude of the representative point two-dimensional sine wave is a predetermined frequency band
- the (b2) step may include (b21) representative points of the small area, where the amplitude of the secondary sine wave of the small area is equal to or greater than a predetermined value. Any of the forces when the value obtained by normalizing the magnitude of the amplitude of the next sine wave with the magnitude of the amplitude of the largest representative point secondary sine wave among a plurality of small areas is equal to or greater than a predetermined value Determining that the subregion to be satisfied is a clear finger and palm print region.
- the (a) step includes: (a4) a first analysis result of frequency analysis of the central portion of the small area; and a second analysis of the frequency analysis of the small area including the peripheral portion Determining the result.
- the step (b3) when there is a difference between the first analysis result and the second analysis result, the small area is determined as an area having a fine structure, and the first analysis result and the second analysis result are obtained. Determining the subregion as a monotonous flow region if there is no difference
- the above-described fingerprint / palmprint image processing method further includes the step of (c) determining the quality of the finger / palmprint image based on the determination results of all the clarity of the plurality of small areas.
- the step (a) includes the step of (a5) acquiring a finger / palmprint image from the finger / palmprint image input device. (B) the step comprising (b4) determining the image quality of a predetermined number of finger / palmprint images and determining the quality of the finger / palm-print image input device
- the method of extracting ridges in the finger / palm print image of the small area is changed based on the determination result of the small area clarity for each of the plurality of small areas.
- the method further includes the step of extracting ridges.
- the (a) step comprises (a6) sequentially inputting a finger / palmprint image for each small area. Frequency analysis is performed for each small area.
- the step (a) includes the steps of (a7) inputting the entire finger / palmprint image, and (a8) dividing the finger / palmprint image into small regions. Frequency analysis is performed for each small area.
- a program of the present invention is divided into (a) a plurality of small areas. Performing frequency analysis on each of a plurality of small areas in the finger / palm print image to obtain a plurality of frequency components representative of each of the plurality of small areas; and (b) based on the frequency components, Determining the intelligibility of the corresponding small area.
- the finger / palmprint image indicates at least one of a fingerprint and a palmprint.
- the step (a) comprises the step of using a Fourier transform as (al) frequency analysis.
- the step (b) comprises the step of determining the clarity of the small area corresponding to the frequency component based on the (bl) frequency component and the result of Fourier transformation of the clear two-dimensional sine wave.
- step determines (a2) one point of the frequency space as the frequency component based on the result of the frequency analysis, and (a3) a small region corresponding to the frequency component. And approximating with a representative point two-dimensional sine wave as a two-dimensional sine wave corresponding to one point in the frequency space.
- the step (b) includes the steps of (b2) the amplitude of the representative point two-dimensional sine wave or the amplitude of the representative point two-dimensional sine wave at a predetermined frequency band. It comprises the step of determining using one of the ratio to the total of the amplitude of the dimensional sine wave.
- the step (b2) includes the step (b21) of the representative point secondary sine wave of the small area if the magnitude of the amplitude of the representative point secondary sine wave of the small area is greater than or equal to a predetermined value.
- the small area satisfying the force in any of the cases where the value obtained by normalizing the amplitude magnitude with the amplitude magnitude of the largest representative point secondary sine wave among the plurality of small areas is equal to or greater than a predetermined value It includes the step of determining it as a palmprint area.
- step (a) includes (a4) a first analysis result of frequency analysis of the central part of the small area and a second analysis result of frequency analysis of the small area including the peripheral part. Provide the required steps.
- step (b3) when there is a difference between the first analysis result and the second analysis result, the small area is determined as an area having a fine structure, and the difference between the first analysis result and the second analysis result There is a step of determining the small area as the area of monotonous flow if no.
- the method further includes the step of (c) determining the quality of the finger / palm-print image based on the determination results of all of the plurality of small areas.
- the step includes (a5) acquiring a finger / palmprint image from the finger / palmprint image input device.
- the step includes (b4) determining the quality of a predetermined number of finger / palm-print images and determining the quality of the finger / palm-print image input device.
- the method of extracting ridges in the finger / palm print image of the small area is changed based on the determination result of the small area clarity.
- the method further comprises the step of extracting.
- step comprises (a6) sequentially inputting a finger / palm-print image for each small area. Frequency analysis is performed for each small area.
- the (a) step comprises (a7) a step of inputting the entire finger / palmprint image, and (a8) dividing the finger / palmprint image into small areas. Frequency analysis is performed for each small area.
- the finger / palmprint area can be correctly determined even in the case where some shade other than the finger / palm print such as dirt exists in the background. Even if there is an unclear part in the finger / palm print area due to the influence of noise, the finger / palm print area can be correctly determined. Even if the wrinkles, flaws, or ridges have a minute structure, the ridges can be accurately extracted.
- FIG. 1 is a block diagram showing a configuration of a first embodiment of a finger / palm print image processing system of the present invention.
- FIG. 2 is a flow chart showing the operation of the first embodiment of the finger / palm print image processing system of the present invention.
- FIG. 3 is a graph showing an image showing a two-dimensional sine wave in a small area and a two-dimensional sine wave on a frequency space obtained by performing two-dimensional Fourier transform of the two-dimensional sine wave.
- FIG. 4 is a diagram showing ridges of a finger / palm print and a two-dimensional sine wave in a small area of a finger / palm print image.
- FIG. 5 is a view showing a region where frequency analysis is performed in a finger / palm print image.
