CN104484652A - Method for fingerprint recognition - Google Patents
Method for fingerprint recognition Download PDFInfo
- Publication number
- CN104484652A CN104484652A CN201410765993.1A CN201410765993A CN104484652A CN 104484652 A CN104484652 A CN 104484652A CN 201410765993 A CN201410765993 A CN 201410765993A CN 104484652 A CN104484652 A CN 104484652A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- image
- fingerprint image
- carried out
- gray
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
-
- 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
Abstract
The invention discloses a method for fingerprint recognition. The fingerprint recognition comprises the steps of fingerprint image preprocessing, feature extraction and feature matching. The method for footprint recognition overcomes the defects of large amount of labor, low reliability and complex operation process in the prior art, so that the advantages of small amount of labor, high reliability and simple operation process can be achieved.
Description
Technical field
The present invention relates to electronic technology field, particularly, relate to a kind of fingerprint identification method.
Background technology
China takes up the modern work of fingerprint management from the sixties, at present, China generally defines a fingerprint working net, fingerprint theoretical research also achieves important achievement, the application of fingerprint is increasingly extensive, fingerprint recognition receives the concern of more and more people as a kind of biological identification technology of hot topic, and domestic and international many mechanisms and scholar have employed much different algorithms and carry out pre-service and coupling to fingerprint image.But the many factors such as the non-linear deformation that some algorithm can cause due to the noise of fingerprint image, skin elasticity, cause occurring error in identifying, affect discrimination etc., the development of the fingerprint identification technology of China needs to be improved further.
Along with the fast development of modern network, the discriminating for identity becomes more and more important, and we there has also been more and more higher requirement for the certification of identity.The shortcoming of traditional identity discrimination method is that individually defined thing likely can lose, stolen or not band, identify the difficulty existed in memory and the risk be decrypted, intelligent identity identification technology based on fingerprint characteristic identification is also paid close attention to gradually widely, and fingerprint identification technology is the one developing in the world the earliest, the most generally apply at present.According to the ubiquity of fingerprint, uniqueness and permanent biological characteristic, fingerprint identification technology progressively instead of traditional recognition method based on mark and numeral.
Now, fingerprint system stores the information of different fingerprint characteristic, fingerprint comparison can be carried out with the fingerprint that will differentiate with the speed of more than 60,000 time p.s., computing machine in minutes just can provide the similar fingerprint matched, this method greatly reduces the artificial labor capacity differentiated, at present, China defines a comparatively perfect fingerprint working net, but its development does not still have external rapid, because they have carried out studying comparatively reasoningly to fingerprint, thus fingerprint to have more deep abroad, the research of science, in the research of fingerprint identification method, algorithm becomes the key component in system, China strengthens the research of this respect just gradually.
Realizing in process of the present invention, inventor finds at least to exist in prior art the defect such as manual labor amount is large, reliability is low and operating process is complicated.
Summary of the invention
The object of the invention is to, for the problems referred to above, propose a kind of fingerprint identification method, to realize, manual labor amount is little, reliability is high and the simple advantage of operating process.
For achieving the above object, the technical solution used in the present invention is: a kind of fingerprint identification method, comprising:
Fingerprint image preprocessing;
Feature extraction;
Characteristic matching.
