CN103020953A - Segmenting method of fingerprint image - Google Patents

Segmenting method of fingerprint image Download PDF

Info

Publication number
CN103020953A
CN103020953A CN2012104407357A CN201210440735A CN103020953A CN 103020953 A CN103020953 A CN 103020953A CN 2012104407357 A CN2012104407357 A CN 2012104407357A CN 201210440735 A CN201210440735 A CN 201210440735A CN 103020953 A CN103020953 A CN 103020953A
Authority
CN
China
Prior art keywords
image
piece
gray
foreground blocks
background
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN2012104407357A
Other languages
Chinese (zh)
Inventor
刘汉英
周剑勋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guilin University of Technology
Original Assignee
Guilin University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guilin University of Technology filed Critical Guilin University of Technology
Priority to CN2012104407357A priority Critical patent/CN103020953A/en
Publication of CN103020953A publication Critical patent/CN103020953A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Image Analysis (AREA)

Abstract

The invention discloses a segmenting method of a fingerprint image. The segmenting method specifically comprises the following steps: a, reading in the fingerprint image; b, quickly cutting the fingerprint image; c, transforming in reverse colour; d, equalizing; e, carrying out top-hat transformation; f, calculating the characteristic quantity in blockst; g, segmenting in blocks; h, processing the image according to morphology; and i, obtaining the segmented fingerprint image. The segmenting method of the finger image is applicable to the fingerprint image poorer in quality, can correctly segment the fingerprint, and is higher in reliability; the ISODATA (Iterative Self-organizing Data Analysis Techniques Algorithm) clustering algorithm is adopted and used for segmenting in blocks, and the clustering speed is higher; the quick cutting way is carried out, thereby the processing time is reduced; the block segmenting mode and pixel segmenting mode are combined, thus the segmented fingerprint is relatively smooth in contour; and the image equalizing mode and the top-hat transformation mode are adopted to enhance the image, and as a result, the segmenting is more efficient.

Description

A kind of dividing method of fingerprint image
Technical field
The present invention relates to a kind of Pre-processing Method for Fingerprint Image, particularly a kind of dividing method of fingerprint image.
Background technology
Fingerprint image identification be use the earliest in the human biometrics identification technology, the cheapest branch of price, be widely used in criminal investigation and case detection, house safety, the identity validation of the financial institutions such as bank, security, insurance, gate inhibition's control of important area, the field such as office worker or member management has broad application prospects.
Fingerprint Image Segmentation is the important step of fingerprint identification pretreatment stage, fundamental purpose is to remove non-fingerprint region and the more finger-print region that is not easily distinguishable of noise, effectively cut apart the time that can reduce subsequent treatment, reduce the extraction of pseudo-characteristic point, improve recognition accuracy.
Fingerprint segmentation method commonly used has at present: a is according to the dividing method of gradation of image characteristic, utilize fingerprint image average gray and variance that fingerprint image is cut apart, having global threshold to cut apart with adaptive threshold cuts apart, global threshold is cut apart and is depended on the well-distributed bimodality of gradation of image, if bimodality is not obvious or gray scale is the multimodal distribution, segmentation effect is just undesirable, adaptive threshold is cut apart can be low with contrast and the Region Segmentation of the easy recovery of high directivity is fallen, and there is blocking effect in the fingerprint image after cutting apart; B is according to the dividing method of fingerprint image orientation and frequency characteristic, this method more complicated, and the calculating of particularly putting direction or dot frequency, zone or the central cam near zone inhomogeneous to the crestal line thickness are difficult to accurate calculating; C is according to the dividing method of gamma characteristic and directivity characteristics, utilize Local standard deviation (or variance) and the consistance feature of image, adopt linear classification to cut apart, this method has been considered directivity characteristics and gamma characteristic, multifrequency nature is merged, but the selection of its coefficient is very crucial, and the setting of threshold value is difficulty relatively; D is based on the dividing method of hidden Markov model; E is based on the dividing method of conversion and energy field; Method d and method e have considered many factors, but the algorithm computational complexity is larger, and be low to the low quality fingerprint image treatment effeciency, can not accurately cut apart.
Summary of the invention
The dividing method that the purpose of this invention is to provide a kind of fingerprint image, the method is applied to ISODATA clustering algorithm (iteration Self Organization Analysis algorithm) and morphological images disposal route in the Fingerprint Image Segmentation, first fingerprint image is carried out cutting, if the fingerprint image contrast is lower, then image is carried out equalization processing, then image is carried out top cap conversion, compensate inhomogeneous background luminance, with the ISODATA cluster image is carried out piecemeal at last and cut apart, morphological images is processed.
Concrete steps are:
(1) read in fingerprint image, determine a minute block size W according to image resolution ratio resolution, if resolution 600dpi, if W=30 then is resolution<400 dpi, then W=8, otherwise the W acquiescence equals 16, and fingerprint image is converted to double class image img.
(2) the double class image img of step (1) gained carried out Fast trim:
A. since the 1st row, capable every x, calculate the difference diff (i) of the capable maximum gradation value of i and minimum gradation value; I=1+kx wherein, k is nonnegative integer,
Figure DEST_PATH_GDA00002777286800021
M is the line number of image, i≤m, and i rounds with the floor function;
B. obtain the maximal value diffmax of the difference diff (i) of all maximum gradation value and minimum gradation value;
C. the larger calculating row diffd(of difference that finds out maximum gradation value and minimum gradation value gets the difference of maximum gradation value and minimum gradation value greater than the row of diffmax/3);