- FIG. 6 is a view showing an example of a finger / palm-print image.
- FIG. 7 shows the configuration of a second embodiment of the finger / palm print image processing system of the present invention. It is a block diagram.
- FIG. 8 is a flow chart showing the operation (the second embodiment of the finger / palm-print image processing method) of the second embodiment of the finger / palm-print image processing system of the present invention.
- FIG. 9 is a view showing an example of a finger / palm print image in a small area.
- FIG. 10 is a view showing an example of a finger / palm print image in a small area.
- FIG. 11 is a view showing an example of a finger / palm print image in a small area.
- FIG. 12 is a view showing an example of a finger / palm print image in a small area.
- FIG. 13 is a view showing an example of a finger / palm print image in a small area.
- FIG. 14 is a view showing an example of a finger / palm print image in a small area.
- a first embodiment of a finger / palm-print image processing system and a fingerprint / palm-print image processing method of the present invention will be described.
- FIG. 1 is a block diagram showing the configuration of a first embodiment of a finger / palm print image processing system according to the present invention.
- the finger / palm-print image processing system 1 of the present invention comprises a finger / palm-print image input device 3, a finger / palm-print image processing device 4 and an output device 5.
- the finger / palm-print image input device 3 acquires finger / palm-print image data representing an image of the finger / palm-print, and outputs the finger / palm-print image data to the finger / palm-print image processing device 4.
- the finger / palm-print image input device 3 is exemplified by a finger / palm-print sensor or a scanner.
- the finger / palmprint image input device 3 and the finger / palmprint image processing device 4 may be connected via a network, or may be connected by a normal connection cable.
- the finger / palm-print image processing device 4 acquires finger / palm-print image data. Then, an image processing result obtained by performing predetermined image processing on the acquired finger / palm-print image data and a determination result obtained by performing predetermined determination using the image processing result are output to the output device 5.
- the finger / palm-print image processing device 4 is exemplified as a personal computer, a work station, or a portable information terminal. However, as the finger / palm-print image data, one already input and stored in the storage unit (not shown) of the finger / palm-print image processing device 4 can be used.
- An example of another information processing apparatus is an authentication apparatus that authenticates a person with a finger and palm print.
- the output device 5 outputs the image processing result and the determination result of the finger / palmprint image processing device 4.
- the output device 5 is exemplified by a display or a printer. However, the output device 5 and the finger / palmprint image processing device 4 may be connected via a network, or a normal connection cable Connected by Re, even Re.
- the finger / palm-print image processing device 4 includes a frequency component analysis unit 11 as a program, a frequency component determination unit 12 and an image quality determination unit 13.
- the frequency component analysis unit 11 takes in finger / palm-print image data from the finger / palm-print image input device 3.
- the finger / palm-print image of the finger / palm-print image data is divided into a plurality of small areas.
- the frequency components of the finger / palm print image are analyzed for each of the plurality of small regions.
- the analysis result for each small area is output to the frequency component determination unit 12.
- the analysis results include the frequency components (vertical frequency, horizontal frequency) of the image of the small area and its amplitude.
- the area with the finger / palmprint is divided into an arbitrary unit to be determined whether it is clear or not.
- orthogonal transformation such as two-dimensional Fourier transformation, discrete cosine transformation, Walsh transformation, wavelet transformation, or autocorrelation can be used for each of a plurality of small regions.
- the frequency component determination unit 12 determines whether or not each small region is a clear finger / palm print region.
- the determination result for each small area is output to the image quality determination unit 13.
- the determination method determines, for example, whether or not a frequency component representing each small area satisfies a predetermined condition that is seen when the ridges of the finger / palm print clearly appear.
- the image quality determination unit 13 integrates the determination results for each small area obtained by the frequency component determination unit 12 and determines whether the entire finger / palm-print image of the input finger / palm-print image data is clear. The determination result is output to the output device 5.
- FIG. 2 is a flow chart showing an operation (first embodiment of finger / palm print image processing method) of the first embodiment of finger / palm print image processing system of the present invention.
- the finger / palm-print image input device 3 acquires finger / palm-print image data indicating a finger / palm-print image.
- the finger / palm-print image processing device 4 receives finger / palm-print image data from the finger / palm-print image input device 3.
- the frequency component analysis unit 11 divides the finger / palm-print image of the finger / palm-print image data into small areas.
- the method of dividing into small regions is divided into units for determining whether a region with finger and palm print is clear or not. For example, it is divided into square grids of a predetermined size.
- the frequency component analysis unit 11 performs frequency analysis on each of the divided small areas, and detects the frequency components (vertical frequency, horizontal frequency) and the amplitude of the image of the small area. Then, a frequency component representative of the small area is determined. For example, frequency analysis is performed by two-dimensional Fourier transform for each of a plurality of small regions.
- FIG. 3 shows an image showing a two-dimensional sine wave (left figure) and a graph showing a two-dimensional sine wave in frequency space obtained by performing two-dimensional Fourier transformation of the two-dimensional sine wave (right figure) It is.
- the vertical axis is the vertical frequency
- the horizontal axis is the horizontal frequency.
- a pair of points represents one two-dimensional sine wave.
- FIG. 4 is a view showing ridges 23 (left view) of the finger / palm print in the small area 21 of the finger / palm print image and a two-dimensional sine wave (right view). As shown in the figure, if the small area 21 is small enough that the ridges 23 of the finger / palm print can be regarded as parallel lines, the ridges 23 of the finger / palm print in the small area 21 can be approximated by a two-dimensional sine wave 25 .
