CN101324920B - Method for searching human face remarkable characteristic and human face comparison method - Google Patents
Method for searching human face remarkable characteristic and human face comparison method Download PDFInfo
- Publication number
- CN101324920B CN101324920B CN2007100421706A CN200710042170A CN101324920B CN 101324920 B CN101324920 B CN 101324920B CN 2007100421706 A CN2007100421706 A CN 2007100421706A CN 200710042170 A CN200710042170 A CN 200710042170A CN 101324920 B CN101324920 B CN 101324920B
- Authority
- CN
- China
- Prior art keywords
- face
- people
- search
- remarkable characteristic
- compared
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to a method for searching marked human facial features and a method for comparing human faces. Gray difference exists between obvious features such as moles, color mottles, birth marks, etc., on a human face and the color of surrounding skin, so that a human face to be searched is firstly converted into a gray-scale map so as to form a human face gray-scale image when the obvious features are searched. The human face gray-scale map is divided into a plurality of searching sub-areas to improve the searching precision; average gray-level of each searching sub-area is recorded; each searching sub-area is searched; the image gray-scale of each searching point is calculated; and the calculated image gray-scale for each time and the average gray-scale of corresponding searching sub-area are compared to determine whether the corresponding searching point is the obvious feature of the human face. Therefore, the obvious features can be effectively searched. In addition, the comparison range can be reduced based on whether the human face has obvious feature during the process of comparison, thereby greatly improving the comparison speed and precision.
Description
Technical field
The present invention relates to a kind of method and people's face comparison method of seeker's face remarkable characteristic.
Background technology
In face recognition technology, normally people's face of people's face to be identified and face database stored is compared to identify the identity of described people's face to be identified, but because people's face of face database storage is numerous, and the data that each people's face comprises are bigger, cause the speed and the precision of the comparison of people's face all more restricted.
Yet, many people have black mole on the face, and black mole is not subjected to the influence of factors such as age, attitude, expression, simultaneously from people's angle of cognition, features such as black mole also allow the people accept than being easier in real life, how this feature application have been become the technical task that those skilled in the art need to be resolved hurrily in fact in the portrait comparison.
Summary of the invention
The object of the present invention is to provide a kind of method of seeker's face remarkable characteristic, can effectively search out the remarkable characteristic that has on the facial image.
Another object of the present invention is to people's face comparison method, to improve comparison speed and comparison accuracy based on people's face remarkable characteristic.
In order to achieve the above object, the method for seeker's face remarkable characteristic provided by the invention comprises step: 1) facial image to be searched is converted to gray-scale map to form people's face gray level image; 2) described people's face gray level image is divided into a plurality of search subarea, and the average gray in subarea respectively searched in record; 3) according to described a plurality of search subarea setting search order, each search size and search spacing; 4) search in described a plurality of search subarea respectively successively according to the search order of setting, each search size and search spacing, calculate the gradation of image in each search range of size, and the gradation of image that will at every turn calculate and the average gray in corresponding search subarea compare with judge corresponding each whether search for be people's face remarkable characteristic.
Wherein, described step 1) also comprises carries out normalized with described people's face gray level image, described a plurality of search subarea is respectively: left cheek subarea, right cheek subarea, chin subarea, forehead half son district, a left side and half son district, the forehead right side, described remarkable characteristic is a kind of in black mole, color spot and the birthmark.
In addition, the people's face comparison method based on people's face remarkable characteristic of the present invention comprises step: 1) people's face to be compared is searched for to judge whether described people's face to be compared has remarkable characteristic according to the method for the arbitrary described seeker's face remarkable characteristic of claim 1 to 4; 2) if people's face to be compared has remarkable characteristic, then write down the position at described remarkable characteristic place; 3) described people's face to be compared with remarkable characteristic and the people's face with remarkable characteristic in the face database are compared whether identical with the position of identification remarkable characteristic, and then to discern described people's face to be compared; 4) if described people's face to be compared does not have remarkable characteristic, then the people's face that does not have remarkable characteristic in described people's face to be compared and the described face database is compared to discern described people's face to be compared.
In sum, the method of seeker's face remarkable characteristic of the present invention and people's face comparison method are according to the gray scale difference of remarkable characteristic and surrounding skin existence, the remarkable characteristic that can effectively people's face be had is searched for out, simultaneously whether having remarkable characteristic according to people's face can dwindle the comparison scope, so comparison speed can be improved, comparison accuracy can be improved again.
Description of drawings
Fig. 1 is the operating process synoptic diagram of the method for seeker's face remarkable characteristic of the present invention.
Embodiment
See also Fig. 1, the method for seeker's face remarkable characteristic of the present invention may further comprise the steps at least:
S10: facial image to be searched is converted to gray-scale map to form people's face gray level image, the principle of conversion and method is known to those skilled in the art knows, do not repeat them here, it is convenient to be generally search, generally also described people's face gray level image being carried out normalized makes size of images size normalizing become 64 * 68, correspondingly do some pre-service again, make the face of image comparatively clear.
S11: described people's face gray level image is divided into a plurality of search subarea, and the average gray in subarea respectively searched in record, usually described people's face gray level image is divided into left cheek subarea, right cheek subarea, chin subarea, forehead half son district, a left side and the right half son of forehead district, so can effectively avoid of the interference of zones such as eyebrow, eyes, nostril, face to search, average gray can calculate according to each gray scale of searching for the image pixel that the subarea comprises, and is not going to repeat.
S12: according to described a plurality of search subarea setting search order, each search size and search spacing, for example, setting search is in proper order: half son district, a forehead left side, the right half son of forehead district, cheek subarea, a left side, right cheek subarea and chin subarea, set each search size to be the circle that is radius with 3 pixels, the search spacing also is 3 pixels, it is noted that in addition, when each search subarea is searched for, usually from the first trip of image first, when searching in left cheek subarea, also first begins etc. from the first trip of image, certainly those skilled in the art also can set different search orders according to actual conditions, search size and search spacing, for example, setting search circle that to be of a size of with 2 pixels be radius etc.
S13: according to the search order of setting, each search size and search spacing are searched in described a plurality of search subarea respectively successively, calculate the gradation of image in each search range of size, and the gradation of image that will at every turn calculate compares to judge whether corresponding each search point is people's face remarkable characteristic with the average gray in corresponding search subarea, for example, when half son zone, a forehead left side is searched for, earlier with its first trip first column contains search starting point, calculating this starting point earlier is the gradation of image in the circle zone of radius with 3 pixels, and the average gray in half son zone, this a gradation of image and described forehead left side compared, as differ less then this search starting point and do not have remarkable characteristic, promptly there is not black mole, color spot or birthmark etc., 3 pixels of search point right translation are as second search point then, and calculating radius this moment is the gradation of image in the circle zone of 3 pixels, and the average gray in half son zone, itself an and described forehead left side compared, if both differ bigger, then has remarkable characteristic in second search point zone, usually remarkable characteristic is a black mole, so progressively search, after the search of finishing half son zone, a forehead left side, can enter the right half son of forehead zone successively, cheek subarea, a left side, right cheek subarea, whether the search in chin subarea also has remarkable characteristic to search out corresponding subarea.
In sum, the method of seeker's face remarkable characteristic of the present invention has black mole, color spot or birthmark according to some faces can have gray scale difference with the color of surrounding skin, and black mole, color spot or the birthmark that can effectively people's face be had is that remarkable characteristic is searched for out.
In addition, the people's face comparison method based on people's face remarkable characteristic of the present invention mainly may further comprise the steps:
The first step: search for to judge whether described ground to be compared people's face has remarkable characteristic, and searching method is similar to the method for aforesaid seeker's face remarkable characteristic, no longer repeats at this at people's face to be compared.
Second step: if people's face to be compared has remarkable characteristic, then write down the position at described remarkable characteristic place, for example,, described position is given record if searching out remarkable characteristic is that center radius is in the zone of 3 pixels at left cheek with the 6th pixel.
The 3rd step: compare with the position of identification remarkable characteristic whether identical with the people's face in the face database described people's face to be compared with remarkable characteristic with remarkable characteristic, and then to discern described people's face to be compared, it is noted that, even a certain people's face that identifies in people's face to be compared and the face database has identical remarkable characteristic, still need other information (eyes for example to people's face, information such as eyebrow) compare and just can identify described people's face to be compared, because other information of people's face are compared are familiar with, so no longer describe in detail by those skilled in the art.
The 4th step:, then the people's face that does not have remarkable characteristic in described people's face to be compared and the described face database is compared to discern described people's face to be compared if described people's face to be compared does not have remarkable characteristic.
In sum, whether the people's face comparison method based on people's face remarkable characteristic of the present invention has remarkable characteristic according to people's face to be compared can be divided into two comparison, promptly having people's face of remarkable characteristic and the people's face with remarkable characteristic in the face database compares, not having people's face of remarkable characteristic and the people's face that does not have remarkable characteristic in the face database compares, so both comparison speed can be improved, comparison accuracy can be improved again.
Claims (5)
1. the method for seeker's face remarkable characteristic is characterized in that comprising step:
1) facial image to be searched is converted to gray-scale map to form people's face gray level image;
2) described people's face gray level image is divided into a plurality of search subarea, and the average gray in subarea respectively searched in record;
3) according to described a plurality of search subarea setting search order, each search size and search spacing;
4) search in described a plurality of search subarea respectively successively according to the search order of setting, each search size and search spacing, calculate the gradation of image in each search range of size, and the gradation of image that will at every turn calculate and the average gray in corresponding search subarea compare with judge corresponding each whether search for be people's face remarkable characteristic.
2. the method for seeker's face remarkable characteristic as claimed in claim 1, it is characterized in that described step 1) also comprises carries out normalized with described people's face gray level image.
3. the method for seeker's face remarkable characteristic as claimed in claim 1 is characterized in that described a plurality of search subarea is respectively: left cheek subarea, right cheek subarea, chin subarea, forehead half son district, a left side and the right half son of forehead district.
4. the method for seeker's face remarkable characteristic as claimed in claim 1 is characterized in that: described remarkable characteristic is a kind of in black mole, color spot and the birthmark.
5. people's face comparison method based on people's face remarkable characteristic is characterized in that comprising step:
1) people's face to be compared is searched for to judge whether described people's face to be compared has remarkable characteristic according to the method for the arbitrary described seeker's face remarkable characteristic of claim 1 to 4;
2) if people's face to be compared has remarkable characteristic, then write down the position at described remarkable characteristic place;
3) described people's face to be compared with remarkable characteristic and the people's face with remarkable characteristic in the face database are compared whether identical with the position of identification remarkable characteristic, and then to discern described people's face to be compared;
4) if described people's face to be compared does not have remarkable characteristic, then the people's face that does not have remarkable characteristic in described people's face to be compared and the described face database is compared to discern described people's face to be compared.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2007100421706A CN101324920B (en) | 2007-06-15 | 2007-06-15 | Method for searching human face remarkable characteristic and human face comparison method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2007100421706A CN101324920B (en) | 2007-06-15 | 2007-06-15 | Method for searching human face remarkable characteristic and human face comparison method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101324920A CN101324920A (en) | 2008-12-17 |
| CN101324920B true CN101324920B (en) | 2011-06-15 |
Family
ID=40188457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2007100421706A Expired - Fee Related CN101324920B (en) | 2007-06-15 | 2007-06-15 | Method for searching human face remarkable characteristic and human face comparison method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101324920B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101964064B (en) * | 2010-07-27 | 2013-06-19 | 上海摩比源软件技术有限公司 | Human face comparison method |
| CN103049746B (en) * | 2012-12-30 | 2015-07-29 | 信帧电子技术（北京）有限公司 | Detection based on face recognition is fought the method for behavior |
| CN103353942A (en) * | 2013-07-30 | 2013-10-16 | 上海电机学院 | Interactive face identification system and method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1215618A2 (en) * | 2000-12-14 | 2002-06-19 | Eastman Kodak Company | Image processing method for detecting human figures in a digital image |
| EP1452995A2 (en) * | 2003-02-28 | 2004-09-01 | Eastman Kodak Company | Method for detecting color objects in digital images |
| CN1584916A (en) * | 2004-06-11 | 2005-02-23 | 清华大学 | Attribute normalizing method for human face image collecting apparatus |
-
2007
- 2007-06-15 CN CN2007100421706A patent/CN101324920B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1215618A2 (en) * | 2000-12-14 | 2002-06-19 | Eastman Kodak Company | Image processing method for detecting human figures in a digital image |
| EP1452995A2 (en) * | 2003-02-28 | 2004-09-01 | Eastman Kodak Company | Method for detecting color objects in digital images |
| CN1584916A (en) * | 2004-06-11 | 2005-02-23 | 清华大学 | Attribute normalizing method for human face image collecting apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101324920A (en) | 2008-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7869626B2 (en) | Iris recognition method and apparatus thereof | |
| Husken et al. | Strategies and benefits of fusion of 2D and 3D face recognition | |
| US9208375B2 (en) | Face recognition mechanism | |
| US9489561B2 (en) | Method and system for estimating fingerprint pose | |
| JP6212099B2 (en) | Image template masking | |
| US8749658B2 (en) | Data processing device, image matching method, program, and image matching system | |
| US20210334998A1 (en) | Image processing method, apparatus, device and medium for locating center of target object region | |
| CN111563512B (en) | Method and device for automatically smearing answers, electronic equipment and storage medium | |
| CN108108734B (en) | License plate recognition method and device | |
| EP1374144A1 (en) | Non-contact type human iris recognition method by correction of rotated iris image | |
| CN101901336A (en) | Fingerprint and finger vein bimodal recognition decision level fusion method | |
| CN102779275A (en) | Paper characteristic identification method and relative device | |
| US8090151B2 (en) | Face feature point detection apparatus and method of the same | |
| US10846568B2 (en) | Deep learning-based automatic gesture recognition method and system | |
| CN104680154B (en) | A kind of personal identification method merged based on face characteristic and palm print characteristics | |
| CN110458158A (en) | A kind of text detection and recognition methods for blind person's aid reading | |
| CN101324920B (en) | Method for searching human face remarkable characteristic and human face comparison method | |
| Ratyal et al. | 3D face recognition based on pose and expression invariant alignment | |
| CN110427826B (en) | Palm recognition method and device, electronic equipment and storage medium | |
| Bakshi et al. | Optimized periocular template selection for human recognition | |
| JP2013218605A (en) | Image recognition device, image recognition method, and program | |
| KR101396713B1 (en) | Apparatus for recognizing medicine using image technique | |
| CN117636442A (en) | Attendance checking method, system, equipment and storage medium based on multi-feature face recognition | |
| KR20070088982A (en) | Deformation-resilient iris recognition methods | |
| Peng et al. | A robust and efficient algorithm for eye detection on gray intensity face |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20110615 Termination date: 20170615 |