CN105608409A - Method and device for fingerprint identification - Google Patents
Method and device for fingerprint identification Download PDFInfo
- Publication number
- CN105608409A CN105608409A CN201510420617.3A CN201510420617A CN105608409A CN 105608409 A CN105608409 A CN 105608409A CN 201510420617 A CN201510420617 A CN 201510420617A CN 105608409 A CN105608409 A CN 105608409A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- image
- region
- area
- characteristic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 239000000284 extract Substances 0.000 claims description 10
- 230000008569 process Effects 0.000 abstract description 17
- 230000008878 coupling Effects 0.000 description 13
- 238000010168 coupling process Methods 0.000 description 13
- 238000005859 coupling reaction Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 5
- 238000013316 zoning Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 230000003292 diminished effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
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
-
- 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
- G06V40/1365—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a method and a device for fingerprint identification. The fingerprint identification method comprises steps: a to-be-identified fingerprint image is acquired; the fingerprint image is divided into multiple regions, and according to a fingerprint matching algorithm corresponding to any region in the multiple regions, fingerprint features in the any region are matched with features in a corresponding region of a reference fingerprint image; and according to the matching rate of the fingerprint features in the any region, whether the to-be-identified fingerprint image is successfully matched with the reference fingerprint image is determined. According to the technical scheme of the invention, through carrying out different region dividing on the acquired fingerprint image, a different algorithm is adopted to process a different region, the fingerprint identification can be quickly carried out, the fingerprint information utilization rate during the fingerprint identification process can be improved, and the success rate and the accuracy for fingerprint identification can be further improved.
Description
Technical field
The present invention relates to fingerprint identification technology field, in particular to a kind of method of fingerprint recognitionDevice with a kind of fingerprint recognition.
Background technology
At present, fingerprint identification technology is as a kind of more ripe biometrics identification technology, by extensivelyBe applied in multiple fields. And first fingerprint recognition will gather fingerprint image conventionally, at fingerprint imageIn gatherer process, because the orientation of each stamp is not exclusively the same, impetus difference can be brought different journeysHow the distortion of degree, therefore carry out processing to the fingerprint image collecting and can have influence on whole fingerprint recognitionAccuracy.
In correlation technique, for the processing method of fingerprint image, normally according to the former fingerprint collectingThe corresponding image less than former figure (image 102 as shown in Figure 1) that generates of image, to reduceThe relevant finger print information amount of post-processed and storage. There is certain defect in the method: although do not damagingIn the situation of useful information, original image is diminished, but still abandoned in theory a part of image letterBreath, has reduced the information content in fingerprint recognition process, thereby the success rate that affects fingerprint recognition is with accurateProperty.
Therefore, how can improve the utilization rate of finger print information in fingerprint recognition process, refer to thereby improveSuccess rate and the accuracy of line identification become technical problem urgently to be resolved hurrily.
Summary of the invention
The present invention just based on above-mentioned technical problem one of at least, has proposed a kind of side of fingerprint recognitionCase, not only can carry out fingerprint recognition rapidly, and can improve fingerprint letter in fingerprint recognition processThe utilization rate of breath, and then improved success rate and the accuracy of fingerprint recognition.
In view of this, the present invention proposes a kind of method of fingerprint recognition, comprising: gather to be identifiedFingerprint image; Described fingerprint image is divided into multiple regions, and according to described multiple regions inThe corresponding fingerprint matching algorithm in arbitrary region is by fingerprint characteristic and reference finger in described arbitrary regionFeature in the corresponding region of image is mated; According to the fingerprint characteristic in described arbitrary regionJoining rate determines described fingerprint image to be identified and described reference finger image whether the match is successful.
In this technical scheme, the finger print information amount difference comprising due to the diverse location of fingerprint image,Therefore be divided into multiple regions by collecting fingerprint image, with according to multiple regions in arbitraryThe corresponding fingerprint matching algorithm in region is right by the fingerprint characteristic in arbitrary region and reference finger imageAnswer the feature in region to mate, and determine and treat according to the matching rate of the fingerprint characteristic in arbitrary regionWhether the match is successful for the fingerprint image of identification and reference finger image, makes it possible to in arbitrary regionThe number of the information content comprising takes corresponding matching algorithm to mate, and can be to zones of differentInterior finger print information all effectively extracts, thereby has improved the profit of finger print information in fingerprint recognition processBy rate, be conducive to improve success rate and the accuracy of fingerprint recognition.
In addition, than the scheme of whole fingerprint image being processed in prior art, of the present inventionTechnical scheme, owing to only relevant treatment being carried out in multiple regions of dividing, therefore can effectively reduce fingerprintThe memory space of finger print information in identifying has shortened whole fingerprint recognition process spent simultaneouslyTime, realize the quick identification to fingerprint image.
In technique scheme, preferably, according to the coupling of the fingerprint characteristic in described arbitrary regionRate is determined described fingerprint image to be identified and the described reference finger image step tool whether the match is successfulBody comprises: if the matching rate of the fingerprint characteristic in the arbitrary region in described multiple region is all greater than or etc.In predetermined threshold, determine that described fingerprint image to be identified becomes with described reference finger images matchMerit, described predetermined if the matching rate of the fingerprint characteristic in the arbitrary region in described multiple region is all less thanThreshold value, determines described fingerprint image to be identified and the failure of described reference finger images match.
In this technical scheme, by the coupling of the fingerprint characteristic in the arbitrary region in multiple regionsWhen rate is all more than or equal to predetermined threshold, determine fingerprint image to be identified and reference finger images matchSuccess, otherwise, determine fingerprint image to be identified and the failure of reference finger images match, make it possible toImprove the accuracy of fingerprint matching.