D. find the larger begin column mb of difference, from the first calculating row beginning that step (2) c found out the step, if the difference of continuous two calculating row is all larger, determines that begin column is last calculating row (being not less than 1) of this calculating row, otherwise seek backward;
E. find out the larger end line me of difference, last that find out from step (2) c go on foot calculates row to begin, if the difference that continuous two calculating are gone is all larger, then end line is that this rear calculating of calculating row is gone (being not more than m), otherwise forward searching;
F. the method by step a ~ e finds the larger begin column nb of difference and end column ne;
G. end line me and end column ne are adjusted, make cutting after image be of a size of minute integral multiple of block size W, original image img is carried out cutting, obtain image img1 after the cutting, the image size is m1*n1 after the cutting, m1=me-mb wherein, n1=ne-nb.
(3) inverse conversion:
A. the average gray avgbound of pixel around the computed image img1 namely calculates the first row, last column, and first row is listed as the average gray of all pixels with last;
If b. background is brighter, i.e. avgbound〉0.5, then carry out inverse conversion img1=1-img1, otherwise jump to step (4).
(4) equalization;
A. the average gray of computed image img1 avg 1 = Σ i = 1 m 1 Σ j = 1 n 1 img 1 ( i , j ) - - - ( 1 )
B. the standard deviation of computed image std 1 = Σ i = 1 m 1 Σ j = 1 n 1 ( imgl ( i , j ) - avg 1 ) 2 m 1 * n 1 - 1 - - - ( 2 )
C. image histogram equalization is if std1<T1(T1 gets 0.11), then carry out the image histogram equalization, otherwise jump to step (5).
(5) top cap conversion;
A., it is that radius is the circle of W/2 that structural element is set;
B. image img1 is carried out top cap conversion, obtain image img2.
(6) piecemeal calculated characteristics amount;
A. the fritter imgb that image img2 is divided into the non-overlapping copies of W*W size, the calculated characteristics amount;
B. computing block gray average avgb: avgb = Σ i = 1 w Σ j = 1 w imgb ( i , j ) - - - ( 3 )
C. computing block standard deviation stdb: stdb = Σ i = 1 w Σ j = 1 w ( imgb ( i , j ) - avgb ) 2 w * w - 1 - - - ( 4 )
D. computing block grey-scale contrast zb:
Figure DEST_PATH_GDA00002777286800033
In the formula, n1 is gray-scale value counting more than or equal to piece gray average avgb in the piece, n2 is gray-scale value counting less than piece gray average avgb in the piece, t1 is the had some gray-scale value sum of gray-scale value in the piece more than or equal to piece gray average avgb, and t2 is the had some gray-scale value sum of gray-scale value in the piece less than piece gray average avgb;
E. computing block direction consistance cohb: cohb = ( G xx - G yy ) 2 + 4 G xy 2 G xx + G yy - - - ( 6 )
G xx = Σ u = 1 w Σ v = 1 w ▿ x ( i + u , j + v ) 2
G yy = Σ u = 1 w Σ v = 1 w ▿ y ( i + u , j + v ) 2
In the formula, G yy = Σ u = 1 w Σ v = 1 w ▿ x ( i + u , j + v ) · ▿ y ( i + u , j + v ) - - - ( 7 )
▿ x = Σ u = 1 3 Σ v = 1 3 S x ( u , v ) · imgb ( i + u , j + v )
▿ y = Σ u = 1 3 Σ v = 1 3 S y ( u , v ) · imgb ( i + u , j + v )
S x, S yBe the Sobel operator.
(7) piecemeal is cut apart;
A. determine respectively four characteristic quantity bound up_feature and low_feature;
up_feature= min{0.9,maxfeature-difffeature}
low_feature= min{0.1,minfeature+difffeature} (8)
In the formula, difffeature=(maxfeature-minfeature)/10, maxfeature are the maximal value of all block feature amounts, and minfeature is the minimum value of all block feature amounts;
B. determine initial background piece class and initial background piece class center.When certain characteristic quantity is the initial background piece less than its corresponding lower prescribing a time limit.The piece number of initial background piece is more than or equal to 1.Initial background class center is the four-dimensional vector that the mean value of all initial background block feature amounts forms;
C. determine initial foreground blocks class and initial foreground blocks class center.When all characteristic quantities all are initial foreground blocks greater than its corresponding upper prescribing a time limit.The four-dimensional vector that the mean value that initial foreground blocks class center is all initial foreground blocks characteristic quantities forms.If do not find initial foreground blocks, namely the piece number of initial foreground blocks is 0, and so initial foreground blocks class center is the four-dimensional vector that four characteristic quantity upper limits form;
D. piece is determined at the end of each non-initial foreground blocks and non-initial background piece, calculated respectively four characteristic quantities to the distance of four components at foreground blocks class center and background piece class center, i.e. Euclidean distance;
If e. all greater than the twice to the distance at background piece class center, then this piece is the background piece to the distance at foreground blocks class center for four characteristic quantities; If all greater than the twice to the distance at foreground blocks class center, then this piece is foreground blocks to the distance at background piece class center for four characteristic quantities; The piece of other situation for temporarily determining;
F. calculate respectively the center of foreground blocks class and background piece class.Background piece class center is four-dimensional vectorial for that have powerful connections, block feature amount mean value formed.Foreground blocks class center is the four-dimensional vector that the mean value of all foreground blocks characteristic quantities forms.If do not find foreground blocks, then foreground blocks class center is the four-dimensional vector that four characteristic quantity upper limits form;
G. with new cluster centre and old cluster centre relatively, if distance is made as 0.01 less than threshold value T2() then stop, otherwise, take new cluster centre as benchmark, return steps d.
(8) morphological images is processed:
A. to image img1, calculate the average gray avgback at the background piece place that piecemeal is partitioned into, if background is darker, namely the inverse conversion is carried out in avgback<0.5, namely y=1-img1 replaces background place gray-scale value with background place average gray.;
B. number of processes n is initialized as 1;
C. the structural element with the 5*5 size corrodes image y, strengthen (square), find regional mask msk with OTSU method (maximum variance between clusters), msk is negated, remove less object;
D. the structural element with the 7*7 size corrodes regional mask msk, fills hole, and number of processes n adds 1, if step c is returned in n≤4, otherwise execution in step e;
E. excessive for preventing boundary segmentation, the segmentation result outer boundary is enlarged W/2, obtain final segmentation result msk.
(9) fingerprint image after obtaining cutting apart:
The effect of described step (2) is that non-finger-print region is removed, and reduces the time of subsequent treatment, adopts the interval several rows to calculate, and has accelerated processing speed.
Described step (3) is only implemented the brighter image of background, and its effect is that to change fingerprint image into background dark, and the image that prospect is bright is so that step (5) is implemented top cap conversion.
Described step (4) is only implemented the low image of contrast, and its effect is that the gray scale spacing of image is pulled open, and makes intensity profile even, increases contrast, makes image detail clear.
The effect of described step (5) is the inhomogeneous background luminance of compensation.
Four characteristic quantities such as described step (6) piecemeal computing block gray average, piece standard deviation, piece grey-scale contrast and piece direction consistance, the foundation of cutting apart as step (7) piecemeal.
Described step (7) adopts the ISODATA clustering algorithm, value according to step (6) characteristic quantity is set initial foreground blocks and initial background piece, carry out cluster take the average of initial foreground blocks and initial background piece as initial cluster center, the result of cluster has three kinds: foreground blocks, background piece, the piece that temporarily can't determine, only the end is determined that piece calculates, judges during cluster, the cluster speed.
Described step (8) uses the morphology disposal route according to pixels to cut apart, image is carried out burn into to be strengthened, with maximum variance between clusters regional mask is carried out binaryzation, deletion small object and hole, for preventing the border over-segmentation, the segmentation result outer boundary is enlarged W/2, obtain final segmentation result msk, this border does not affect subsequent treatment.
Different from existing method, the dividing method of fingerprint image of the present invention have a following advantage:
(1) the present invention is also applicable to second-rate fingerprint image, can correctly cut apart, and higher reliability is arranged;
(2) the present invention adopts the ISODATA clustering algorithm, carries out piecemeal and cuts apart, the cluster speed; Adopt Fast trim, reduced the processing time;
(3) the present invention adopts piece to cut apart with pixel segmentation to combine, and the fingerprint profile that is partitioned into is smoother;
(4) the present invention adopts image equalization and top cap transfer pair image to strengthen, make cut apart more effective.
Description of drawings
Fig. 1 is fingerprint segmentation method flow diagram of the present invention.
Fig. 2 is the fingerprint image of the embodiment of the invention.
Among the figure: (a) be original image FVC2004db3 103_5.GIF; (b) be the image behind (a) Fast trim; (c) be image after the cap conversion of (b) top; (d) be (c) piecemeal segmentation result, black is the background piece; (e) be the conversion of (b) inverse and basis (d) replace the background place with background place average gray image; (f) be that (e) carries out the image mask that the morphology processing obtains; (g) be (f) expand to the original image size with (a) with computing after image.
Fig. 3 is block feature amount of the present invention, is the decimal between 0 ~ 1, and wherein the most black is 0, is 1 the most in vain.
Among the figure: (a) piece gray average avgb; (b) piece standard deviation stdb; (c) piece grey-scale contrast zb; (d) piece direction consistance cohb.
Embodiment
Embodiment:
Method of the present invention is to move under Windows XP environment, realizes with the Matlab language, and its step is:
(1) use the imread function to read in fingerprint image FVC2004db3 103_5.GIF (type of collector is the heat scraping), use the imfinfo function to obtain image resolution ratio resolution, determine a minute block size W=16, be double class image img with image transitions, the image size is 480*300, m=480, n=300 is such as Fig. 2 (a).
(2) image img is carried out Fast trim, x=21.9089 calculates respectively the 1st, 22,44,66,88,110,132,154,176,198,220 ... the maximum gradation value of 461 row and the difference diff of minimum gradation value (i), maximal value diffmax=0.3137, mb=44, me=454, nb=18, ne=300, and be the integral multiple of W with adjusted size, me=443, ne=289, obtain image img1 after the cutting, the image size is 400*272, such as Fig. 2 (b).
(3) pixel average avgbound=0.4009 around the computed image img1, step (4) is jumped in avgbound<0.5.
(4) the standard deviation std1=0.3201 of computed image img1, std1〉0.11, jump to step (5).
(5) use function strel to create radius and be the morphological structuring elements of the circle of W/2=8 size, use function imtophat that image img1 is carried out top cap conversion, obtain image img2, such as Fig. 2 (c).
(6) to image img2 piecemeal computing block gray average avgb, piece standard deviation stdb, piece grey-scale contrast zb, piece direction consistance cohb, as shown in Figure 3.
(7) determine piece gray average bound 0.5018,0.0558,, standard deviation bound 0.4248,0.0472, piece grey-scale contrast bound 0.8380,0.0931, piece direction consistance bound 0.8684,0.0965, initial background piece class center is (0.0343,0.0260,0.0439,0.3199), initial foreground blocks class center is (0.4483,0.4464,0.8646,0.9166), use the ISODATA clustering algorithm to find out part background piece, namely obtaining piecemeal segmentation result mskback, is the part background piece of finding out such as black block among Fig. 2 (d).
(8) to image img1, according to mskback, calculate the average gray avgback=0.3090 of background place that piecemeal is partitioned into, image is carried out the inverse conversion, and background place gray-scale value is replaced with 1-avgback, obtain image y, such as Fig. 2 (e); Use function imerode, with the structural element of 5*5 size image y is corroded, square, find regional mask msk with the OTSU method, negate, remove small object; Structural element with the 7*7 size corrodes regional mask msk, fills hole with function imfill, enlarges W/2=8 again, obtains final mask msk, such as Fig. 2 (f).
(9) mask is expanded to original image size 480*300, the output segmentation effect, such as Fig. 2 (g), black is the background that is partitioned into.

Claims (1)

1. the dividing method of a fingerprint image is characterized in that concrete steps are:
(1) read in fingerprint image, determine a minute block size W according to image resolution ratio resolution, if resolution 600dpi, if W=30 then is resolution<400dpi, then W=8, otherwise the W acquiescence equals 16, and fingerprint image is converted to double class image img;
(2) the double class image img of step (1) gained carried out Fast trim:
A. since the 1st row, capable every x, calculate the difference diff (i) of the capable maximum gradation value of i and minimum gradation value, i=1+kx wherein, k is nonnegative integer,
Figure DEST_PATH_FDA00002777286700011
M is the line number of image, i≤m, and i rounds with the floor function;
B. obtain the maximal value diffmax of the difference diff (i) of all maximum gradation value and minimum gradation value;
C. find out the larger calculating row diffd of difference of maximum gradation value and minimum gradation value---get the difference of maximum gradation value and minimum gradation value greater than the row of diffmax/3;
D. find the larger begin column mb of difference, from the first calculating row beginning that step (2) c found out the step, if the difference of continuous two calculating row is all larger, determine that begin column is last calculating row of this calculating row, is not less than 1, otherwise seeks backward;
E. find out the larger end line me of difference, last that find out from step (2) c go on foot calculates row to begin, if the difference that continuous two calculating are gone is all larger, then end line is that this rear calculating of calculating row is gone, and is not more than m, otherwise forward searching;
F. the method by step a ~ e finds the larger begin column nb of difference and end column ne;
G. end line me and end column ne are adjusted, make cutting after image be of a size of minute integral multiple of block size W, original image img is carried out cutting, obtain image img1 after the cutting, the image size is m1*n1 after the cutting, m1=me-mb wherein, n1=ne-nb;
(3) inverse conversion:
A. the average gray avgbound of pixel around the computed image img1 namely calculates the first row, last column, and first row is listed as the average gray of all pixels with last;
If b. background is brighter, i.e. avgbound〉0.5, then carry out inverse conversion img1=1-img1, otherwise jump to step (4);
(4) equalization:
A. the average gray of computed image img1
Figure DEST_PATH_FDA00002777286700012
B. the standard deviation of computed image
Figure DEST_PATH_FDA00002777286700013
C. image histogram equalization, if std1<T1, T1 gets 0.11, then carries out the image histogram equalization, otherwise jumps to step (5);
(5) top cap conversion:
A., it is that radius is the circle of W/2 that structural element is set;
B. image img1 is carried out top cap conversion, obtain image img2;
(6) piecemeal calculated characteristics amount:
A. the fritter imgb that image img2 is divided into the non-overlapping copies of W*W size, the calculated characteristics amount;
B. computing block gray average avgb:
Figure DEST_PATH_FDA00002777286700021
C. computing block standard deviation stdb:
Figure DEST_PATH_FDA00002777286700022
D. computing block grey-scale contrast zb:
Figure DEST_PATH_FDA00002777286700023
In the formula, n1 is gray-scale value counting more than or equal to piece gray average avgb in the piece, n2 is gray-scale value counting less than piece gray average avgb in the piece, t1 is the had some gray-scale value sum of gray-scale value in the piece more than or equal to piece gray average avgb, and t2 is the had some gray-scale value sum of gray-scale value in the piece less than piece gray average avgb;
E. computing block direction consistance cohb:
Figure DEST_PATH_FDA00002777286700024
Figure DEST_PATH_FDA00002777286700025
Figure DEST_PATH_FDA00002777286700026
In the formula,
Figure DEST_PATH_FDA00002777286700027
Figure DEST_PATH_FDA00002777286700028
Figure DEST_PATH_FDA00002777286700029
S x, S yBe the Sobel operator;
(7) piecemeal is cut apart:
A. determine respectively four characteristic quantity bound up_feature and low_feature;
up_feature=min{0.9,maxfeature-difffeature}
low_feature=min{0.1,minfeature+difffeature} (8)
In the formula, difffeature=(maxfeature-minfeature)/10, maxfeature are the maximal value of all block feature amounts, and minfeature is the minimum value of all block feature amounts;
B. determine initial background piece class and initial background piece class center, when certain characteristic quantity is the initial background piece less than its corresponding lower prescribing a time limit, the piece number of initial background piece is more than or equal to 1, and initial background class center is the four-dimensional vector that the mean value of all initial background block feature amounts forms;
C. determine initial foreground blocks class and initial foreground blocks class center, when all characteristic quantities all are initial foreground blocks greater than its corresponding upper prescribing a time limit, the four-dimensional vector that the mean value that initial foreground blocks class center is all initial foreground blocks characteristic quantities forms, if do not find initial foreground blocks, the piece number that is initial foreground blocks is 0, and so initial foreground blocks class center is the four-dimensional vector that four characteristic quantity upper limits form;
D. piece is determined at the end of each non-initial foreground blocks and non-initial background piece, calculated respectively four characteristic quantities to the distance of four components at foreground blocks class center and background piece class center, i.e. Euclidean distance;
If e. all greater than the twice to the distance at background piece class center, then this piece is the background piece to the distance at foreground blocks class center for four characteristic quantities; If all greater than the twice to the distance at foreground blocks class center, then this piece is foreground blocks to the distance at background piece class center for four characteristic quantities; The piece of other situation for temporarily determining;
F. calculate respectively the center of foreground blocks class and background piece class, background piece class center is four-dimensional vectorial for that have powerful connections, block feature amount mean value formed, foreground blocks class center is the four-dimensional vector that the mean value of all foreground blocks characteristic quantities forms, if do not find foreground blocks, then foreground blocks class center is the four-dimensional vector that four characteristic quantity upper limits form;
G. with new cluster centre and old cluster centre relatively, if distance less than threshold value T2 then stop, T2 is made as 0.01, otherwise, take new cluster centre as benchmark, return steps d;
(8) morphological images is processed:
A. to image img1, calculate the average gray avgback at the background piece place that piecemeal is partitioned into, if background is darker, namely the inverse conversion is carried out in avgback<0.5, namely y=1-img1 replaces background place gray-scale value with background place average gray;
B. number of processes n is initialized as 1;
C. the structural element with the 5*5 size corrodes image y, strengthens---square, use the OTSU method, namely maximum variance between clusters finds regional mask msk, and msk is negated, and removes less object;
D. the structural element with the 7*7 size corrodes regional mask msk, fills hole, and number of processes n adds 1, if step c is returned in n≤4, otherwise execution in step e;
E. excessive for preventing boundary segmentation, the segmentation result outer boundary is enlarged W/2, obtain final segmentation result msk;
(9) fingerprint image after obtaining cutting apart.
CN2012104407357A 2012-11-07 2012-11-07 Segmenting method of fingerprint image Pending CN103020953A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2012104407357A CN103020953A (en) 2012-11-07 2012-11-07 Segmenting method of fingerprint image

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2012104407357A CN103020953A (en) 2012-11-07 2012-11-07 Segmenting method of fingerprint image

Publications (1)

Publication Number Publication Date
CN103020953A true CN103020953A (en) 2013-04-03

Family

ID=47969519

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2012104407357A Pending CN103020953A (en) 2012-11-07 2012-11-07 Segmenting method of fingerprint image

Country Status (1)

Country Link
CN (1) CN103020953A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104952071A (en) * 2015-06-11 2015-09-30 昆明理工大学 Maximum between-cluster variance image segmentation algorithm based on GLSC (gray-level spatial correlation)
CN106803053A (en) * 2015-11-26 2017-06-06 奇景光电股份有限公司 fingerprint image processing method and device
CN107710671A (en) * 2015-04-30 2018-02-16 德山真旭 Terminal installation and computer program
CN107800499A (en) * 2017-11-09 2018-03-13 周小凤 A kind of radio programs broadcast control method
CN111815654A (en) * 2020-07-14 2020-10-23 北京字节跳动网络技术有限公司 Method, apparatus, device and computer readable medium for processing image
CN112215851A (en) * 2020-09-28 2021-01-12 武汉理工大学 Road network automatic construction method, storage medium and system
CN112699863A (en) * 2021-03-25 2021-04-23 深圳阜时科技有限公司 Fingerprint enhancement algorithm, computer-readable storage medium and electronic device
CN114549670A (en) * 2022-02-23 2022-05-27 京东方数字科技有限公司 Image processing method and image processing system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007107050A1 (en) * 2006-03-23 2007-09-27 Zksoftware Beijing Inc. Fingerprint identification method and system
CN101526994A (en) * 2009-04-03 2009-09-09 山东大学 Fingerprint image segmentation method irrelevant to collecting device
CN102208021A (en) * 2011-07-21 2011-10-05 中国人民解放军国防科学技术大学 Fingerprint image splitting method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007107050A1 (en) * 2006-03-23 2007-09-27 Zksoftware Beijing Inc. Fingerprint identification method and system
CN101526994A (en) * 2009-04-03 2009-09-09 山东大学 Fingerprint image segmentation method irrelevant to collecting device
CN102208021A (en) * 2011-07-21 2011-10-05 中国人民解放军国防科学技术大学 Fingerprint image splitting method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
梁媛媛等: "一种指纹图像的快速分割方法", 《计算机工程》 *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107710671A (en) * 2015-04-30 2018-02-16 德山真旭 Terminal installation and computer program
CN107710671B (en) * 2015-04-30 2020-06-12 德山真旭 Terminal device and computer-readable storage medium
CN104952071A (en) * 2015-06-11 2015-09-30 昆明理工大学 Maximum between-cluster variance image segmentation algorithm based on GLSC (gray-level spatial correlation)
CN106803053A (en) * 2015-11-26 2017-06-06 奇景光电股份有限公司 fingerprint image processing method and device
CN106803053B (en) * 2015-11-26 2019-10-11 奇景光电股份有限公司 Fingerprint image processing method and device
CN107800499A (en) * 2017-11-09 2018-03-13 周小凤 A kind of radio programs broadcast control method
CN111815654A (en) * 2020-07-14 2020-10-23 北京字节跳动网络技术有限公司 Method, apparatus, device and computer readable medium for processing image
CN112215851A (en) * 2020-09-28 2021-01-12 武汉理工大学 Road network automatic construction method, storage medium and system
CN112215851B (en) * 2020-09-28 2022-06-21 武汉理工大学 Road network automatic construction method, storage medium and system
CN112699863A (en) * 2021-03-25 2021-04-23 深圳阜时科技有限公司 Fingerprint enhancement algorithm, computer-readable storage medium and electronic device
CN114549670A (en) * 2022-02-23 2022-05-27 京东方数字科技有限公司 Image processing method and image processing system
CN114549670B (en) * 2022-02-23 2023-04-07 京东方数字科技有限公司 Image processing method and image processing system

Similar Documents

Publication Publication Date Title
CN103020953A (en) Segmenting method of fingerprint image
CN109145713B (en) Small target semantic segmentation method combined with target detection
CN111340824B (en) Image feature segmentation method based on data mining
CN106875395B (en) Super-pixel-level SAR image change detection method based on deep neural network
CN102254319B (en) Method for carrying out change detection on multi-level segmented remote sensing image
CN107748873A (en) A kind of multimodal method for tracking target for merging background information
CN110415208B (en) Self-adaptive target detection method and device, equipment and storage medium thereof
CN106991686B (en) A kind of level set contour tracing method based on super-pixel optical flow field
CN103810503A (en) Depth study based method for detecting salient regions in natural image
CN104751142A (en) Natural scene text detection algorithm based on stroke features
CN105809121A (en) Multi-characteristic synergic traffic sign detection and identification method
CN104050471A (en) Natural scene character detection method and system
CN113537316B (en) Vehicle detection method based on 4D millimeter wave radar point cloud
CN101515325A (en) Character extracting method in digital video based on character segmentation and color cluster
CN104899862A (en) Retinal vessel segmentation algorithm based on global or local threshold
CN104537673A (en) Infrared image segmentation method based on multiple threshold values and self-adaptation fuzzy clustering
CN103761726B (en) Block adaptive image partition method based on FCM
CN104809433A (en) Zebra stripe detection method based on maximum stable region and random sampling
CN105719275A (en) Parallel combination image defect segmentation method
CN109784216B (en) Vehicle-mounted thermal imaging pedestrian detection Rois extraction method based on probability map
Kosarevych et al. Image segmentation based on the evaluation of the tendency of image elements to form clusters with the help of point field characteristics
CN107944354A (en) A kind of vehicle checking method based on deep learning
CN106778661A (en) A kind of express lane line detecting method based on morphological transformation and adaptive threshold
CN111612130B (en) Frequency shift keying communication signal modulation mode identification method
Gad et al. Real-time lane instance segmentation using SegNet and image processing

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20130403