- Japanese Patent Application Laid-Open Nos. 9-167230, 2002-288641 and 2002-288672 can be used. Evaluate the continuity between the frequency component of each small area described in the publication and the frequency component of the surrounding area, and select a method to select the frequency component that represents each area so that the ridges of the finger print become continuous. Alternatively, it may be selected from the connectivity with the surrounding area.
- FIG. 5 is a diagram showing a region where frequency analysis is performed on a finger / palm print image. Finger palm print image 2 When frequency analysis is performed on the small regions 21 with respect to each of the small regions 21 of 0, the frequency analysis may be performed on a slightly wider region 27 including the small regions 21. In this case, the stability of the judgment result is improved.
- the frequency analysis range (small region 21 or region 27) should have at least two ridges. . If the frequency analysis range is too large, it is strongly affected by the curvature of the ridges, so it is desirable to keep the size smaller than about 4 ridges. In order to improve the stability of frequency analysis, image processing such as blurring around the periphery may be performed before frequency analysis.
- frequency component determination unit 12 has a case where the frequency component representative of each small region determined for each small region by frequency component analysis unit 11 has a ridge of a finger print clearly present. It is determined for each small area whether or not the predetermined condition found in
- the frequency component determination unit 12 determines that the small area is an area where there is a finger print clearly.
- FIG. 6 is a view showing an example of a finger / palm-print image.
- the input finger / palm print image 20 has a background region 31 without finger / palm print, a ridge of finger / palm print and a region 33 with a clear ridge of finger / palm print, and a ridge of finger / palm print but a scratch or It can be classified into the area 35 where the ridges of the finger / palm print are unclear due to dirt.
- ridges of the finger and palm print can be well approximated by a two-dimensional sine wave. Therefore, in the area 33 where the ridges of the finger and palm print are clear, the amplitude of the two-dimensional sine wave approximating the area is large. However, in the background region 31 with no ridges of the finger-palm print, since there is nothing represented by a two-dimensional sine wave, the amplitude of the two-dimensional sine wave should be zero or very small. In the area 35 where scratches and dirt are included and the ridges of the finger and palm print are unclear, a two-dimensional sine wave can be generated due to the scratches and dirt. The amplitude of the two-dimensional sine wave that approximates the region should be small. That is, if the amplitude of the two-dimensional sine wave is large, it can be determined that there is a clear finger and palm print.
- the ridges of the finger-palm print resemble a two-dimensional sine wave as a clear waveform.
- the ridges of the finger print are not very similar to the two-dimensional sine wave which is a clear waveform. Therefore, judging from the magnitude of the amplitude of the similar two-dimensional sine wave or the amplitude of the frequency component corresponding to the two-dimensional sine wave as described above means that the finger-palm print in the input image. It can be considered as a method of judging by the degree of similarity between a ridge and a two-dimensional sine wave.
- the magnitude of the amplitude of the two-dimensional sine wave is directly affected by the density of the input image. Therefore, when variations in density are considered in the input image, the above determination should be made after normalizing the amplitude of the two-dimensional sine wave with the largest one of the two-dimensional sine waves representing each region. You can also.
- the ratio of the ratio of the size of the two-dimensional sine wave representing the area to the sum of the amplitude sizes at all frequencies, and the area to the sum of the amplitude sizes in the frequency band that can be taken as ridges of the finger print It can also be determined whether or not the ratio of the size of the two-dimensional sine wave representing A exceeds a predetermined ratio.
- step S 04 when the predetermined condition is satisfied (step S 04: Yes), the frequency component determination unit 12 determines that the small region is a clear finger / palm print region.
- step S04 the frequency component determination unit 12 determines that the small region is not a clear finger / palmprint region.
- Step S07 The frequency component determination unit 12 checks whether or not all the small regions have been determined. If there is an uninspected small area, the process returns to step S03 to inspect the next area. Based on the determination, the frequency component determination unit 12 outputs to the image quality determination unit 13 the determination result as to whether or not each small area is a clear area of a finger / palm print. It is also possible to output the determination result to the output device 5.
- the background area is determined using the method disclosed in Japanese Patent Laid-Open No. 2003-44856, etc., and the area where the ridges of the finger / palm print are clearly present and the other areas are determined using the frequency components for the remaining part. can do.
- the background region 31, the region 33 where the ridges are clear, and the region 35 where the ridges are unclear can be classified into three.
- the ratio of the clear area to the remaining part can be determined, and the influence of the difference in size of the finger / palm print area in the input finger / palm print image can be eliminated.
- the image quality determination unit 13 integrates the determination results for each small area of the frequency component determination unit 12 and determines whether or not a predetermined condition is satisfied.
- the predetermined condition is exemplified in the case where the ratio of the small area determined as the clear finger / palmprint image among the plurality of small areas is a predetermined ratio or more. In that case, the image quality determination unit 13 determines that the input finger / palm-print image is good.
- step S 08 Yes
- the image quality determination unit 13 determines that the entire input fingerprint image is good. The determination result is output to the output device 5.
- step S08 the image quality determination unit 13 determines that the entire finger / palm-print image input is not good. The determination result is output to the output device 5.
- step S 07, step S 09 and step S 10 are displayed and output in the output device 5.
- it is configured to determine whether or not the frequency component representing the area represents a distinct ridge of finger / palm-print. Therefore, it is possible to determine whether or not each small area has a finger print clearly. If the input image is determined by integrating the determination results of each small area, the entire input image can be determined.