In technique scheme, preferably, described fingerprint image is divided into the step in multiple regionsSpecifically comprise: described fingerprint image is divided into the first area that is positioned at described fingerprint image centerWith the second area that is positioned at outside, described first area.
In this technical scheme, fingerprint image is divided into first area and second area, and wherein firstRegion is positioned at fingerprint image center, and the finger print information amount that it comprises is many; Second area is positioned atOutside, first area, the finger print information amount that it comprises is less than first area. In addition, the application is to fingerprintNumber and the dividing mode of the zoning of image do not limit, and those skilled in the art can basisActual demand is divided.
In technique scheme, preferably, according to relative with the arbitrary region in described multiple regionsThe fingerprint matching algorithm of answering is the corresponding district with reference finger image by the fingerprint characteristic in described arbitrary regionThe step that feature in territory is mated specifically comprises: adopt full matching algorithm to enter to described first areaRow coupling, adopts the matching algorithm of multiple characteristic points to mate to described second area.
In this technical scheme, the finger print information comprising due to first area is maximum, so by theOne region adopts full matching algorithm to mate, and has effectively improved the utilization rate of finger print information, favourableIn the accuracy that improves fingerprint recognition; Because the finger print information amount that second area comprises is relatively less, instituteTo mate by the matching algorithm that adopts multiple characteristic points, but not adopt full matching algorithm to carry outJoin, make it possible to greatly shorten the whole spent time of fingerprint recognition process.
In technique scheme, preferably, adopt full matching algorithm to carry out to described first areaThe step of joining specifically comprises: image enhancement processing is carried out in described first area, obtain figure after treatmentPicture; Extract the characteristic information in described image after treatment, corresponding with described reference finger imageFeature in region is mated.
According to a second aspect of the invention, also propose a kind of device of fingerprint recognition, having comprised: gatheredUnit, for gathering fingerprint image to be identified; Division unit, for dividing described fingerprint imageFor multiple regions; Matching treatment unit is relative with arbitrary region in described multiple regions for basisThe fingerprint matching algorithm of answering is the corresponding district with reference finger image by the fingerprint characteristic in described arbitrary regionFeature in territory is mated; Determining unit, for according to the fingerprint characteristic in described arbitrary regionMatching rate is determined described fingerprint image to be identified and described reference finger image, and whether the match is successful.
In this technical scheme, the finger print information amount difference comprising due to the diverse location of fingerprint image,Therefore be divided into multiple regions by collecting fingerprint image, with according to multiple regions in arbitraryThe corresponding fingerprint matching algorithm in region is right by the fingerprint characteristic in arbitrary region and reference finger imageAnswer the feature in region to mate, and determine and treat according to the matching rate of the fingerprint characteristic in arbitrary regionWhether the match is successful for the fingerprint image of identification and reference finger image, makes it possible to in arbitrary regionThe number of the information content comprising takes corresponding matching algorithm to mate, and can be to zones of differentInterior finger print information all effectively extracts, thereby has improved the profit of finger print information in fingerprint recognition processBy rate, be conducive to improve success rate and the accuracy of fingerprint recognition.
In addition, than the scheme of whole fingerprint image being processed in prior art, of the present inventionTechnical scheme, owing to only relevant treatment being carried out in multiple regions of dividing, therefore can effectively reduce fingerprintThe memory space of finger print information in identifying has shortened whole fingerprint recognition process spent simultaneouslyTime, realize the quick identification to fingerprint image.
In technique scheme, preferably, described determining unit specifically for: if described multiple districtThe matching rate of the fingerprint characteristic in the arbitrary region in territory is all more than or equal to predetermined threshold, determines instituteState fingerprint image to be identified and the success of described reference finger images match, if in described multiple regionThe matching rate of the fingerprint characteristic in arbitrary region is all less than described predetermined threshold, determines described to be identifiedFingerprint image and described reference finger images match failure.
In this technical scheme, by the coupling of the fingerprint characteristic in the arbitrary region in multiple regionsWhen rate is all more than or equal to predetermined threshold, determine fingerprint image to be identified and reference finger images matchSuccess, otherwise, determine fingerprint image to be identified and the failure of reference finger images match, make it possible toImprove the accuracy of fingerprint matching.
In technique scheme, preferably, described division unit specifically for: by described fingerprint imagePicture is divided into and is positioned at the first area of described fingerprint image center and is positioned at outside, described first areaSecond area.
In this technical scheme, fingerprint image is divided into first area and second area, and wherein firstRegion is positioned at fingerprint image center, and the finger print information amount that it comprises is many; Second area is positioned atOutside, first area, the finger print information amount that it comprises is less than first area. In addition, the application is to fingerprintNumber and the dividing mode of the zoning of image do not limit, and those skilled in the art can basisActual demand is divided.
In technique scheme, preferably, described matching treatment unit specifically for: to describedOne region adopts full matching algorithm to mate, and described second area is adopted to the coupling of multiple characteristic pointsAlgorithm mates.
In this technical scheme, the finger print information comprising due to first area is maximum, so by theOne region adopts full matching algorithm to mate, and has effectively improved the utilization rate of finger print information, favourableIn the accuracy that improves fingerprint recognition; Because the finger print information amount that second area comprises is relatively less, instituteTo mate by the matching algorithm that adopts multiple characteristic points, but not adopt full matching algorithm to carry outJoin, make it possible to greatly shorten the whole spent time of fingerprint recognition process.
