CN107169466A - A kind of palmprint image quality overall evaluation method based on sum of ranks ratio method - Google Patents
A kind of palmprint image quality overall evaluation method based on sum of ranks ratio method Download PDFInfo
- Publication number
- CN107169466A CN107169466A CN201710379075.9A CN201710379075A CN107169466A CN 107169466 A CN107169466 A CN 107169466A CN 201710379075 A CN201710379075 A CN 201710379075A CN 107169466 A CN107169466 A CN 107169466A
- Authority
- CN
- China
- Prior art keywords
- palmprint image
- block
- sum
- palmprint
- ranks
- 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.)
- Granted
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention relates to a kind of palmprint image quality overall evaluation method based on sum of ranks ratio method, including:Step S01:Preliminary assessment is done to palmprint image quality, to regard as palmprint image quality overall evaluation unqualified for not reaching the palmprint image of preliminary assessment requirement;Step S02:By palmprint image stripping and slicing, numbering, form palmprint image block and evaluate sequence;Step S03:Every evaluation index of each palmprint image block is calculated respectively;Step S04:Quality overall evaluation is carried out to whole palmprint image blocks using sum of ranks ratio method;Step S041:Every evaluation index to palmprint image block carries out row's order;Step S042:The sum of ranks of the whole palmprint image blocks of definition compares matrix;Step S043:The sum of ranks ratio of each palmmprint block is calculated successively;Step S05:Some sums of ranks are preset than threshold value, statistics determines the quality scale of each palmprint image more than the palmprint image block number of different threshold values.Palmprint image quality overall evaluation two-stage evaluation model of the present invention by palmprint image quality preliminary assessment and based on sum of ranks ratio method can fast and accurately complete the overall merit to palmprint image quality.
Description
Technical field
The present invention provides a kind of palmprint image quality overall evaluation method based on sum of ranks ratio method, belongs to biological characteristic knowledge
Other field, in particular it relates to palm grain identification method.
Background technology
Palmmprint automatic identification technology has fabulous accuracy and higher warp relative to other biological feature identification technique
Ji practicality, current application prospect is very bright and clear.Palmprint image quality evaluation is to influence personal recognition accuracy most directly, most
One of important factor.High-quality palmprint image may insure that Palm Print Recognition System extracts more palm print characteristics data, can
To allow whole palm print datas in the more efficient differentiation palm print database of palmmprint alignment algorithm.Although palmprint image and fingerprint image
Similar on texture and form and common quality evaluating method is also close with fingerprint image quality evaluation method, but passes
The fingerprint image quality evaluation method of system can not be indiscriminately imitated directly in palmprint image quality evaluation problem, and reason is:(1) palmmprint
Image area is bigger than fingerprint image area much times, if still carrying out palmmprint evaluation using fingerprint image quality evaluation method,
The long period is needed to complete;(2) due to palm physiological structure be different from finger, the pressing dynamics of palm it is more uneven and
Impetus is more scattered, and this causes the otherness between each region of palmprint image big, is not suitable for unified using full figure global quality
The mode evaluation image quality of evaluation;(3) when there are multiple evaluation indexes to be used for palmprint image quality evaluation, lack and refer to these
Mark is condensed and is given a synthesis, the strategy of scientific evaluation result.
Not yet there is all effective solution in terms of above three in current palmprint image quality overall evaluation method
And successful application.
The content of the invention
The technology of the present invention solves problem:For palmprint image quality evaluation problem, overcome prior art people's evaluation time long;
Pressing dynamics is uneven, impetus disperses;Without science and effectively evaluating people, not enough there is provided a kind of palm based on sum of ranks ratio method
Print image quality overall evaluation method, by palmprint image quality preliminary assessment and the palmprint image quality based on sum of ranks ratio method
Overall merit two-stage evaluation model can fast and accurately complete the overall merit to palmprint image quality.
Overall flow of the present invention is as shown in figure 1, comprise the following steps:
Step S01:Preliminary assessment is done to palmprint image quality, the palmprint image identification for not reaching preliminary assessment requirement
It is unqualified for palmprint image quality overall evaluation;
Wherein, in general described preliminary assessment includes following quality evaluation:Whether palmprint image complete and the centre of the palm
Two evaluation indexes of white space size.The characteristics of above-mentioned evaluation index, is that computational methods are simple, calculates quick.