Further, the operation of described fingerprint image preprocessing, specifically comprises:
(1) gray processing process is carried out to collection image
Change the fingerprint picture collected into BMP bitmap format, then 256 look colour pictures are converted into grey picture;
(2) Threshold segmentation process is carried out to fingerprint image
The background of digital fingerprint image and foreground segmentation, computer programming is used to obtain fingerprint pattern identification object, from the angle of picture field, the intensity field value of fingerprint object part is higher, and the intensity field value of background parts is lower, the value distribution of fingerprint image intensity field can represent with grey level histogram;
(3) gray balance process is carried out to fingerprint image
The equilibrium of yardstick aspect is fairly simple, corrects carry out mainly through standard; The equilibrium of gray scale aspect is due to sensor difference, and for same fingerprint, the image that sensor gathers also can be different, and some is partially dark, and some is partially bright;
(4) to the smoothing filtering process of fingerprint image
The distortion of fingerprint image intensity field is due to noise, specifically, fingerprint image noise is noisy, shows as under light or electromagnetic irradiation, the photon of reflection fingerprint image arbitrfary point, through the seizure of sensor in the potential well at this some place, finally forms noisy fingerprint grayscale image;
(5) binary conversion treatment is carried out to fingerprint image
Gray level image is changed into the image only having two kinds of color values, namely make the valley line area grayscale being less than threshold value all reach 255 by Global thresholding, make the crestal line area grayscale being greater than threshold value all reach 0;
(6) thinning processing is carried out to fingerprint image
Fingerprint characteristic occurs with unique point form usually, and the streakline width after binaryzation is made up of image through the process of streakline image abstraction more than one pixel.
The fingerprint identification method of various embodiments of the present invention, owing to comprising: fingerprint image preprocessing; Feature extraction; Characteristic matching; Thus the defect that in prior art, manual labor amount is large, reliability is low and operating process is complicated can be overcome, to realize, manual labor amount is little, reliability is high and the simple advantage of operating process.
Other features and advantages of the present invention will be set forth in the following description, and, partly become apparent from instructions, or understand by implementing the present invention.
Below by drawings and Examples, technical scheme of the present invention is described in further detail.
Accompanying drawing explanation
Accompanying drawing is used to provide a further understanding of the present invention, and forms a part for instructions, together with embodiments of the present invention for explaining the present invention, is not construed as limiting the invention.In the accompanying drawings:
Fig. 1 is the FB(flow block) of fingerprint identification method in the present invention.
Embodiment
Below in conjunction with accompanying drawing, the preferred embodiments of the present invention are described, should be appreciated that preferred embodiment described herein is only for instruction and explanation of the present invention, is not intended to limit the present invention.
According to the embodiment of the present invention, as shown in Figure 1, a kind of fingerprint identification method is provided.
In the inventive solutions, fingerprint identification method:
The composition fingerprint recognition of fingerprint identification method is the one of living things feature recognition, there is the general character of all living things feature recognitions, fingerprint identification method in technical scheme of the present invention relates generally to three large steps: fingerprint image preprocessing, feature extraction, characteristic matching three parts, the FB(flow block) of fingerprint identification method as shown in Figure 1.
In the inventive solutions, fingerprint image preprocessing: fingerprint image preprocessing is mainly in order to prepare to the extraction of fingerprint below.The pre-service of image roughly can be divided into the following steps: gray processing, Threshold segmentation, gray balance, smothing filtering, binaryzation and refinement.
3.1 pairs gather image and carry out gray processing process
In this experiment, I first changes the fingerprint picture collected into BMP bitmap format, then 256 look colour pictures is converted into grey picture.The feature of BMP file forms image pixel matrix in units of the data of every pixel, and the length and width of this image pixel matrix, the brightness of unit picture element data and color length can define in the composition format header file of BMP file.
3.2 pairs of fingerprint images carry out Threshold segmentation process
The background of digital fingerprint image and foreground segmentation, computer programming is used to obtain fingerprint pattern identification object, from the angle of picture field, the intensity field value of fingerprint object part is higher, and the intensity field value of background parts is lower, the value distribution of fingerprint image intensity field can represent with grey level histogram.
3.3 pairs of fingerprint images carry out gray balance process
Fingerprint image equilibrium can be described from gray scale and yardstick two aspects.The equilibrium of yardstick aspect is fairly simple, corrects carry out mainly through standard.The equilibrium of gray scale aspect is due to sensor difference, and for same fingerprint, the image that sensor gathers also can be different, and some is partially dark, and some is partially bright, at this moment, just needs to revise image, makes their balanced normalizings, allow them in same brightness.
3.4 pairs of smoothing filtering process of fingerprint image
The distortion of fingerprint image intensity field is due to noise, specifically, fingerprint image noise is noisy, show as under the irradiation of light (or electromagnetic wave), the photon of reflection fingerprint image arbitrfary point is through the seizure of sensor in the potential well at this some place, because surrounding environment dust, sensor surface spot, extraneous wigwag, circuit undesired signal etc. can superpose thereon, the fingerprint grayscale image that final formation is noisy.
The noise that computing machine is thought is exactly the pixel grey scale of crestal line or valley line, after fingerprint image smoothing processing, noise quilt " removal ", the multiple noises on fingerprint image are noisy, can regard the simple addition of single noise spot as.
3.5 pairs of fingerprint images carry out binary conversion treatment
Fingerprint Image Binarization defines: gray level image is changed into the image only having two kinds of color values, namely the valley line area grayscale being less than threshold value is made all to reach 255 by Global thresholding, make the crestal line area grayscale being greater than threshold value all reach 0, fingerprint ridge object can be made by this method to become the image of black and white two kinds of colors.
From the angle of picture field, the some intensity field value on streakline is higher, and some intensity field value in background is lower, so the method for general binaryzation establishes a threshold value, is greater than being set to of threshold value white, is less than being set to of threshold value black, also passable conversely.
The algorithm of Fingerprint Image Binarization has weighted mean value-based algorithm and overall Binarization methods, in actual operation, owing to considering error component, generally have employed average weighted method to reduce error.But in this design, the method that I adopts is the algorithm of overall binaryzation, namely the threshold value A of an overall binaryzation is set, when fingerprint pixel is greater than threshold value A, then pixel is set to 0, when fingerprint pixel is less than threshold value A, then pixel is set to 255, the threshold value A that I adopts in the inventive solutions is 125.
3.6 pairs of fingerprint images carry out thinning processing
Fingerprint characteristic occurs with unique point form usually, and the streakline width after binaryzation is made up of more than one pixel, is therefore difficult to set up the unique point model that width only has a point, so must to image through the process of streakline image abstraction.
In the inventive solutions: print image feature extraction, mark and mate
What adopt in the inventive solutions is exactly the method for extract minutiae from the picture after refinement, this method extracts feature from the image after process, this method is fairly simple relative to first method, and we can be extracted the end points that we want and bifurcation by the template of 3 × 3.
Technical scheme of the present invention is from by extracting finger print image, the pre-service such as intensity slicing, image filtering, binaryzation, refinement are carried out to the fingerprint image extracted, then finger print image is clearly obtained, take the fingerprint unique point (minutiae point) again from finger print image clearly, stored in template of filing.When fingerprint comparison, adopting uses the same method obtains fingerprint image clearly, sets up comparison template, finally by comparison template with set up template and utilize minutiae point Vectors matching algorithm to compare, draw desirable result.
Last it is noted that the foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, although with reference to previous embodiment to invention has been detailed description, for a person skilled in the art, it still can be modified to the technical scheme described in foregoing embodiments, or carries out equivalent replacement to wherein portion of techniques feature.Within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (2)
1. a fingerprint identification method, is characterized in that, comprising:
Fingerprint image preprocessing;
Feature extraction;
Characteristic matching.
2. fingerprint identification method according to claim 1, is characterized in that, the operation of described fingerprint image preprocessing, specifically comprises:
(1) gray processing process is carried out to collection image
Change the fingerprint picture collected into BMP bitmap format, then 256 look colour pictures are converted into grey picture;
(2) Threshold segmentation process is carried out to fingerprint image
The background of digital fingerprint image and foreground segmentation, computer programming is used to obtain fingerprint pattern identification object, from the angle of picture field, the intensity field value of fingerprint object part is higher, and the intensity field value of background parts is lower, the value distribution of fingerprint image intensity field can represent with grey level histogram;
(3) gray balance process is carried out to fingerprint image
The equilibrium of yardstick aspect is fairly simple, corrects carry out mainly through standard; The equilibrium of gray scale aspect is due to sensor difference, and for same fingerprint, the image that sensor gathers also can be different, and some is partially dark, and some is partially bright;
(4) to the smoothing filtering process of fingerprint image
The distortion of fingerprint image intensity field is due to noise, specifically, fingerprint image noise is noisy, shows as under light or electromagnetic irradiation, the photon of reflection fingerprint image arbitrfary point, through the seizure of sensor in the potential well at this some place, finally forms noisy fingerprint grayscale image;
(5) binary conversion treatment is carried out to fingerprint image
Gray level image is changed into the image only having two kinds of color values, namely make the valley line area grayscale being less than threshold value all reach 255 by Global thresholding, make the crestal line area grayscale being greater than threshold value all reach 0;
(6) thinning processing is carried out to fingerprint image
Fingerprint characteristic occurs with unique point form usually, and the streakline width after binaryzation is made up of image through the process of streakline image abstraction more than one pixel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410765993.1A CN104484652A (en) | 2014-12-15 | 2014-12-15 | Method for fingerprint recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410765993.1A CN104484652A (en) | 2014-12-15 | 2014-12-15 | Method for fingerprint recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104484652A true CN104484652A (en) | 2015-04-01 |
Family
ID=52759193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410765993.1A Pending CN104484652A (en) | 2014-12-15 | 2014-12-15 | Method for fingerprint recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104484652A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105718851A (en) * | 2015-10-30 | 2016-06-29 | 深圳芯启航科技有限公司 | Fingerprint image filtering method and apparatus applied to fingerprint sensor |
| CN106022047A (en) * | 2016-05-24 | 2016-10-12 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN106529961A (en) * | 2016-11-07 | 2017-03-22 | 郑州游爱网络技术有限公司 | Bank fingerprint payment processing method |
| CN106649829A (en) * | 2016-12-29 | 2017-05-10 | 北京奇虎科技有限公司 | Method and device for processing business based on palmprint data |
| CN108121940A (en) * | 2016-11-29 | 2018-06-05 | 深圳指芯智能科技有限公司 | A kind of method and apparatus of fingerprint image analysis |
| CN108596060A (en) * | 2018-04-12 | 2018-09-28 | 上海思立微电子科技有限公司 | Fingerprint image processing method, fingerprint identification device and electronic equipment |
| CN109118240A (en) * | 2018-08-19 | 2019-01-01 | 吴伟锋 | Subway scene fee payment method |
| CN109784195A (en) * | 2018-12-20 | 2019-05-21 | 金菁 | A kind of fingerprint identification method checked card for enterprise's fingerprint and system |
| CN109858418A (en) * | 2019-01-23 | 2019-06-07 | 上海思立微电子科技有限公司 | The treating method and apparatus of fingerprint image |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6567765B1 (en) * | 2000-08-17 | 2003-05-20 | Siemens Corporate Research, Inc. | Evaluation system and method for fingerprint verification |
| CN101004788A (en) * | 2006-01-17 | 2007-07-25 | 公安部第一研究所 | System and method of evaluating algorithm for recognizing fingerprint on certificate |
-
2014
- 2014-12-15 CN CN201410765993.1A patent/CN104484652A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6567765B1 (en) * | 2000-08-17 | 2003-05-20 | Siemens Corporate Research, Inc. | Evaluation system and method for fingerprint verification |
| CN101004788A (en) * | 2006-01-17 | 2007-07-25 | 公安部第一研究所 | System and method of evaluating algorithm for recognizing fingerprint on certificate |
Non-Patent Citations (1)
| Title |
|---|
| 邹军: "《自动指纹识别算法分析与设计》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105718851A (en) * | 2015-10-30 | 2016-06-29 | 深圳芯启航科技有限公司 | Fingerprint image filtering method and apparatus applied to fingerprint sensor |
| CN107622235B (en) * | 2016-05-24 | 2021-01-12 | Oppo广东移动通信有限公司 | Fingerprint unlocking method and related product |
| CN106022047A (en) * | 2016-05-24 | 2016-10-12 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
| CN106022047B (en) * | 2016-05-24 | 2017-10-24 | 广东欧珀移动通信有限公司 | A kind of unlocked by fingerprint method and terminal |
| CN107622235A (en) * | 2016-05-24 | 2018-01-23 | 广东欧珀移动通信有限公司 | Unlocked by fingerprint method and Related product |
| CN106529961A (en) * | 2016-11-07 | 2017-03-22 | 郑州游爱网络技术有限公司 | Bank fingerprint payment processing method |
| CN108121940A (en) * | 2016-11-29 | 2018-06-05 | 深圳指芯智能科技有限公司 | A kind of method and apparatus of fingerprint image analysis |
| CN106649829A (en) * | 2016-12-29 | 2017-05-10 | 北京奇虎科技有限公司 | Method and device for processing business based on palmprint data |
| CN108596060A (en) * | 2018-04-12 | 2018-09-28 | 上海思立微电子科技有限公司 | Fingerprint image processing method, fingerprint identification device and electronic equipment |
| CN108596060B (en) * | 2018-04-12 | 2021-10-15 | 上海思立微电子科技有限公司 | Fingerprint image processing method, fingerprint identification device and electronic equipment |
| CN109118240A (en) * | 2018-08-19 | 2019-01-01 | 吴伟锋 | Subway scene fee payment method |
| CN109118240B (en) * | 2018-08-19 | 2020-10-09 | 平湖市超凯科技有限公司 | Instant payment system based on fingerprint acquisition |
| CN109784195A (en) * | 2018-12-20 | 2019-05-21 | 金菁 | A kind of fingerprint identification method checked card for enterprise's fingerprint and system |
| CN109858418A (en) * | 2019-01-23 | 2019-06-07 | 上海思立微电子科技有限公司 | The treating method and apparatus of fingerprint image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104484652A (en) | Method for fingerprint recognition | |
| CN107578035B (en) | Human body contour extraction method based on super-pixel-multi-color space | |
| EP3455782B1 (en) | System and method for detecting plant diseases | |
| CN106874871B (en) | Living body face double-camera identification method and identification device | |
| Guan et al. | Accurate segmentation of partially overlapping cervical cells based on dynamic sparse contour searching and GVF snake model | |
| Konwar et al. | An American sign language detection system using HSV color model and edge detection | |
| CN110309806B (en) | Gesture recognition system and method based on video image processing | |
| CN107256543B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN106096491B (en) | Automatic identification method for microaneurysms in fundus color photographic image | |
| CN104408780A (en) | Face recognition attendance system | |
| CN108830857B (en) | Self-adaptive Chinese character copy label image binarization segmentation method | |
| WenJuan et al. | A real-time lip localization and tacking for lip reading | |
| CN111079688A (en) | Living body detection method based on infrared image in face recognition | |
| CN110598574A (en) | Intelligent face monitoring and identifying method and system | |
| CN104102907A (en) | LBP (Local Binary Pattern) face recognition method for eliminating illumination evenness | |
| Shah et al. | An iterative approach for shadow removal in document images | |
| CN107633251A (en) | A kind of vehicle identification system based on image enhaucament | |
| CN108154116A (en) | A kind of image-recognizing method and system | |
| CN105528795B (en) | A kind of infrared face dividing method using annular shortest path | |
| CN204347865U (en) | A kind of finger vein recognition terminal of banking system | |
| CN106446904A (en) | Image recognition method based on global binarization | |
| Liang et al. | Applying Image Processing Technology to Face Recognition. | |
| Prasad et al. | Unsupervised resolution independent based natural plant leaf disease segmentation approach for mobile devices | |
| Zhou et al. | Medical diagnosis algorithm based on tongue image on mobile device | |
| Subramani et al. | A novel binarization method for degraded tamil palm leaf images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150401 |
|
| RJ01 | Rejection of invention patent application after publication |