In technique scheme, preferably, described matching treatment unit adopts described first areaThe operation that full matching algorithm mates specifically comprises: figure image intensifying place is carried out in described first areaReason, obtains image after treatment; Extract the characteristic information in described image after treatment, with describedFeature in the corresponding region of reference finger image is mated.
According to a third aspect of the invention we, also propose a kind of terminal, having comprised: as above-mentioned any one skillThe device of the fingerprint recognition described in art scheme.
By above technical scheme, by the fingerprint image collecting is carried out to zones of different division, andAdopt different algorithms to process to zones of different, not only can carry out rapidly fingerprint recognition, andAnd can improve the utilization rate of finger print information in fingerprint recognition process, and then improve the one-tenth of fingerprint recognitionPower and accuracy.
Brief description of the drawings
Fig. 1 shows the effect schematic diagram of in correlation technique, the fingerprint image collecting being processed;
Fig. 2 shows the exemplary flow of the method for fingerprint recognition according to an embodiment of the inventionFigure;
Fig. 3 shows the schematic block diagram of the device of fingerprint recognition according to an embodiment of the invention;
Fig. 4 shows the signal to fingerprint image zoning according to an embodiment of the inventionFigure;
Fig. 5 shows the schematic diagram that the region 404 shown in Fig. 4 is carried out to feature point extraction;
Fig. 6 shows the schematic diagram that the zones of different shown in Fig. 4 is mated.
Detailed description of the invention
In order more clearly to understand above-mentioned purpose of the present invention, feature and advantage, below in conjunction with attachedFigure and detailed description of the invention are further described in detail the present invention. It should be noted that, notIn the situation of conflict, the feature in the application's embodiment and embodiment can combine mutually.
Set forth in the following description a lot of details so that fully understand the present invention, still,The present invention can also adopt other to be different from other modes described here and implement, therefore, and the present inventionProtection domain be not subject to the restriction of following public specific embodiment.
Fig. 2 shows the exemplary flow of the method for fingerprint recognition according to an embodiment of the inventionFigure.
As shown in Figure 2, the method for fingerprint recognition according to an embodiment of the invention, comprising: stepRapid 202, gather fingerprint image to be identified; Step 204, is divided into multiple by described fingerprint imageRegion, and according to the fingerprint matching algorithm corresponding with arbitrary region in described multiple regions will described inFeature in the corresponding region of the fingerprint characteristic in arbitrary region and reference finger image is mated; StepRapid 206, determine described fingerprint to be identified according to the matching rate of the fingerprint characteristic in described arbitrary regionWhether the match is successful for image and described reference finger image.
In this technical scheme, the finger print information amount difference comprising due to the diverse location of fingerprint image,Therefore be divided into multiple regions by collecting fingerprint image, with according to multiple regions in arbitraryThe corresponding fingerprint matching algorithm in region is right by the fingerprint characteristic in arbitrary region and reference finger imageAnswer the feature in region to mate, and determine and treat according to the matching rate of the fingerprint characteristic in arbitrary regionWhether the match is successful for the fingerprint image of identification and reference finger image, makes it possible to in arbitrary regionThe number of the information content comprising takes corresponding matching algorithm to mate, and can be to zones of differentInterior finger print information all effectively extracts, thereby has improved the profit of finger print information in fingerprint recognition processBy rate, be conducive to improve success rate and the accuracy of fingerprint recognition.
In addition, than the scheme of whole fingerprint image being processed in prior art, of the present inventionTechnical scheme, owing to only relevant treatment being carried out in multiple regions of dividing, therefore can effectively reduce fingerprintThe memory space of finger print information in identifying has shortened whole fingerprint recognition process spent simultaneouslyTime, realize the quick identification to fingerprint image.
In technique scheme, preferably, according to the coupling of the fingerprint characteristic in described arbitrary regionRate is determined described fingerprint image to be identified and the described reference finger image step tool whether the match is successfulBody comprises: if the matching rate of the fingerprint characteristic in the arbitrary region in described multiple region is all greater than or etc.In predetermined threshold, determine that described fingerprint image to be identified becomes with described reference finger images matchMerit, described predetermined if the matching rate of the fingerprint characteristic in the arbitrary region in described multiple region is all less thanThreshold value, determines described fingerprint image to be identified and the failure of described reference finger images match.
In this technical scheme, by the coupling of the fingerprint characteristic in the arbitrary region in multiple regionsWhen rate is all more than or equal to predetermined threshold, determine fingerprint image to be identified and reference finger images matchSuccess, otherwise, determine fingerprint image to be identified and the failure of reference finger images match, make it possible toImprove the accuracy of fingerprint matching.
In technique scheme, preferably, described fingerprint image is divided into the step in multiple regionsSpecifically comprise: described fingerprint image is divided into the first area that is positioned at described fingerprint image centerWith the second area that is positioned at outside, described first area.
In this technical scheme, fingerprint image is divided into first area and second area, and wherein firstRegion is positioned at fingerprint image center, and the finger print information amount that it comprises is many; Second area is positioned atOutside, first area, the finger print information amount that it comprises is less than first area. In addition, the application is to fingerprintNumber and the dividing mode of the zoning of image do not limit, and those skilled in the art can basisActual demand is divided.
In technique scheme, preferably, according to relative with the arbitrary region in described multiple regionsThe fingerprint matching algorithm of answering is the corresponding district with reference finger image by the fingerprint characteristic in described arbitrary regionThe step that feature in territory is mated specifically comprises: adopt full matching algorithm to enter to described first areaRow coupling, adopts the matching algorithm of multiple characteristic points to mate to described second area.