Wherein, described every evaluation index, specific explanations are as follows:It is assumed that the height of palmprint image is H pixels, width is
W pixels, then whether (1) palmprint image is complete.The ratio that full figure can be accounted for according to palmmprint region is evaluated:Cpalm=Ipalm/(H
× W), wherein IpalmFor the number of pixels in image in palmmprint region;(2) centre of the palm white space size.In view of convenient design
Threshold value, the index is used as evaluation index using the inverse of number of pixels in the white space of the centre of the palm.Its calculation formula is Bpalm=1/
Iblank, IblankFor the number of pixels of centre of the palm white space.
Wherein, the centre of the palm white space, refers to that palm center does not collect palmmprint line by palm-print image capture equipment
The region of line.The reason for it is formed is due to that the centre of the palm is recessed gently towards the back of the hand direction compared to palm circumference on physiological structure
Fall into, cause centre of the palm part not gathered by palmmprint collecting device.The region that Fig. 2 intermediate cam shapes ABC is identified is exactly that the centre of the palm is empty
White region.In palmprint image quality overall evaluation, the area in the region is the smaller the better.
Wherein, it is described do not reach preliminary assessment requirement refer to be directed to each preliminary assessment index in any one do not surpass
Cross threshold value set in advance, then it is assumed that the palmprint image quality overall evaluation is unqualified, no longer carries out follow-up palmprint image
Quality overall evaluation.
Step S02:By palmprint image stripping and slicing, numbering, palmprint image block quality evaluation sequence is formed;
Wherein, the palmprint image stripping and slicing refers to palmprint image is cut into some image blocks according to certain size, its mesh
Be palmmprint figure is split as some palmprint image blocks, it is convenient follow-up S03 steps are carried out using parallel mode to calculate each palmmprint
Every evaluation index of image block.It is assumed that the height of each palmprint image block is HblockPixel, width is WblockPixel, then slap
The number that print image has the image block that can be cut out altogether isWherein H and W respectively can be by HblockWith
WblockDivide exactly.
Step S03:Every evaluation index of each palmprint image block is calculated respectively;
Wherein, every evaluation index is generally comprised:(1) palmmprint region is in image block accounting;(2) image block dry and wet journey
Degree;(3) image block readability;(4) palmmprint streakline orientation consistency degree.These evaluation indexes are from different perspectives to palmmprint figure
As quality is evaluated.
Wherein, the palmmprint region is in the computational methods of image block accounting:Cblock=Iblock/(Hblock×Wblock),
IblockFor the number of pixels in image block in palmmprint region.
Wherein, described image block dry and wet degree is defined as DRYblock=| 128-Eblock|, EblockFor whole pictures in image block
The desired value of plain gray value.DRYblockIt is higher, illustrate palmmprint block in collection, either palm is partially dry, or it is partially wet.
Wherein, described image block readability can use the standard deviation S of whole grey scale pixel values in palmprint image blockblockEnter
Row is evaluated.
Wherein, palmmprint streakline orientation consistency degree can utilize the method for Gabol filtering in image procossing to the image
Block is filtered calculating, obtains the degree of grain direction uniformity.In the present invention, its result of calculation CONblockRepresent.
Step S04:Quality overall evaluation is carried out to whole palmprint image blocks using sum of ranks ratio method;
Wherein, the use sum of ranks ratio method carries out quality overall evaluation to whole palmprint image blocks and is divided into following several again
Sub-steps:
Step S041:Every evaluation index to palmprint image block carries out row's order;
Step S042:The sum of ranks of the whole palmprint image blocks of definition compares matrix;
Step S043:The sum of ranks ratio of each palmprint image block is calculated successively.
Wherein, every evaluation index carries out row's order described in step S041, and typically (1) palmmprint region in palmprint image block is existed
Image block accounting;(2) image block dry and wet degree;(3) image block readability;(4) streakline orientation consistency degree, four indexs
Carry out row's order.Wherein (1), (3), (4) three indexs are high excellent order, and (2) are low excellent order.