- the predetermined number of input finger / palm print images are judged to be good or bad is determined only by the pass / fail judgment of each input finger / palm-print image, and the image judged to be a good image is not less than a predetermined ratio. If so, it can be judged that the finger / palmprint image input device 3 such as a finger / palmprint scanner is good. That is, it can also be used for the pass / fail judgment of the finger / palmprint image input device 3.
- a second embodiment of a finger / palm-print image processing system and a fingerprint / palm-print image processing method of the present invention will be described.
- FIG. 7 is a block diagram showing the configuration of a second embodiment of a finger / palm print image processing system according to the present invention.
- a finger / palm-print image processing system la according to the present invention includes a finger / palm-print image input device 3, a finger / palm-print image processing device 4a, and an output device 5a.
- the finger / palm-print image input device 3 is the same as that of the first embodiment, so the description thereof is omitted.
- the finger / palm-print image processing device 4 a acquires finger / palm-print image data. Then, image processing of the acquired finger / palm-print image data is divided into a plurality of small areas. Image processing is performed on each of the divided small areas to determine the state of each small area. Based on the determination results, determine the ridge restoration method for each small area, extract the ridges, and restore. Extraction ⁇ Output the restoration result to the output device 5a.
- the finger / palm-print image processing device 4a is exemplified as a personal computer, a work station, or a portable information terminal.
- the finger / palm-print image data it is also possible to use one already input and stored in the storage unit (not shown) of the finger / palm-print image processing device 4a. Storing the storage unit (not shown) of the finger / palmprint image processing device 4 as an output destination of the restoration result, or to another information processing device (not shown) via a network (not shown) It is also possible to output.
- Another information processing apparatus is exemplified as an authentication apparatus that authenticates a person with a finger print.
- the output device 5a outputs the extraction result of the finger / palmprint image processing device 4a.
- the output device 5a is exemplified by a display or a printer. However, the output device 5 and the finger / palm-print image processing device 4a may be connected via a network or may be connected by a normal connection cable.
- the finger / palm-print image processing device 4 a includes a frequency component analysis unit l la as a program, a frequency component determination unit 12 a, and a ridge image extraction unit 15.
- the frequency component analysis unit 11 a takes in finger / palm-print image data from the finger / palm-print image input device 3.
- the finger / palm-print image of the finger / palm-print image data is divided into a plurality of small areas.
- the frequency components of the finger / palm print image are analyzed for each of the plurality of small regions. Alternatively, in each small area, frequency components are analyzed separately for the case of only the central part and the case of including the peripheral part (overall).
- the analysis result for each small area is output to the frequency component determination unit 12.
- the description thereof is omitted.
- the frequency component determination unit 12a determines the state of each small region based on the result of analysis by the frequency component analysis unit 11a. That is, if the analysis result is a representative frequency component for each small area of the finger / palm print image, it is determined whether each small area is a clear area of finger / palm print. If the analysis results show only the central part and each frequency component of the whole, it is determined whether each small area has a single structure or a fine structure. It is also possible to make both determinations based on the analysis results. The determination result for each small area is output to the ridge line image extraction unit 15.
- a frequency component representing each small area satisfies a predetermined condition that is seen when the ridges of the finger / palm print clearly appear. Do. For a region with a fine structure, it is determined whether the relationship between the frequency component at the center of the small region and the total frequency component satisfies a predetermined condition that is seen when the fine structure is present.
- the ridge image extraction unit 15 selects an appropriate ridge extraction / restoration method for each small region based on the determination result for each small region obtained by the frequency component determination unit 12 a, and the ridge image is selected. Extract ,Restore. The extraction and restoration result is output to the output device 5a.
- an extraction method for example, the methods of Japanese Patent Application Laid-Open Nos. 8-110945 and 9-167230 can be used.
- FIG. 8 is a flow chart showing the operation (the second embodiment of the finger / palm print image processing method) of the second embodiment of the finger / palm print image processing system of the present invention.
- the finger / palm-print image input device 3 acquires finger / palm-print image data indicating a finger / palm-print image.
- the finger / palm-print image processing device 4 a receives finger / palm-print image data from the finger / palm-print image input device 3.
- the frequency component analysis unit 11a divides the finger / palmprint image of the finger / palmprint image data into small regions.
- the method of dividing into small regions is divided into units for determining whether a region with finger and palm print is clear or not. For example, it is divided into square grids of a predetermined size.
- Frequency analysis is performed for each of the divided small areas, and the frequency components (vertical frequency, horizontal frequency) of the image of the small area and its amplitude are detected. Then, a frequency component representative of the small area is determined. Alternatively, for each small area, frequency analysis is performed separately for the central part only and the entire case including the peripheral part, and the central part of the image of the small area and the entire frequency components (vertical frequency, horizontal The frequency) and its amplitude are detected. Also, it is good if you decide the frequency component that represents the central part of the small area and the frequency component that represents the whole case.
- the method of determining frequency components is the same as that of the first embodiment (explained in step S23), and thus the description thereof is omitted.
- the frequency component determination unit 12a is configured such that a frequency component representative of each small region determined for each small region by the frequency component analysis unit 11a, or a frequency component representative of each of the central portion and the whole of each small region is Whether or not a predetermined condition is satisfied is determined for each small area.
- each small area is bright. It is determined whether the area is a plain finger / palm print area.
- the determination method is the same as that of the first embodiment (explained in step S04), and thus the description thereof is omitted.
- the determination is made as follows. That is, in each small area, the central frequency component is compared with the entire frequency component. As a result of comparison, it can be determined that the difference between the two is within a predetermined range and is a region having a fine structure if it is within a predetermined range, or a monotonous flow region if it is within a predetermined range. The reason is explained using FIG. 9 and FIG.
- FIG. 9 and FIG. 14 are diagrams showing an example of a finger / palm print image in a small area.
- the ridge line in the central portion 28a is approximated by a periodic straight line to become a straight line like the small area 41 shown in FIG.
- An approximation of the ridges of the entire body 21a including the part by a periodic straight line is a straight line like a small area 42 shown in FIG. Therefore, the approximation (41) based on the central portion 28a and the approximation (42) based on the whole 21a have the same pattern.
- the small area 21b having a minute structure such as a feature point as shown in FIG.
- the ridge line of the central portion 28b approximated by a periodic straight line is inclined as in the small area 44 shown in FIG. It becomes a straight line, and the approximation of the ridges of the whole 21b including the peripheral part by a periodic straight line becomes a straight line as shown by a small area 45 shown in FIG. Therefore, the approximation (44) based on the central portion 28b and the approximation (45) based on the whole 21b have different patterns. As for this, if the central frequency component and the overall frequency component are compared and it is determined whether or not both are in agreement or within a predetermined range, the small area is monotonous. You can determine the area force you have.
- the ridge line image extraction unit 15 selects an appropriate ridge line extraction / restoration method for each small area, based on the determination result for each small area obtained by the frequency component determination unit 12a. Extract and restore images of ridges. The extraction and restoration results are output to the output device 5.
- a threshold value for appropriately dividing the finger / palmprint image into ridges and valleys is determined. By binarizing, the ridges can be restored faithfully to the original image.
- one small area is two-dimensionally By restoring it as a monotonous pattern such as a chord wave, it is possible to restore ridges without being affected by scratches and wrinkles.
- the ridges and valleys of the finger / palm print image are appropriately determined based on the histogram of the pixel values of each small area, as in Japanese Patent Laid-Open No. 8-110945.
- the ridges can be restored faithfully to the original image by obtaining and binarizing the threshold value to be divided into two.
- one small area can be restored as a monotonous pattern such as a two-dimensional sine wave, as in JP-A-9-167230.
- the characteristic amount when the frequency component determination unit 12a determines clearness or negativeness, fine structure or monotonous area force is taken as a measure indicating clearness or monotony, and the directional filter
- emphasizing the input image with a strong directional filter according to monotony and a weak directional filter according to complexity and clarity an appropriate ridge image is obtained for each small area. Extraction ⁇ It is also possible to restore.
- the ridge line image extraction unit 15 checks whether all the subregions have been extracted and restored. If there is a small area that has not been extracted and restored yet, the process returns to step S23 and the next area is checked.
- the ridge line image restoration unit 15 restores the entire finger / palmprint image based on the restored ridge lines of each small area, and outputs the restored image to the output device 5.
- the output device 5 outputs the finger / palmprint image.
- the ridge extraction method is determined using the determination result for each small area and the ridges are restored, the ridges of the finger / palm print can be restored more accurately.
- the finger / palm-print image input device 3 when the finger / palm-print image input device 3 inputs the finger / palm-print image at one time, it sequentially inputs the partial images used for analyzing the small area with the finger / palm-print image processing device 4 (a). It is also possible. In the case of inputting the entire finger / palm-print image, if the storage capacity of the finger / palm-print image processing device 4 (a) is small and the entire finger / palm-print image can not be stored at one time, image processing may become impossible. However, by inputting partial images sequentially, it is possible to perform image processing as long as the storage capacity necessary for processing a small area is sufficient.
- the finger / palm-print image input device 3 receives an input from the finger / palm-print sensor through a network with a slow communication speed
- communication between the finger / palm-print image input device 3 and the finger / palm-print image processing device 4 (a) If the speed is slow, you can not start image processing until the communication of the entire finger / palm print image is finished, if you try to input the entire finger / palm print image.
- the frequency component analysis unit 11 (a) it is possible to start image processing when only the image of the small area required by the frequency component analysis unit 11 (a) is input.
- communication and frequency component analysis can be performed in parallel, and processing time can be shortened.
- a method is conceivable in which the finger / palm-print image processing device 4 (a) requests the finger / palm-print image processing device 4 for the image of the next small area, and the finger / palm-print image input device 3 sends it according to the request.
- the finger / palm-print image processing device 4 (a) requests the finger / palm-print image processing device 4 for the image of the next small area, and the finger / palm-print image input device 3 sends it according to the request.
- it is not limited to this example.
- the pixel value of the same degree as that of the finger / palm print is determined in order to determine whether it is a frequency component seen in the ridges of the finger / palm print that are not You can distinguish between the background with and the ridge area of the finger print. As a result, the finger / palmprint area can be correctly determined even if there is some shade other than the finger / palm print such as dirt on the background.
- the image quality of the finger / palm print image is judged based on the density of the pixels and the density of the end points and the branch points using whether or not it is a frequency component found in a clear ridge of the finger / palm print. It is possible to distinguish areas that are unclear due to scratches or collapses from areas where ridges are clearly present. Thus, the finger / palmprint area can be correctly determined even if there is an unclear portion in the finger / palmprint area due to the influence of noise.
- the present invention is suitable for applications such as a fingerprint / palmprint image processing system and a fingerprint / palmprint image processing method with an improved image processing function of fingerprint / palmprint.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
- Image Input (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/591,427 US7769206B2 (en) | 2004-03-04 | 2005-01-28 | Finger/palm print image processing system and finger/palm print image processing method |
EP05709462.5A EP1724725B1 (en) | 2004-03-04 | 2005-01-28 | Finger/palm print image processing system and finger/palm print image processing method |
JP2006510620A JP4029412B2 (ja) | 2004-03-04 | 2005-01-28 | 指紋掌紋画像処理システムおよび指紋掌紋画像処理方法 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2004-061292 | 2004-03-04 | ||
JP2004061292 | 2004-03-04 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2005086091A1 true WO2005086091A1 (ja) | 2005-09-15 |
Family
ID=34918058
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2005/001236 WO2005086091A1 (ja) | 2004-03-04 | 2005-01-28 | 指紋掌紋画像処理システムおよび指紋掌紋画像処理方法 |
Country Status (5)
Country | Link |
---|---|
US (1) | US7769206B2 (ja) |
EP (1) | EP1724725B1 (ja) |
JP (1) | JP4029412B2 (ja) |
CN (1) | CN100565580C (ja) |
WO (1) | WO2005086091A1 (ja) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2010001447A1 (ja) | 2008-06-30 | 2010-01-07 | 富士通株式会社 | 認証装置、認証方法および認証プログラム |
WO2010119500A1 (ja) | 2009-04-13 | 2010-10-21 | 富士通株式会社 | 生体情報登録装置、生体情報登録方法及び生体情報登録用コンピュータプログラムならびに生体認証装置、生体認証方法及び生体認証用コンピュータプログラム |
WO2011152213A1 (ja) * | 2010-06-04 | 2011-12-08 | 日本電気株式会社 | 指紋認証システム、指紋認証方法および指紋認証プログラム |
JP2013242914A (ja) * | 2006-04-26 | 2013-12-05 | Aware Inc | 指紋プリビュー品質ならびに細分化 |
WO2016104712A1 (ja) * | 2014-12-26 | 2016-06-30 | Necソリューションイノベータ株式会社 | 画像処理装置、画像処理方法及びプログラム |
DE102018220920A1 (de) | 2017-12-15 | 2019-06-19 | Fujitsu Limited | Informationsverarbeitungsgerät, Verfahren zur biometrischen Authentifizierung und Aufzeichnungsmedium mit einem darauf aufgezeichneten Prgoramm zur biometrischen Authentifizierung |
JPWO2021161375A1 (ja) * | 2020-02-10 | 2021-08-19 |
Families Citing this family (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100573585C (zh) * | 2004-07-22 | 2009-12-23 | 日本电气株式会社 | 图像处理系统 |
KR101481551B1 (ko) * | 2008-06-03 | 2015-01-13 | 엘지전자 주식회사 | 영상 노이즈 제거 장치 및 방법 |
EP2544147A4 (en) | 2010-03-01 | 2016-08-10 | Fujitsu Ltd | DEVICE AND METHOD FOR MANAGING BIOLOGICAL INFORMATION |
CN109905562B (zh) | 2011-12-19 | 2021-12-31 | 夏普株式会社 | 图像输出系统、装置和方法、信息处理装置及认证装置 |
US9330294B2 (en) | 2012-01-26 | 2016-05-03 | Aware, Inc. | System and method of capturing and producing biometric-matching quality fingerprints and other types of dactylographic images with a mobile device |
US9977947B2 (en) * | 2015-08-25 | 2018-05-22 | Gingy Technology Inc. | Fingerprint identification method and device thereof |
US10216978B2 (en) | 2014-08-26 | 2019-02-26 | Gingy Technology Inc. | Fingerprint identification device and fingerprint identification method |
US9547083B2 (en) | 2014-09-12 | 2017-01-17 | Qualcomm Incorporated | Determining whether a target object was present during a scanning operation |
KR101639986B1 (ko) * | 2015-10-07 | 2016-07-15 | 크루셜텍 (주) | 지문 등록 및 인증 속도 향상을 위한 지문 정보 프로세싱 방법 및 그 장치 |
US11449061B2 (en) | 2016-02-29 | 2022-09-20 | AI Incorporated | Obstacle recognition method for autonomous robots |
US10452071B1 (en) | 2016-02-29 | 2019-10-22 | AI Incorporated | Obstacle recognition method for autonomous robots |
US11927965B2 (en) | 2016-02-29 | 2024-03-12 | AI Incorporated | Obstacle recognition method for autonomous robots |
US10788836B2 (en) | 2016-02-29 | 2020-09-29 | AI Incorporated | Obstacle recognition method for autonomous robots |
US9946917B2 (en) * | 2016-03-31 | 2018-04-17 | Synaptics Incorporated | Efficient determination of biometric attribute for fast rejection of enrolled templates and other applications |
US20170364920A1 (en) * | 2016-06-16 | 2017-12-21 | Vishal Anand | Security approaches for virtual reality transactions |
TWI576717B (zh) * | 2016-07-26 | 2017-04-01 | Dimensional biometric identification system and method | |
CN109784195B (zh) * | 2018-12-20 | 2021-03-23 | 金菁 | 一种用于企业指纹打卡的指纹识别方法及系统 |