In this technical scheme, the finger print information comprising due to first area is maximum, so by theOne region adopts full matching algorithm to mate, and has effectively improved the utilization rate of finger print information, favourableIn the accuracy that improves fingerprint recognition; Because the finger print information amount that second area comprises is relatively less, instituteTo mate by the matching algorithm that adopts multiple characteristic points, but not adopt full matching algorithm to carry outJoin, make it possible to greatly shorten the whole spent time of fingerprint recognition process.
In technique scheme, preferably, adopt full matching algorithm to carry out to described first areaThe step of joining specifically comprises: image enhancement processing is carried out in described first area, obtain figure after treatmentPicture; Extract the characteristic information in described image after treatment, corresponding with described reference finger imageFeature in region is mated.
Fig. 3 shows the schematic block diagram of the device of fingerprint recognition according to an embodiment of the invention.
As shown in Figure 3, the device 300 of fingerprint recognition according to an embodiment of the invention, bagDraw together: collecting unit 302, division unit 304, matching treatment unit 306 and determining unit 308.
Wherein, collecting unit 302, for gathering fingerprint image to be identified; Division unit 304,For described fingerprint image is divided into multiple regions; Matching treatment unit 306, for basis and instituteState the corresponding fingerprint matching algorithm in arbitrary region in multiple regions by the fingerprint in described arbitrary regionFeature in the corresponding region of feature and reference finger image is mated; Determining unit 308, forDetermine described fingerprint image to be identified and institute according to the matching rate of the fingerprint characteristic in described arbitrary regionWhether the match is successful to state reference finger image.
In this technical scheme, the finger print information amount difference comprising due to the diverse location of fingerprint image,Therefore be divided into multiple regions by collecting fingerprint image, with according to multiple regions in arbitraryThe corresponding fingerprint matching algorithm in region is right by the fingerprint characteristic in arbitrary region and reference finger imageAnswer the feature in region to mate, and determine and treat according to the matching rate of the fingerprint characteristic in arbitrary regionWhether the match is successful for the fingerprint image of identification and reference finger image, makes it possible to in arbitrary regionThe number of the information content comprising takes corresponding matching algorithm to mate, and can be to zones of differentInterior finger print information all effectively extracts, thereby has improved the profit of finger print information in fingerprint recognition processBy rate, be conducive to improve success rate and the accuracy of fingerprint recognition.
In addition, than the scheme of whole fingerprint image being processed in prior art, of the present inventionTechnical scheme, owing to only relevant treatment being carried out in multiple regions of dividing, therefore can effectively reduce fingerprintThe memory space of finger print information in identifying has shortened whole fingerprint recognition process spent simultaneouslyTime, realize the quick identification to fingerprint image.
In technique scheme, preferably, described determining unit 308 specifically for: if described manyThe matching rate of the fingerprint characteristic in the arbitrary region in individual region is all more than or equal to predetermined threshold, trueFixed described fingerprint image to be identified and the success of described reference finger images match, if described multiple regionIn arbitrary region in the matching rate of fingerprint characteristic be all less than described predetermined threshold, described in determining, treatThe fingerprint image of identification and the failure of described reference finger images match.
In this technical scheme, by the coupling of the fingerprint characteristic in the arbitrary region in multiple regionsWhen rate is all more than or equal to predetermined threshold, determine fingerprint image to be identified and reference finger images matchSuccess, otherwise, determine fingerprint image to be identified and the failure of reference finger images match, make it possible toImprove the accuracy of fingerprint matching.
In technique scheme, preferably, described division unit 304 specifically for: by described fingerPrint image is divided into and is positioned at the first area of described fingerprint image center and is positioned at described first areaThe second area in outside.
In this technical scheme, fingerprint image is divided into first area and second area, and wherein firstRegion is positioned at fingerprint image center, and the finger print information amount that it comprises is many; Second area is positioned atOutside, first area, the finger print information amount that it comprises is less than first area. In addition, the application is to fingerprintNumber and the dividing mode of the zoning of image do not limit, and those skilled in the art can basisActual demand is divided.
In technique scheme, preferably, described matching treatment unit 306 specifically for: to instituteState first area and adopt full matching algorithm to mate, described second area is adopted to multiple characteristic pointsMatching algorithm mates.
In this technical scheme, the finger print information comprising due to first area is maximum, so by theOne region adopts full matching algorithm to mate, and has effectively improved the utilization rate of finger print information, favourableIn the accuracy that improves fingerprint recognition; Because the finger print information amount that second area comprises is relatively less, instituteTo mate by the matching algorithm that adopts multiple characteristic points, but not adopt full matching algorithm to carry outJoin, make it possible to greatly shorten the whole spent time of fingerprint recognition process.
In technique scheme, preferably, described matching treatment unit 306 is to described first areaAdopt the operation that full matching algorithm mates specifically to comprise: to carry out figure image intensifying to described first areaProcess, obtain image after treatment; Extract the characteristic information in described image after treatment, with instituteThe feature of stating in the corresponding region of reference finger image is mated.
The invention allows for a kind of terminal (not shown), comprising: refer to as shown in Figure 3The device 300 of line identification.
Below technical scheme of the present invention is further illustrated.
As shown in Figure 4, fingerprint capturer is collected to fingerprint image and carry out region division, be divided into positionIn the region 402 and the region 404 that is positioned at 402 outsides, region of fingerprint image center, and districtThe size in territory 402 is less than the shared area size of image 102 shown in Fig. 1. And after dividingRegion 402 and the memory space that takies of the image that comprises of region 404 be less than the figure shown in Fig. 1The memory space that picture 102 is shared.
For region 402, can carry out figure image intensifying and feature information extraction, can for region 404To carry out the extraction of multiple spot characteristic information, to obtain multiple characteristic point informations, black as shown in Figure 5Look round dot represents the characteristic point of extracting, and it is obvious that these characteristic points possess feature, the spy that information content is strongPoint.
When the fingerprint image of processing in Fig. 4 and Fig. 5 is mated with master-fingerprint image, as figureShown in 6, the zones of different of fingerprint image is adopted to different matching algorithms, particularly, to region402 adopt full matching algorithm, and the characteristic information in region 402 is carried out to coupling one by one, obtainJoin rate P1; Single-point characteristic information in region 404 is mated, obtain matching rate P2, andThe matching rate of P1 and P2 is all more than or equal to P3 (P3 is the predefined threshold values that the match is successful)Time, judge that the match is successful, otherwise it fails to match.
Technique scheme of the present invention has following advantage:
1, be less than the memory space of existing fingerprint recognition. The storage sky in the region 402 shown in Fig. 4Between+storage of image 102 after the Fingerprint Image Segmentation shown in the memory space < Fig. 1 in region 404Space;
2, be less than the match time of scheme shown in Fig. 1 match time. Region 402 is less than institute in Fig. 1Show cut apart after image 102, so when be less than the coupling of image 102 match time in region 402Between, and in region 404, just do the coupling of multiple spot feature, so match time < Fig. 1 of Fig. 4Match time.
3, there is more accurate, sufficient fingerprint characteristic information. In Fig. 4, the fingerprint in region 402Information is the most easily to extract and is the part that information content is maximum; Be multiple spot spy for 404, regionThe extraction of levying, is to improve finger print information utilization rate, and improves the best side of the fingerprint matching degree of accuracyCase; Give up for other image sections, because this partial information not necessarily can be extracted (limitThe size of fingerprint module on current mobile phone), giving up this part does not affect the success rate of coupling yet.
More than be described with reference to the accompanying drawings technical scheme of the present invention, the present invention proposes a kind of newThe scheme of fingerprint recognition, by the fingerprint image collecting is carried out to zones of different division, and to differenceRegion adopts different algorithms to process, and not only can carry out rapidly fingerprint recognition, and canImprove the utilization rate of finger print information in fingerprint recognition process, so improved fingerprint recognition success rate andAccuracy.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, forThose skilled in the art, the present invention can have various modifications and variations. All in essence of the present inventionWithin god and principle, any amendment of doing, be equal to replacement, improvement etc., all should be included in the present inventionProtection domain within.
Claims (10)
1. a method for fingerprint recognition, is characterized in that, comprising:
Gather fingerprint image to be identified;
Described fingerprint image is divided into multiple regions, and according to described multiple regions in arbitrary districtThe corresponding fingerprint matching algorithm in territory is by the fingerprint characteristic in described arbitrary region and reference finger imageFeature in corresponding region is mated;
Determine described fingerprint image to be identified according to the matching rate of the fingerprint characteristic in described arbitrary regionWhether the match is successful with described reference finger image.
2. the method for fingerprint recognition according to claim 1, is characterized in that, according to describedThe matching rate of the fingerprint characteristic in arbitrary region determines that described fingerprint image to be identified and described benchmark refer toThe print image step whether the match is successful specifically comprises:
If the matching rate of the fingerprint characteristic in the arbitrary region in described multiple region is all more than or equal in advanceDetermine threshold value, determine described fingerprint image to be identified and the success of described reference finger images match, ifThe matching rate of the fingerprint characteristic in the arbitrary region in described multiple region is all less than described predetermined threshold,Determine described fingerprint image to be identified and the failure of described reference finger images match.
3. the method for fingerprint recognition according to claim 1 and 2, is characterized in that, by instituteStating the step that fingerprint image is divided into multiple regions specifically comprises:
Described fingerprint image is divided into and is positioned at the first area of described fingerprint image center and is positioned atThe second area in outside, described first area.
4. the method for fingerprint recognition according to claim 3, is characterized in that, according to instituteState the corresponding fingerprint matching algorithm in arbitrary region in multiple regions by the fingerprint in described arbitrary regionThe step that feature in the corresponding region of feature and reference finger image is mated specifically comprises:
Adopt full matching algorithm to mate to described first area, adopt multiple to described second areaThe matching algorithm of characteristic point mates.
5. the method for fingerprint recognition according to claim 4, is characterized in that, to describedOne region adopts the step that full matching algorithm mates specifically to comprise:
Image enhancement processing is carried out in described first area, obtain image after treatment;
Extract the characteristic information in described image after treatment, corresponding with described reference finger imageFeature in region is mated.
6. a device for fingerprint recognition, is characterized in that, comprising:
Collecting unit, for gathering fingerprint image to be identified;
Division unit, for being divided into multiple regions by described fingerprint image;
Matching treatment unit, for the basis fingerprint corresponding with arbitrary region in described multiple regionsMatching algorithm is by the spy in the corresponding region of the fingerprint characteristic in described arbitrary region and reference finger imageLevy and mate;
Determining unit is treated described in determining according to the matching rate of the fingerprint characteristic in described arbitrary regionWhether the match is successful for the fingerprint image of identification and described reference finger image.
7. the device of fingerprint recognition according to claim 6, is characterized in that, described definiteUnit specifically for:
If the matching rate of the fingerprint characteristic in the arbitrary region in described multiple region is all more than or equal in advanceDetermine threshold value, determine described fingerprint image to be identified and the success of described reference finger images match, ifThe matching rate of the fingerprint characteristic in the arbitrary region in described multiple region is all less than described predetermined threshold,Determine described fingerprint image to be identified and the failure of described reference finger images match.