Wherein, the sum of ranks of whole palmprint image blocks is defined described in step S042 than matrix, its specific practice is:Define sum of ranks
It is than matrixOne shared N number of block of image participates in quality overall evaluation, and 4 represent step
4 evaluation indexes described in S041.Either element is R in matrixij, represent the row of j-th of index of i-th of palmprint image block
Order result.
Wherein, the sum of ranks ratio of each palmprint image block is calculated described in step S043 successively, its specific practice is:To any palmmprint
Image block i, its sum of ranks ratio is:
Step S05:Some sums of ranks are preset than threshold value, statistics determines each palm more than the palmprint image block number of different threshold values
The quality scale of print image;
Wherein, described to preset some sums of ranks than threshold value, its specific practice is setting sum of ranks than threshold value Y1And Y2, wherein Y1's
Value is more than Y2Value.
Wherein, statistics is more than the palmprint image block number of different threshold values, and its specific practice is to count each palmmprint respectively successively
Image block RSRiValue is more than or equal to Y1And Y2Number be respectively z1And z2, wherein more than or equal to Y1RSRiValue is also simultaneously greater than Y2。
Wherein it is determined that the quality scale of each palmprint image, its specific practice be set palmprint image quality overall evaluation as
The threshold value of " outstanding " is Z1, palmprint image quality overall evaluation is Z for the threshold value of " good "2.Its judging rules is as follows:If z1
≥Z1, then the final result for assert palmprint image quality overall evaluation is outstanding;If z1<Z1And z2≥Z2, then it is final to assert the palm
The result of print image quality overall evaluation is good;It is final to assert palmmprint figure if above-mentioned two Rule of judgment is unsatisfactory for
As the result of quality overall evaluation is " qualified ".
The present invention has following beneficial technique effect:
(1) a kind of palmprint image quality overall evaluation method based on sum of ranks ratio method of the present invention, can be to palmprint image
Quality carries out preliminary assessment, filters out palmprint image off quality;To palmprint image stripping and slicing, calculate every using parallel mode
Every quality evaluation index of block image block.Which it also avoid palm pressing dynamics not while evaluation time is reduced
Uniformly, impetus is scattered is difficult control problem to the standard that image quality evaluation is brought;Sum of ranks ratio method can be with science, effective
Every palmprint image evaluation index is condensed and provide a comprehensive evaluation result.
(2) the inventive method is for when having multiple metrics evaluation palmprint image quality, giving can be condensed by indices
And provide a synthesis, the strategy of scientific evaluation result.Increasingly extensive, the of the invention Advantageous applied with personal recognition
Effect is more obvious;
(3) mode for the every palmmprint quality evaluation index of palmmprint stripping and slicing and parallel computation that the present invention is constructed is on the one hand effective
Overcome palmprint image quality evaluation calculate time length deficiency;On the other hand also overcome when palm is gathered because of pressing dynamics
Uneven and impetus is scattered, causes the otherness between each region of palmprint image big, is not suitable for using full figure global quality system
One shortcoming evaluated.
Brief description of the drawings
The flow chart of Fig. 1 implementations of the present invention;
Fig. 2 centres of the palm white space schematic diagram.
Embodiment
Below in conjunction with the accompanying drawings and embodiment the present invention is described in detail.
As shown in figure 1, this method comprises the following steps:
Step S01:Preliminary assessment is done to palmprint image quality, the palmprint image identification for not reaching preliminary assessment requirement
It is unqualified for palmprint image quality overall evaluation;
For certain given palmprint image collected, it is assumed that its picture altitude H=2304 pixels, width W=2304
Pixel.The following index of primary Calculation:(1) whether palmprint image is complete.Utilize palmmprint region and the ash of each pixel in background area
The difference of angle value, using the correlation technique of image processing techniques, palmmprint region and background area are cut into by image, palmmprint is counted
The number I of pixel in regionpalm=4034396, thus Cpalm=4034396/ (2304 × 2304)=0.76;(2) centre of the palm is empty
The inverse of white region number of pixels.For the palmmprint region being stripped out from image, stochastical sampling at heart position wherein
Pixel.If pixel gray value is approached with image background regions gray value, filled out using the seed in computer graphics
The method such as fill and progressively find centre of the palm white space.The pixel number for counting centre of the palm white space is Ipalm=4290, then Bpalm
=1/Iblank=1/4290.Set CpalmThreshold value be 0.5, Bpalm=1/9000, then this time complete palmprint image quality comprehensive
The preliminary assessment heel row of evaluation removes underproof situation, then enters step S02.