KR102577587B1 (ko) * | 2019-01-03 | 2023-09-12 | 삼성전자주식회사 | 지문 인증 방법 및 장치 |
CN110717429B (zh) * | 2019-09-27 | 2023-02-21 | 联想(北京)有限公司 | 一种信息处理方法、电子设备及计算机可读存储介质 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09167230A (ja) * | 1995-12-18 | 1997-06-24 | Nec Corp | 指掌紋画像処理装置 |
WO2001055966A1 (fr) * | 2000-01-28 | 2001-08-02 | Chuo Hatsujo Kabushiki Kaisha | Procede d'evaluation d'une image d'empreinte digitale et dispositif d'appariement d'empreintes digitales |
JP2002288672A (ja) * | 2001-03-26 | 2002-10-04 | Nec Corp | 指掌紋画像処理装置及び方法 |
JP2002288641A (ja) * | 2001-03-26 | 2002-10-04 | Nec Corp | 指掌紋画像処理装置及び方法 |
Family Cites Families (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB1172539A (en) * | 1966-10-12 | 1969-12-03 | Atomic Energy Authority Uk | Improvements in or relating to Methods and Apparatus for Classifying Patterns |
US4225850A (en) * | 1978-11-15 | 1980-09-30 | Rockwell International Corporation | Non-fingerprint region indicator |
JPS63308679A (ja) | 1987-06-11 | 1988-12-16 | Secom Co Ltd | 隆線紋様の隆線方向検出装置 |
JPH08110945A (ja) | 1993-05-07 | 1996-04-30 | Sharp Corp | 指紋入力方法 |
JPH08110949A (ja) | 1993-05-07 | 1996-04-30 | Sharp Corp | 指紋画像の画質判定方法 |
JPH08129644A (ja) | 1993-05-07 | 1996-05-21 | Sharp Corp | 指紋画像の画質判定方法 |
US5963656A (en) * | 1996-09-30 | 1999-10-05 | International Business Machines Corporation | System and method for determining the quality of fingerprint images |
JP2002099912A (ja) | 2000-09-21 | 2002-04-05 | Nippon Telegr & Teleph Corp <Ntt> | 画像処理方法,画像処理装置および画像処理プログラム記録媒体 |
JP2003044856A (ja) | 2001-07-30 | 2003-02-14 | Dds:Kk | 指紋照合装置、指紋照合方法及び指紋照合プログラム |
US7489807B2 (en) * | 2003-08-07 | 2009-02-10 | Kyungtae Hwang | Statistical quality assessment of fingerprints |
-
2005
- 2005-01-28 JP JP2006510620A patent/JP4029412B2/ja active Active
- 2005-01-28 EP EP05709462.5A patent/EP1724725B1/en active Active
- 2005-01-28 WO PCT/JP2005/001236 patent/WO2005086091A1/ja not_active Application Discontinuation
- 2005-01-28 CN CNB2005800068304A patent/CN100565580C/zh active Active
- 2005-01-28 US US10/591,427 patent/US7769206B2/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09167230A (ja) * | 1995-12-18 | 1997-06-24 | Nec Corp | 指掌紋画像処理装置 |
WO2001055966A1 (fr) * | 2000-01-28 | 2001-08-02 | Chuo Hatsujo Kabushiki Kaisha | Procede d'evaluation d'une image d'empreinte digitale et dispositif d'appariement d'empreintes digitales |
JP2002288672A (ja) * | 2001-03-26 | 2002-10-04 | Nec Corp | 指掌紋画像処理装置及び方法 |
JP2002288641A (ja) * | 2001-03-26 | 2002-10-04 | Nec Corp | 指掌紋画像処理装置及び方法 |
Non-Patent Citations (1)
Title |
---|
See also references of EP1724725A4 * |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10325137B2 (en) | 2006-04-26 | 2019-06-18 | Aware, Inc. | Fingerprint preview quality and segmentation |
US10083339B2 (en) | 2006-04-26 | 2018-09-25 | Aware, Inc. | Fingerprint preview quality and segmentation |
US11250239B2 (en) | 2006-04-26 | 2022-02-15 | Aware, Inc. | Fingerprint preview quality and segmentation |
US9792483B2 (en) | 2006-04-26 | 2017-10-17 | Aware, Inc. | Fingerprint preview quality and segmentation |
JP2013242914A (ja) * | 2006-04-26 | 2013-12-05 | Aware Inc | 指紋プリビュー品質ならびに細分化 |
US9626548B2 (en) | 2006-04-26 | 2017-04-18 | Aware, Inc. | Fingerprint preview quality and segmentation |
US9405957B2 (en) | 2006-04-26 | 2016-08-02 | Aware, Inc. | Fingerprint preview quality and segmentation |
US9031291B2 (en) | 2006-04-26 | 2015-05-12 | Aware, Inc. | Fingerprint preview quality and segmentation |
US9152843B2 (en) | 2006-04-26 | 2015-10-06 | Aware, Inc. | Fingerprint preview quality and segmentation |
US10776604B2 (en) | 2006-04-26 | 2020-09-15 | Aware, Inc. | Fingerprint preview quality and segmentation |
US8464323B2 (en) | 2008-06-30 | 2013-06-11 | Fujitsu Limited | Authentication apparatus |
WO2010001447A1 (ja) | 2008-06-30 | 2010-01-07 | 富士通株式会社 | 認証装置、認証方法および認証プログラム |
US8644566B2 (en) | 2009-04-13 | 2014-02-04 | Fujitsu Limited | Biometric authentication device and biometric authentication method |
WO2010119500A1 (ja) | 2009-04-13 | 2010-10-21 | 富士通株式会社 | 生体情報登録装置、生体情報登録方法及び生体情報登録用コンピュータプログラムならびに生体認証装置、生体認証方法及び生体認証用コンピュータプログラム |
US8942439B2 (en) | 2010-06-04 | 2015-01-27 | Nec Corporation | Fingerprint authentication system, fingerprint authentication method, and fingerprint authentication program |
JP5850341B2 (ja) * | 2010-06-04 | 2016-02-03 | 日本電気株式会社 | 指紋認証システム、指紋認証方法および指紋認証プログラム |
WO2011152213A1 (ja) * | 2010-06-04 | 2011-12-08 | 日本電気株式会社 | 指紋認証システム、指紋認証方法および指紋認証プログラム |
JPWO2016104712A1 (ja) * | 2014-12-26 | 2017-10-05 | Necソリューションイノベータ株式会社 | 画像処理装置、画像処理方法及びプログラム |
US10275677B2 (en) | 2014-12-26 | 2019-04-30 | Nec Solution Innovators, Ltd. | Image processing apparatus, image processing method and program |
WO2016104712A1 (ja) * | 2014-12-26 | 2016-06-30 | Necソリューションイノベータ株式会社 | 画像処理装置、画像処理方法及びプログラム |
DE102018220920A1 (de) | 2017-12-15 | 2019-06-19 | Fujitsu Limited | Informationsverarbeitungsgerät, Verfahren zur biometrischen Authentifizierung und Aufzeichnungsmedium mit einem darauf aufgezeichneten Prgoramm zur biometrischen Authentifizierung |
JPWO2021161375A1 (ja) * | 2020-02-10 | 2021-08-19 | ||
WO2021161375A1 (ja) * | 2020-02-10 | 2021-08-19 | 日本電気株式会社 | 画像処理装置、画像処理方法、及び、記録媒体 |
JP7322980B2 (ja) | 2020-02-10 | 2023-08-08 | 日本電気株式会社 | 画像処理装置、画像処理方法、及び、プログラム |
Also Published As
Publication number | Publication date |
---|---|
US7769206B2 (en) | 2010-08-03 |
EP1724725A1 (en) | 2006-11-22 |
EP1724725A4 (en) | 2011-01-12 |
JP4029412B2 (ja) | 2008-01-09 |
EP1724725B1 (en) | 2015-09-23 |
CN1954341A (zh) | 2007-04-25 |
JPWO2005086091A1 (ja) | 2008-04-24 |
US20070189586A1 (en) | 2007-08-16 |
CN100565580C (zh) | 2009-12-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2005086091A1 (ja) | 指紋掌紋画像処理システムおよび指紋掌紋画像処理方法 | |
US7970185B2 (en) | Apparatus and methods for capturing a fingerprint | |
US6876757B2 (en) | Fingerprint recognition system | |
EP0780781B1 (en) | Feature extraction for fingerprint recognition | |
WO2007029591A1 (ja) | 画像処理装置、マスク作成方法及びプログラム | |
Hambalık | Fingerprint recognition system using artificial neural network as feature extractor: design and performance evaluation | |
WO2016029346A1 (zh) | 指纹提取方法和装置 | |
Julasayvake et al. | An algorithm for fingerprint core point detection | |
Gamassi et al. | Fingerprint local analysis for high-performance minutiae extraction | |
Singh et al. | Fusion of 4-slap fingerprint images with their qualities for human recognition | |
Orczyk et al. | Fingerprint ridges frequency | |
JP6229352B2 (ja) | 画像処理装置、画像処理方法およびプログラム | |
JP6879524B2 (ja) | 認証情報処理プログラム及び認証情報処理装置 | |
US7136515B2 (en) | Method and apparatus for providing a binary fingerprint image | |
KR100359920B1 (ko) | 홍채 인식 시스템에서의 모조 홍채 판별방법 | |
JPH1063847A (ja) | パターン照合装置 | |
JP2008129679A (ja) | 指紋判別モデル構築方法、指紋判別方法、本人認証方法、指紋判別装置、および、本人認証装置 | |
Iwasokun et al. | Review and evaluation of fingerprint singular point detection algorithms | |
Banđur et al. | Improving minutiae extraction in fingerprint images through robust enhancement | |
Kolivand et al. | A functional enhancement on scarred fingerprint using sigmoid filtering | |
CN110659536A (zh) | 指纹识别设备分辨率的测试方法及装置、系统及存储介质 | |
Tachaphetpiboon et al. | A fingerprint matching method using DCT features | |
Julasayvake et al. | A Combined Technique in Fingerprint Core Point detection | |
Ogundepo et al. | Development of a real time fingerprint authentication/identification system for students’ record | |
Hamid et al. | Fingerprint Image Enhancement Using Median Sigmoid Filter |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NA NI NO NZ OM PG PH PL PT RO RU SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWE | Wipo information: entry into national phase |
Ref document number: 2006510620 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 10591427 Country of ref document: US Ref document number: 2005709462 Country of ref document: EP Ref document number: 2007189586 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 200580006830.4 Country of ref document: CN |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWW | Wipo information: withdrawn in national office |
Ref document number: DE |
|
WWP | Wipo information: published in national office |
Ref document number: 2005709462 Country of ref document: EP |
|
WWP | Wipo information: published in national office |
Ref document number: 10591427 Country of ref document: US |