8. according to the device of the fingerprint recognition described in claim 6 or 7, it is characterized in that, described inDivision unit specifically for:
Described fingerprint image is divided into and is positioned at the first area of described fingerprint image center and is positioned atThe second area in outside, described first area.
9. the device of fingerprint recognition according to claim 8, is characterized in that, described couplingProcessing unit specifically for:
Adopt full matching algorithm to mate to described first area, adopt multiple to described second areaThe matching algorithm of characteristic point mates.
10. the device of fingerprint recognition according to claim 9, is characterized in that, described couplingProcessing unit adopts the operation that full matching algorithm mates specifically to comprise to described first area:
Image enhancement processing is carried out in described first area, obtain image after treatment;
Extract the characteristic information in described image after treatment, corresponding with described reference finger imageFeature in region is mated.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510420617.3A CN105608409B (en) | 2015-07-16 | 2015-07-16 | The method and device of fingerprint recognition |
| PCT/CN2015/085828 WO2017008349A1 (en) | 2015-07-16 | 2015-07-31 | Fingerprint recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510420617.3A CN105608409B (en) | 2015-07-16 | 2015-07-16 | The method and device of fingerprint recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105608409A true CN105608409A (en) | 2016-05-25 |
| CN105608409B CN105608409B (en) | 2019-01-11 |
Family
ID=55988336
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510420617.3A Active CN105608409B (en) | 2015-07-16 | 2015-07-16 | The method and device of fingerprint recognition |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN105608409B (en) |
| WO (1) | WO2017008349A1 (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105912918A (en) * | 2016-06-17 | 2016-08-31 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN105912919A (en) * | 2016-06-17 | 2016-08-31 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN105975833A (en) * | 2016-05-27 | 2016-09-28 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN106022069A (en) * | 2016-05-30 | 2016-10-12 | 广东欧珀移动通信有限公司 | Unlocking control method and mobile terminal |
| CN106022074A (en) * | 2016-06-17 | 2016-10-12 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN106055961A (en) * | 2016-05-31 | 2016-10-26 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and mobile terminal |
| CN106055952A (en) * | 2016-05-27 | 2016-10-26 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and apparatus, and user terminal |
| CN106096358A (en) * | 2016-05-30 | 2016-11-09 | 广东欧珀移动通信有限公司 | A kind of solution lock control method and mobile terminal |
| CN106127000A (en) * | 2016-06-17 | 2016-11-16 | 广东欧珀移动通信有限公司 | A kind of unlocked by fingerprint method and terminal |
| CN106203151A (en) * | 2016-06-21 | 2016-12-07 | 广东欧珀移动通信有限公司 | A kind of method opening file and terminal unit |
| CN106250876A (en) * | 2016-08-19 | 2016-12-21 | 深圳市金立通信设备有限公司 | A kind of fingerprint identification method and terminal |
| CN106295559A (en) * | 2016-08-08 | 2017-01-04 | 京东方科技集团股份有限公司 | Method, fingerprint identification device and the display device that a kind of data process |
| CN106326830A (en) * | 2015-06-30 | 2017-01-11 | 三星电子株式会社 | Fingerprint recognition method and apparatus |
| CN106778557A (en) * | 2016-11-30 | 2017-05-31 | 努比亚技术有限公司 | Fingerprint identification device and method |
| CN106934389A (en) * | 2017-04-20 | 2017-07-07 | 维沃移动通信有限公司 | A kind of fingerprint identification method and mobile terminal |
| CN107066852A (en) * | 2016-12-14 | 2017-08-18 | 上海摩软通讯技术有限公司 | The method for generating cipher code and password generating apparatus of application |
| CN107111762A (en) * | 2017-03-20 | 2017-08-29 | 深圳市汇顶科技股份有限公司 | Fingerprint identification method and device |
| CN107341482A (en) * | 2017-07-13 | 2017-11-10 | 青岛海信电器股份有限公司 | Fingerprint identification method, device and computer-readable recording medium |
| CN107358183A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Living iris detection method and Related product |
| CN107528691A (en) * | 2016-06-21 | 2017-12-29 | 中兴通讯股份有限公司 | Communication security control method and wearable device |
| CN108090475A (en) * | 2018-01-17 | 2018-05-29 | 深圳市爱克信智能股份有限公司 | A kind of algorithm for recognizing fingerprint |
| CN108182424A (en) * | 2018-01-29 | 2018-06-19 | 上海天马微电子有限公司 | Display device and its fingerprint identification method |
| CN108304709A (en) * | 2018-01-31 | 2018-07-20 | 广东欧珀移动通信有限公司 | Face unlocking method and related product |
| CN108399374A (en) * | 2017-02-08 | 2018-08-14 | 三星电子株式会社 | Method and apparatus of the selection for the candidate fingerprint image of fingerprint recognition |
| CN109086677A (en) * | 2018-07-09 | 2018-12-25 | 保山市质量技术监督综合检测中心 | A kind of auth method and system based on fingerprint recognition |
| WO2019075601A1 (en) * | 2017-10-16 | 2019-04-25 | 厦门中控智慧信息技术有限公司 | Palm vein recognition method and device |
| CN113191300A (en) * | 2020-10-14 | 2021-07-30 | 王建华 | Method, apparatus and computer readable medium for fingerprint image recognition |
| CN115984948A (en) * | 2023-03-20 | 2023-04-18 | 广东广新信息产业股份有限公司 | Face recognition method applied to temperature sensing and electronic equipment |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109558611B (en) * | 2017-09-27 | 2023-04-07 | 中芯国际集成电路制造(上海)有限公司 | Pattern matching method and matching system thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1521684A (en) * | 2003-02-13 | 2004-08-18 | 合肥工业大学 | Synergic fingerprint identification method |
| CN1664847A (en) * | 2005-03-17 | 2005-09-07 | 上海交通大学 | Embedded system fingerprint identification and matching method |
| CN1831847A (en) * | 2006-03-28 | 2006-09-13 | 北京握奇数据系统有限公司 | Fingerprint characteristic quickly matching method, device and application |
| US20130142405A1 (en) * | 2010-07-29 | 2013-06-06 | Fujitsu Limited | Biometric authentication device, biometric authentication method and computer program for biometric authentication, and biometric information registration device |
| CN104036266A (en) * | 2014-07-03 | 2014-09-10 | 南昌欧菲生物识别技术有限公司 | Fingerprint registration method, fingerprint recognition method, fingerprint recognition device and terminal device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1512437A (en) * | 2002-12-30 | 2004-07-14 | 北京汉王科技有限公司 | Multifunctional off-line finger print attendance machine |
-
2015
- 2015-07-16 CN CN201510420617.3A patent/CN105608409B/en active Active
- 2015-07-31 WO PCT/CN2015/085828 patent/WO2017008349A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1521684A (en) * | 2003-02-13 | 2004-08-18 | 合肥工业大学 | Synergic fingerprint identification method |
| CN1664847A (en) * | 2005-03-17 | 2005-09-07 | 上海交通大学 | Embedded system fingerprint identification and matching method |
| CN1831847A (en) * | 2006-03-28 | 2006-09-13 | 北京握奇数据系统有限公司 | Fingerprint characteristic quickly matching method, device and application |
| US20130142405A1 (en) * | 2010-07-29 | 2013-06-06 | Fujitsu Limited | Biometric authentication device, biometric authentication method and computer program for biometric authentication, and biometric information registration device |
| CN104036266A (en) * | 2014-07-03 | 2014-09-10 | 南昌欧菲生物识别技术有限公司 | Fingerprint registration method, fingerprint recognition method, fingerprint recognition device and terminal device |
Cited By (46)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106326830A (en) * | 2015-06-30 | 2017-01-11 | 三星电子株式会社 | Fingerprint recognition method and apparatus |
| CN106055952A (en) * | 2016-05-27 | 2016-10-26 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and apparatus, and user terminal |
| CN105975833B (en) * | 2016-05-27 | 2019-04-09 | Oppo广东移动通信有限公司 | A kind of unlocked by fingerprint method and terminal |
| CN105975833A (en) * | 2016-05-27 | 2016-09-28 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| US10423814B2 (en) | 2016-05-30 | 2019-09-24 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method for unlocking mobile terminal and mobile terminal |
| CN106096358B (en) * | 2016-05-30 | 2019-04-26 | Oppo广东移动通信有限公司 | A kind of solution lock control method and mobile terminal |
| WO2017206686A1 (en) * | 2016-05-30 | 2017-12-07 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method for unlocking terminal and terminal |
| CN106096358A (en) * | 2016-05-30 | 2016-11-09 | 广东欧珀移动通信有限公司 | A kind of solution lock control method and mobile terminal |
| CN106022069A (en) * | 2016-05-30 | 2016-10-12 | 广东欧珀移动通信有限公司 | Unlocking control method and mobile terminal |
| CN106022069B (en) * | 2016-05-30 | 2019-08-20 | Oppo广东移动通信有限公司 | A kind of solution lock control method and mobile terminal |
| CN106055961A (en) * | 2016-05-31 | 2016-10-26 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and mobile terminal |
| CN106055961B (en) * | 2016-05-31 | 2019-02-05 | Oppo广东移动通信有限公司 | A kind of unlocked by fingerprint method and mobile terminal |
| CN106127000A (en) * | 2016-06-17 | 2016-11-16 | 广东欧珀移动通信有限公司 | A kind of unlocked by fingerprint method and terminal |
| CN105912918A (en) * | 2016-06-17 | 2016-08-31 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN105912919A (en) * | 2016-06-17 | 2016-08-31 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN105912918B (en) * | 2016-06-17 | 2019-04-02 | Oppo广东移动通信有限公司 | A kind of unlocked by fingerprint method and terminal |
| CN106022074A (en) * | 2016-06-17 | 2016-10-12 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN107528691A (en) * | 2016-06-21 | 2017-12-29 | 中兴通讯股份有限公司 | Communication security control method and wearable device |
| CN106203151A (en) * | 2016-06-21 | 2016-12-07 | 广东欧珀移动通信有限公司 | A kind of method opening file and terminal unit |
| CN106203151B (en) * | 2016-06-21 | 2019-02-12 | Oppo广东移动通信有限公司 | A kind of method and terminal device for opening file |
| CN106295559B (en) * | 2016-08-08 | 2019-08-02 | 京东方科技集团股份有限公司 | A kind of method of data processing, fingerprint identification device and display device |
| CN106295559A (en) * | 2016-08-08 | 2017-01-04 | 京东方科技集团股份有限公司 | Method, fingerprint identification device and the display device that a kind of data process |
| CN106250876B (en) * | 2016-08-19 | 2019-10-22 | 深圳市金立通信设备有限公司 | A kind of fingerprint identification method and terminal |
| CN106250876A (en) * | 2016-08-19 | 2016-12-21 | 深圳市金立通信设备有限公司 | A kind of fingerprint identification method and terminal |
| CN106778557A (en) * | 2016-11-30 | 2017-05-31 | 努比亚技术有限公司 | Fingerprint identification device and method |
| CN107066852B (en) * | 2016-12-14 | 2021-03-05 | 上海摩软通讯技术有限公司 | Password generation method and password generation device for application |
| CN107066852A (en) * | 2016-12-14 | 2017-08-18 | 上海摩软通讯技术有限公司 | The method for generating cipher code and password generating apparatus of application |
| CN108399374B (en) * | 2017-02-08 | 2023-09-19 | 三星电子株式会社 | Method and apparatus for selecting candidate fingerprint images for fingerprint identification |
| CN108399374A (en) * | 2017-02-08 | 2018-08-14 | 三星电子株式会社 | Method and apparatus of the selection for the candidate fingerprint image of fingerprint recognition |
| CN107111762A (en) * | 2017-03-20 | 2017-08-29 | 深圳市汇顶科技股份有限公司 | Fingerprint identification method and device |
| CN106934389B (en) * | 2017-04-20 | 2019-01-22 | 维沃移动通信有限公司 | A kind of fingerprint identification method and mobile terminal |
| CN106934389A (en) * | 2017-04-20 | 2017-07-07 | 维沃移动通信有限公司 | A kind of fingerprint identification method and mobile terminal |
| CN107358183A (en) * | 2017-06-30 | 2017-11-17 | 广东欧珀移动通信有限公司 | Living iris detection method and Related product |
| US11200437B2 (en) | 2017-06-30 | 2021-12-14 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Method for iris-based living body detection and related products |
| CN107341482B (en) * | 2017-07-13 | 2020-07-10 | 海信视像科技股份有限公司 | Fingerprint identification method and device and computer readable storage medium |
| CN107341482A (en) * | 2017-07-13 | 2017-11-10 | 青岛海信电器股份有限公司 | Fingerprint identification method, device and computer-readable recording medium |
| WO2019075601A1 (en) * | 2017-10-16 | 2019-04-25 | 厦门中控智慧信息技术有限公司 | Palm vein recognition method and device |
| CN108090475A (en) * | 2018-01-17 | 2018-05-29 | 深圳市爱克信智能股份有限公司 | A kind of algorithm for recognizing fingerprint |
| CN108182424B (en) * | 2018-01-29 | 2020-05-22 | 上海天马微电子有限公司 | Display device and fingerprint identification method thereof |
| CN108182424A (en) * | 2018-01-29 | 2018-06-19 | 上海天马微电子有限公司 | Display device and its fingerprint identification method |
| CN108304709A (en) * | 2018-01-31 | 2018-07-20 | 广东欧珀移动通信有限公司 | Face unlocking method and related product |
| CN108304709B (en) * | 2018-01-31 | 2022-01-04 | Oppo广东移动通信有限公司 | Face unlocking method and related product |
| CN109086677A (en) * | 2018-07-09 | 2018-12-25 | 保山市质量技术监督综合检测中心 | A kind of auth method and system based on fingerprint recognition |
| CN113191300A (en) * | 2020-10-14 | 2021-07-30 | 王建华 | Method, apparatus and computer readable medium for fingerprint image recognition |
| CN113191300B (en) * | 2020-10-14 | 2024-01-26 | 神盾股份有限公司 | Method, apparatus and computer readable medium for fingerprint image recognition |
| CN115984948A (en) * | 2023-03-20 | 2023-04-18 | 广东广新信息产业股份有限公司 | Face recognition method applied to temperature sensing and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2017008349A1 (en) | 2017-01-19 |
| CN105608409B (en) | 2019-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105608409A (en) | Method and device for fingerprint identification | |
| EP3916627A1 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| WO2017020447A1 (en) | Fingerprint recognition method and device | |
| WO2011022212A1 (en) | Automatic identification of fingerprint inpainting target areas | |
| CN105303174B (en) | fingerprint input method and device | |
| CN109635625B (en) | Intelligent identity verification method, equipment, storage medium and device | |
| CN110245573B (en) | Sign-in method and device based on face recognition and terminal equipment | |
| CN109690563A (en) | Fingerprint register method, terminal and computer readable storage medium | |
| CN109088788B (en) | Data processing method, device, equipment and computer readable storage medium | |
| CN106649829B (en) | Service processing method and device based on palm print data | |
| WO2018121552A1 (en) | Palmprint data based service processing method, apparatus and program, and medium | |
| US8879805B2 (en) | Automated image identification method | |
| CN111783677A (en) | Face recognition method, face recognition device, server and computer readable medium | |
| EP2148296A1 (en) | Vein pattern management system, vein pattern registration device, vein pattern authentication device, vein pattern registration method, vein pattern authentication method, program, and vein data structure | |
| CN115527241A (en) | Fingerprint template updating method and device, embedded equipment and storage medium | |
| CN110688894A (en) | Palm key point extraction method and device | |
| CN106682627B (en) | Palm print data identification method and device | |
| CN112270218A (en) | Method and system for automatically identifying fingerprint | |
| CN106682623A (en) | Fingerprint information acquisition method and fingerprint acquisition system | |
| CN105139254A (en) | Earprint recognition-based bank remote identity authentication method and system | |
| CN107046561B (en) | Service processing method and device based on palm print data | |
| CN105912663A (en) | User tag merging method based on big data | |
| CN108090430B (en) | Face detection method and device | |
| Misra et al. | A study report on finger print image enhancement methods | |
| CN106846353B (en) | Density-based image processing method, image processing apparatus and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |