CN106778451A - A kind of eyeglass detection method of face recognition - Google Patents
A kind of eyeglass detection method of face recognition Download PDFInfo
- Publication number
- CN106778451A CN106778451A CN201510828960.1A CN201510828960A CN106778451A CN 106778451 A CN106778451 A CN 106778451A CN 201510828960 A CN201510828960 A CN 201510828960A CN 106778451 A CN106778451 A CN 106778451A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- normalization
- glasses
- measured
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (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)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of eyeglass detection method of face recognition.Face datection is carried out to facial image to be measured, to obtain human face region image, glasses positioning is carried out to the human face region image, and operation is normalized to the human face region image according to the eye positions, to obtain the target image of preliminary dimension size, lens area image is classified using feature classifiers, whether obtains facial image to be measured to the testing result that there should be glasses.
Description
Technical field
The invention belongs to Biometrics field, and in particular to a kind of Glasses detection of face recognition
Method.
Background technology
Because most people all wears glasses, by detect in facial image whether wearing spectacles,
And the location and shape of glasses are calculated, to improving face recognition algorithms performance, human face segmentation, people
Face cartoon etc. is with important practical value.For example, in recognition of face, if in wearing spectacles
Face in detect the position of glasses, you can the naked face of no glasses is obtained by removing glasses.
The content of the invention
A kind of glasses of face recognition are provided it is an object of the invention to solve above-mentioned technical problem
Detection method.
A kind of eyeglass detection method of face recognition, comprises the following steps:
Step 1, obtains lens area image from facial image to be measured;
In an optional implementation method, obtain lens area image the step of can include:
Face datection is carried out to facial image to be measured, to obtain human face region image;
Glasses positioning is carried out to the human face region image, and according to the eye positions to the people
Face area image is normalized operation, to obtain the target image of preliminary dimension size.
In a particular application, normalization operation can include size normalization and gray scale normalization behaviour
Make, wherein, gray scale normalization operation can be taken carries out gray scale drawing to the image after size normalization
Stretch, to improve the contrast of image;Or, image is made using correction techniques such as histogram equalizations
With average and variance in close statistical significance, to partially remove the influence of illumination, the present invention
Pair it is not any limitation as with the concrete mode of normalization operation.
Above-mentioned implementation method is only a kind of optional implementation method, can also be obtained using other modes
To lens area image.No matter which kind of mode is identical effect can be obtained using.
Step 2, is classified using feature classifiers to lens area image, obtains face to be measured
Whether image is to the testing result that should have glasses.
Embodiment of the present invention detection method can apply to human face segmentation, human face cartoon, recognition of face
With face characteristic find etc. occasion, by determine facial image to be measured face whether wearing spectacles,
Further step is taken with according to testing result, for example, if it find that the face wearing spectacles,
The naked face of no glasses can be then obtained by removing glasses.
Specific embodiment
Below, substantive distinguishing features of the invention and advantage are further described with reference to example, but
The invention is not limited in listed embodiment.
In order to illustrate technical solutions according to the invention, said below by specific embodiment
It is bright.
A kind of eyeglass detection method of face recognition, comprises the following steps:
Step 1, obtains lens area image from facial image to be measured;
In an optional implementation method, obtain lens area image the step of can include:
Face datection is carried out to facial image to be measured, to obtain human face region image;
Glasses positioning is carried out to the human face region image, and according to the eye positions to the people
Face area image is normalized operation, to obtain the target image of preliminary dimension size.
In a particular application, normalization operation can include size normalization and gray scale normalization behaviour
Make, wherein, gray scale normalization operation can be taken carries out gray scale drawing to the image after size normalization
Stretch, to improve the contrast of image;Or, image is made using correction techniques such as histogram equalizations
With average and variance in close statistical significance, to partially remove the influence of illumination, the present invention
Pair it is not any limitation as with the concrete mode of normalization operation.
Above-mentioned implementation method is only a kind of optional implementation method, can also be obtained using other modes
To lens area image.No matter which kind of mode is identical effect can be obtained using.
Step 2, is classified using feature classifiers to lens area image, obtains face to be measured
Whether image is to the testing result that should have glasses.
Embodiment of the present invention detection method can apply to human face segmentation, human face cartoon, recognition of face
With face characteristic find etc. occasion, by determine facial image to be measured face whether wearing spectacles,
Further step is taken with according to testing result, for example, if it find that the face wearing spectacles,
The naked face of no glasses can be then obtained by removing glasses.
The above is only the preferred embodiment of the present invention, it is noted that for the art
Those of ordinary skill for, under the premise without departing from the principles of the invention, can also make some
Improvements and modifications, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (1)
1. a kind of eyeglass detection method of face recognition, comprises the following steps:
Step 1, obtains lens area image from facial image to be measured;
In an optional implementation method, obtain lens area image the step of can include:
Face datection is carried out to facial image to be measured, to obtain human face region image;
Glasses positioning is carried out to the human face region image, and according to the eye positions to the people
Face area image is normalized operation, to obtain the target image of preliminary dimension size.
In a particular application, normalization operation can include size normalization and gray scale normalization behaviour
Make, wherein, gray scale normalization operation can be taken carries out gray scale drawing to the image after size normalization
Stretch, to improve the contrast of image;Or, image is made using correction techniques such as histogram equalizations
With average and variance in close statistical significance, to partially remove the influence of illumination, the present invention
Pair it is not any limitation as with the concrete mode of normalization operation.
Above-mentioned implementation method is only a kind of optional implementation method, can also be obtained using other modes
To lens area image.No matter which kind of mode is identical effect can be obtained using.
Step 2, is classified using feature classifiers to lens area image, obtains face to be measured
Whether image is to the testing result that should have glasses.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510828960.1A CN106778451A (en) | 2015-11-20 | 2015-11-20 | A kind of eyeglass detection method of face recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510828960.1A CN106778451A (en) | 2015-11-20 | 2015-11-20 | A kind of eyeglass detection method of face recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106778451A true CN106778451A (en) | 2017-05-31 |
Family
ID=58964312
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510828960.1A Pending CN106778451A (en) | 2015-11-20 | 2015-11-20 | A kind of eyeglass detection method of face recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106778451A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107808120A (en) * | 2017-09-30 | 2018-03-16 | 平安科技(深圳)有限公司 | Glasses localization method, device and storage medium |
US11270100B2 (en) | 2017-11-14 | 2022-03-08 | Huawei Technologies Co., Ltd. | Face image detection method and terminal device |
-
2015
- 2015-11-20 CN CN201510828960.1A patent/CN106778451A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107808120A (en) * | 2017-09-30 | 2018-03-16 | 平安科技(深圳)有限公司 | Glasses localization method, device and storage medium |
US11270100B2 (en) | 2017-11-14 | 2022-03-08 | Huawei Technologies Co., Ltd. | Face image detection method and terminal device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
NZ741863A (en) | Eye pose identification using eye features | |
Ross et al. | Segmenting non-ideal irises using geodesic active contours | |
CN109145742B (en) | Pedestrian identification method and system | |
CN102867179A (en) | Method for detecting acquisition quality of digital certificate photo | |
TWI603293B (en) | Method and apparatus for detecting blink | |
CN103793693A (en) | Method for detecting face turning and facial form optimizing method with method for detecting face turning | |
CN101615241B (en) | Method for screening certificate photos | |
CN104156700A (en) | Face image glass removal method based on mobile shape model and weighted interpolation method | |
CN106097368A (en) | A kind of recognition methods in veneer crack | |
KR20160037305A (en) | Method for User Authentication using Fingerprint Recognition | |
US20160171323A1 (en) | Apparatus for recognizing iris and operating method thereof | |
WenJuan et al. | A real-time lip localization and tacking for lip reading | |
CN115223211B (en) | Identification method for converting vein image into fingerprint image | |
CN106778451A (en) | A kind of eyeglass detection method of face recognition | |
KR20160036375A (en) | Fast Eye Detection Method Using Block Contrast and Symmetry in Mobile Device | |
CN105844727A (en) | Intelligent dynamic human face recognition attendance checking record management system | |
CN104102907A (en) | LBP (Local Binary Pattern) face recognition method for eliminating illumination evenness | |
CN105404854A (en) | Methods and devices for obtaining frontal human face images | |
CN105631285A (en) | Biological feature identity recognition method and apparatus | |
Jarjes et al. | Iris localization: Detecting accurate pupil contour and localizing limbus boundary | |
Rossant et al. | Iris identification and robustness evaluation of a wavelet packets based algorithm | |
CN109409223A (en) | A kind of iris locating method | |
WO2016004706A1 (en) | Method for improving iris recognition performance in non-ideal environment | |
JP2013195577A5 (en) | ||
CN106909880A (en) | Facial image preprocess method in recognition of face |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170531 |
|
WD01 | Invention patent application deemed withdrawn after publication |