Step S02:By palmprint image stripping and slicing, numbering, palmprint image block quality evaluation sequence is formed;
By palmprint image according to each block size be Hblock=128 pixels, Wblock=128 pixels are cut.Then amount to
HaveIndividual image block.Non-overlapping region between each block, according to order from left to right from top to bottom
Give this 324 block numbers.
Step S03:Every evaluation index of each palmprint image block is calculated respectively;
It is assumed that what is be presently processing is the 150th image block, every evaluation index of the palmprint image block is calculated respectively:
(1) palmmprint region is in image block accounting.The index can try to achieve I by the method for image procossingblock=15564, then calculate
Formula Cblock=15564/ (128 × 128)=0.95.(2) image block dry and wet degree.The E of the image block can first be tried to achieveblock
=176, DRYblock=| 128-176 |=48.(3) image block readability.The standard deviation of whole grey scale pixel values in image block
Sblock=1333.(4) streakline orientation consistency degree.The method filtered by Gabol in image procossing is to the side of the image block
Calculated to the degree of consistency, CONblock=202.
Step S04:Quality overall evaluation is carried out to whole palmprint image blocks using sum of ranks ratio method;
After the four indices of whole 324 palmprint image blocks, which are calculated, to be finished, step S04 can be started, the step is divided again
Into following several sub-steps:
Step S041:Every evaluation index to palmprint image block carries out row's order;
Due to employing foregoing four indexs in this example as the Appreciation gist of quality overall evaluation, therefore for all
324 image blocks carry out row's orders to this four indexs respectively, wherein (1), (3), (4) three indexs are high excellent order, (2) are low excellent
Order.The row's of providing order result is as follows, and the numeral in its bracket is row's order result.
Block number | Cblock | DRYblock | Sblock | CONblock |
1 | 0.21(272) | 80(4) | 160(241) | 140(32) |
2 | 0.37(180) | 82(6) | 303(181) | 210(23) |
3 | 0.33(202) | 120(30) | 411(156) | 71(245) |
4 | 0.59(165) | 170(88) | 632(121) | 41(291) |
5 | 0.41(172) | 75(3) | 523(133) | 69(249) |
… | … | … | … | … |
323 | 0.66(143) | 70(1) | 872(76) | 82(182) |
324 | 0.72(123) | 73(2) | 753(82) | 119(158) |
Step S042:The sum of ranks of the whole palmprint image blocks of definition compares matrix;
Step S043:The sum of ranks ratio of each palmprint image block is calculated successively.
According to formulaCalculate the sum of ranks ratio of palmprint image block:
The order of each image block below
Calculated one by one according to formula with ratio.
Step S05:Some sums of ranks are preset than threshold value, statistics determines each palm more than the palmprint image block number of different threshold values
The quality scale of print image;
Default sum of ranks is than threshold value Y1=0.560 and Y2=0.303, its RSR is counted to 324 palmprint image blocks successivelyiValue,
Wherein it is more than or equal to Y1Number z1=35, more than Y2Number z2=212.Presetting palmprint image quality overall evaluation is
The threshold value of " outstanding " is Z1=50, palmprint image quality overall evaluation is Z for the threshold value of " good "2=190.Do following judgement:By
In z1<Z1And z2≥Z2, then the result for finally assert current palmprint image quality overall evaluation is good.
The better embodiment to the present invention is explained in detail above, but the present invention is not limited to above-mentioned embodiment party
, can also be on the premise of present inventive concept not be departed from formula, the knowledge that one skilled in the relevant art possesses
Make a variety of changes.
Claims (10)
1. a kind of palmprint image quality overall evaluation method based on sum of ranks ratio method, it is characterised in that:Comprise the following steps:
Step S01:Preliminary assessment is done to palmprint image quality, the palm is regarded as not reaching the palmprint image of preliminary assessment requirement
Print image quality overall evaluation is unqualified;Wherein preliminary assessment includes whether palmprint image complete and centre of the palm white space size two
Individual evaluation index;It is described not reach preliminary assessment requirement and refer to be not above for any one in two preliminary assessment indexs
Threshold value set in advance, then it is assumed that the palmprint image quality overall evaluation is unqualified, no longer carries out follow-up step;
Step S02:By palmprint image stripping and slicing, numbering, palmprint image block quality evaluation sequence is formed;The palmprint image stripping and slicing is
Palmprint image is cut into some image blocks by finger according to preliminary dimension, convenient to carry out follow-up S03 steps calculating using parallel mode;
Step S03:Every evaluation index of each palmprint image block is calculated respectively;Every evaluation index includes:(1) palmmprint
Region is in image block accounting;(2) image block dry and wet degree;(3) image block readability;(4) palmmprint streakline orientation consistency journey
Degree;
Step S04:Quality overall evaluation is carried out to whole palmprint image blocks using sum of ranks ratio method;The use sum of ranks ratio method
Quality overall evaluation is carried out to whole palmprint image blocks and is divided into following several sub-steps again:
Step S041:Every evaluation index to palmprint image block carries out row's order;
Step S042:The sum of ranks of the whole palmprint image blocks of definition compares matrix;
Step S043:The sum of ranks ratio of each palmprint image block is calculated successively;
Wherein, every evaluation index carries out row's order described in step S041, refers to (1) palmmprint region in palmprint image block in image
Block accounting;(2) image block dry and wet degree;(3) image block readability;(4) streakline orientation consistency degree, four indexs are carried out
Order is arranged, wherein (1), (3), (4) three indexs are high excellent order, (2) are low excellent order;
Step S05:Some sums of ranks are preset than threshold value, statistics determines each palmmprint figure more than the palmprint image block number of different threshold values
The quality scale of picture;Default some sums of ranks are to set sum of ranks than threshold value Y than threshold value1And Y2, wherein Y1Value be more than Y2's
Value;When statistics is more than the palmprint image block number of different threshold values, each palmprint image block RSR is counted respectively successivelyiValue is more than or equal to Y1
And Y2Number be respectively z1And z2, wherein more than or equal to Y1The sum of ranks of any palmprint image block compare RSRiValue is also simultaneously greater than
Y2;
It is described determine each palmprint image quality scale be set palmprint image quality overall evaluation as the threshold value of " outstanding " be Z1,
Palmprint image quality overall evaluation is Z for the threshold value of " good "2, judging rules are as follows:If z1≥Z1, then it is final to assert palmmprint
The result of image quality integrated evaluating is outstanding;If z1<Z1And z2≥Z2, then it is final to assert palmprint image quality overall evaluation
Result be good;If above-mentioned two Rule of judgment is unsatisfactory for, the final knot for assert palmprint image quality overall evaluation
Fruit is " qualified ".
2. the palmprint image quality overall evaluation method according to claim 1 based on sum of ranks ratio method, it is characterised in that:
In the step S01, it is as follows whether palmprint image completely judges:It is assumed that the height of palmprint image is H pixels, width is W pixels,
Then the whether complete ratio for accounting for full figure according to palmmprint region of palmprint image is evaluated:Cpalm=Ipalm/ (H × W), wherein Ipalm
For the number of pixels in image in palmmprint region.
3. the palmprint image quality overall evaluation method according to claim 1 based on sum of ranks ratio method, it is characterised in that:
In the step S01, centre of the palm white space size judges as follows:In view of facilitating design threshold, using in the white space of the centre of the palm
The inverse of number of pixels is as evaluation index, and calculation formula is Bpalm=1/Iblank, IblankFor the pixel of centre of the palm white space
Number, wherein, the centre of the palm white space refers to that palm center is not collected the area of palmmprint streakline by palm-print image capture equipment
The reason for domain, formation is due to that the centre of the palm is recessed on physiological structure compared to palm circumference gently towards the back of the hand direction, causes the palm
Center portion point is not gathered by palmmprint collecting device.
4. the palmprint image quality overall evaluation method according to claim 1 based on sum of ranks ratio method, it is characterised in that:
In the step S02:By palmprint image stripping and slicing, numbering, forming palmprint image block quality evaluation sequence process is:
It is assumed that the height of each palmprint image block is HblockPixel, width is WblockPixel, then palmprint image, which has altogether, to cut
The number of the image block gone out isWherein H and W respectively can be by HblockAnd WblockDivide exactly.
5. the palmprint image quality overall evaluation method according to claim 1 based on sum of ranks ratio method, it is characterised in that:
In the step S03, palmmprint region is in the computational methods of image block accounting:Cblock=Iblock/(Hblock×Wblock), Iblock
For the number of pixels in image block in palmmprint region.
6. the palmprint image quality overall evaluation method according to claim 1 based on sum of ranks ratio method, it is characterised in that:
In step S03, described image block dry and wet degree is defined as DRYblock=| 128-Eblock|, EblockFor whole pixels in image block
The desired value of gray value, DRYblockIt is higher, illustrate palmmprint block in collection, either palm is partially dry, or it is partially wet.
7. the palmprint image quality overall evaluation method according to claim 1 based on sum of ranks ratio method, it is characterised in that:
In step S03, described image block readability can use the standard deviation S of whole grey scale pixel values in palmprint image blockblockCarry out
Evaluate.
8. the palmprint image quality overall evaluation method according to claim 1 based on sum of ranks ratio method, it is characterised in that:
In step S03, the palmmprint streakline orientation consistency degree is entered using the methods filtered of Gabol in image procossing to the image block
Row filtering is calculated, and obtains the degree of grain direction uniformity.
9. the palmprint image quality overall evaluation method according to claim 1 based on sum of ranks ratio method, it is characterised in that:
In step S042, the sum of ranks of the whole palmprint image blocks of definition is than matrix process:Define sum of ranks is than matrixOne shared N number of block of image participates in quality overall evaluation, and 4 represent described in step S041
4 evaluation indexes, either element is R in matrixij, represent row's order result of j-th of index of i-th of palmprint image block.
10. the palmprint image quality overall evaluation method according to claim 1 based on sum of ranks ratio method, its feature exists
In:In step S043, it is described calculate each palmprint image block successively sum of ranks be than process:To any palmprint image block i sum of ranks
Than for:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710379075.9A CN107169466B (en) | 2017-05-25 | 2017-05-25 | Palm print image quality comprehensive evaluation method based on rank-sum ratio method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710379075.9A CN107169466B (en) | 2017-05-25 | 2017-05-25 | Palm print image quality comprehensive evaluation method based on rank-sum ratio method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107169466A true CN107169466A (en) | 2017-09-15 |
CN107169466B CN107169466B (en) | 2020-03-31 |
Family
ID=59821631
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710379075.9A Active CN107169466B (en) | 2017-05-25 | 2017-05-25 | Palm print image quality comprehensive evaluation method based on rank-sum ratio method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107169466B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109003259A (en) * | 2018-06-25 | 2018-12-14 | 张威 | Fingerprint quality evaluation method based on streakline Quality Expert's visual cognition machine learning |
CN109191457A (en) * | 2018-09-21 | 2019-01-11 | 中国人民解放军总医院 | A kind of pathological image quality validation recognition methods |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040042645A1 (en) * | 2002-09-04 | 2004-03-04 | Changchun Hongda Optoelectronic | Fingerprint recognition method, and fingerprint control method and system |
US20060120575A1 (en) * | 2004-12-04 | 2006-06-08 | Ahn Do S | Method and apparatus for classifying fingerprint image quality, and fingerprint image recognition system using the same |
CN102567993A (en) * | 2011-12-15 | 2012-07-11 | 中国科学院自动化研究所 | Fingerprint image quality evaluation method based on main component analysis |
CN106096513A (en) * | 2016-06-01 | 2016-11-09 | 深圳信炜科技有限公司 | Fingerprint identification method, fingerprint recognition system and electronic equipment |
CN106295475A (en) * | 2015-05-29 | 2017-01-04 | 北京东方金指科技有限公司 | A kind of based on sum of ranks than the registered fingerprint replacement method of method |
CN106408552A (en) * | 2015-07-27 | 2017-02-15 | 辽宁省公安厅 | Multi-finger position fingerprint image quality comprehensive evaluation method based on rank sum ratio method |
-
2017
- 2017-05-25 CN CN201710379075.9A patent/CN107169466B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040042645A1 (en) * | 2002-09-04 | 2004-03-04 | Changchun Hongda Optoelectronic | Fingerprint recognition method, and fingerprint control method and system |
US20060120575A1 (en) * | 2004-12-04 | 2006-06-08 | Ahn Do S | Method and apparatus for classifying fingerprint image quality, and fingerprint image recognition system using the same |
CN102567993A (en) * | 2011-12-15 | 2012-07-11 | 中国科学院自动化研究所 | Fingerprint image quality evaluation method based on main component analysis |
CN106295475A (en) * | 2015-05-29 | 2017-01-04 | 北京东方金指科技有限公司 | A kind of based on sum of ranks than the registered fingerprint replacement method of method |
CN106408552A (en) * | 2015-07-27 | 2017-02-15 | 辽宁省公安厅 | Multi-finger position fingerprint image quality comprehensive evaluation method based on rank sum ratio method |
CN106096513A (en) * | 2016-06-01 | 2016-11-09 | 深圳信炜科技有限公司 | Fingerprint identification method, fingerprint recognition system and electronic equipment |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109003259A (en) * | 2018-06-25 | 2018-12-14 | 张威 | Fingerprint quality evaluation method based on streakline Quality Expert's visual cognition machine learning |
CN109003259B (en) * | 2018-06-25 | 2022-02-18 | 张威 | Fingerprint quality evaluation method based on line quality expert visual cognition machine learning |
CN109191457A (en) * | 2018-09-21 | 2019-01-11 | 中国人民解放军总医院 | A kind of pathological image quality validation recognition methods |
CN109191457B (en) * | 2018-09-21 | 2022-07-01 | 中国人民解放军总医院 | Pathological image quality validity identification method |
Also Published As
Publication number | Publication date |
---|---|
CN107169466B (en) | 2020-03-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108447062A (en) | A kind of dividing method of the unconventional cell of pathological section based on multiple dimensioned mixing parted pattern | |
CN104408429B (en) | A kind of video represents frame extracting method and device | |
CN103218619A (en) | Image aesthetics evaluating method | |
CN105989347B (en) | Objective item intelligently reading method and system | |
CN104680524B (en) | A kind of leafy vegetable disease screening method | |
CN110120042B (en) | Crop image pest and disease damage area extraction method based on SLIC super-pixel and automatic threshold segmentation | |
CN110827306B (en) | Purple soil image segmentation and extraction method based on self-adaptive density peak value clustering | |
CN104636721B (en) | A kind of palm grain identification method based on profile Yu Edge texture Fusion Features | |
CN106462771A (en) | 3D image significance detection method | |
CN101526994B (en) | Fingerprint image segmentation method irrelevant to collecting device | |
CN106599051A (en) | Method for automatically annotating image on the basis of generation of image annotation library | |
CN108732172A (en) | Chinese medicine performance rating method, equipment and medium | |
CN109859257B (en) | Skin image texture evaluation method and system based on texture directionality | |
CN108323203A (en) | A kind of method, apparatus and intelligent terminal quantitatively detecting face skin quality parameter | |
CN106340000A (en) | Bone age assessment method | |
CN112991238B (en) | Food image segmentation method, system and medium based on texture and color mixing | |
CN105160346A (en) | Tongue coating greasyness identification method based on texture and distribution characteristics | |
CN110458792A (en) | Method and device for evaluating quality of face image | |
CN109190571B (en) | Method and device for detecting and identifying typical plant species eaten by grazing sheep | |
CN102354388B (en) | Method for carrying out adaptive computing on importance weights of low-level features of image | |
CN107169466A (en) | A kind of palmprint image quality overall evaluation method based on sum of ranks ratio method | |
CN115730858A (en) | Cultural product design intelligent management platform based on big data | |
CN116596879A (en) | Grape downy mildew self-adaptive identification method based on quantiles of boundary samples | |
CN106485266A (en) | A kind of ancient wall classifying identification method based on extraction color characteristic | |
CN110874835B (en) | Crop leaf disease resistance identification method and system, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |