CN103093210A - Method and device for glasses identification in face identification - Google Patents
Method and device for glasses identification in face identification Download PDFInfo
- Publication number
- CN103093210A CN103093210A CN2013100277518A CN201310027751A CN103093210A CN 103093210 A CN103093210 A CN 103093210A CN 2013100277518 A CN2013100277518 A CN 2013100277518A CN 201310027751 A CN201310027751 A CN 201310027751A CN 103093210 A CN103093210 A CN 103093210A
- Authority
- CN
- China
- Prior art keywords
- predeterminable area
- glasses
- predetermined threshold
- threshold value
- pixel
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a method and a device for glasses identification in face identification. The method comprises the steps: obtaining a facial image, and clipping a first preset area in the obtained facial image, wherein a covered range of the first preset area comprises a human eye area and a part or all area covered by a pair of glasses; and judging types of the pair of the glasses according to the first preset area. According to the technical scheme of the method and the device for the glasses identification in the face identification, facial images with the pair of glasses and reflective can be accurately judged out. Through the method and the device for the glasses identification in the face identification, states of eyes in the human eye locating process of the face identification are classified, different methods are adopted to locate human eyes in different situations, and therefore speed and accuracy of human eye locating are improved.
Description
Technical field
The present invention relates to that image is processed and area of pattern recognition, discrimination method and the device of glasses in a kind of recognition of face.
Background technology
In the epoch of current information-based develop rapidly, particularly ecommerce and social safety field, how a people's of precise Identification identity, protection information safety, become the social concern that needs to be resolved hurrily.Identification authentication mode in correlation technique due to existentially forgeable, lose and carry the disadvantage such as inconvenience, more and more be difficult to satisfy the demand of social development, so living things feature recognition has obtained increasing attention.Along with the development of the subjects such as computer science and pattern-recognition, make the cost that realizes of the high-performance automatic identification technology in this field be reduced to the acceptable degree.And face to identify mutually be one of technology that is most widely used in all living things feature recognition methods.Face is identified mutually with respect to other living things feature recognition has the advantages such as speed is fast, convenient, contactless, is the most natural, the most direct means of carrying out identity validation.
Face identify mutually be mainly by people's face detect, human eye location, facial characteristics registration, feature extraction and identification four parts consist of.In face was identified mutually, no matter utilize global characteristics or the local feature of people's face, the variation of people's face orientation and size had significant impact to identification, therefore need to carry out registration to people's face picture.And eyes are as the most significant feature in human face, compare with organs such as nose, faces and have more abundant information, two spacings are subjected to the impact of illumination or expression shape change less simultaneously, straight line deflection with the deflection of people's face in two place, eye pupil holes, so human eye can be used as the standard point of people's face registration.Along with the requirement of face phase recognition system to various aspects such as the precision of eyes location algorithm and speed more improves.Therefore, how fast and effectively eyes to be positioned, become an important study portion in face phase recognition system.At present a lot of people can wearing spectacles, wearing sunglasses will cause carrying out recognition of face, all can produce impact to some extent to the human eye location and wear black surround glasses or common glasses, and wear glasses that the direct projection of light all can cause glasses reflection under natural light or infrared light, this reflectively sometimes even whole zone of human eye all can be sheltered from.Therefore, in face recognition process, need to differentiate the glasses of wearing.In correlation technique, thereby directly whether reflective to carry out the technical scheme speed that human eye locates slower by judge glasses, and accuracy is relatively poor.
Summary of the invention
The invention provides discrimination method and the device of glasses in a kind of recognition of face, to solve the problem that lacks in correlation technique in face recognition process judging the technical scheme that whether reflective glasses differentiated the type of human eye wearing spectacles before.
The discrimination method of glasses in a kind of recognition of face is provided according to an aspect of the present invention.
Comprise according to the discrimination method of glasses in recognition of face of the present invention: obtain facial image, and in the facial image that gets the intercepting the first predeterminable area, wherein, the coverage of the first predeterminable area comprises: the some or all of zone that human eye area and glasses cover; Type according to the first predeterminable area judgement glasses.
Preferably, the type according to the first predeterminable area judgement glasses comprises: statistics in the first predeterminable area gray-scale value less than the number of the pixel of the first predetermined threshold value; According to less than the ratio of the number of the number of the pixel of the first predetermined threshold value and the pixel in the first predeterminable area and the comparative result of the second predetermined threshold value, judge whether the type of glasses is sunglasses.
Preferably, the type according to the first predeterminable area judgement glasses comprises: the first predeterminable area is carried out homomorphic filtering process; The first predeterminable area after processing through homomorphic filtering is carried out the disposal of gentle filter; Process carrying out neighborhood minimum filtering through the first predeterminable area after the disposal of gentle filter; The first predeterminable area after processing through neighborhood minimum filtering is fixed the ratio binary conversion treatment; Intercepting the second predeterminable area on through the first predeterminable area after the fixed proportion binary conversion treatment, wherein, the second predeterminable area is about people's face axis left-right symmetric, and the second predeterminable area comprises: the web member between left eye picture frame and right eye picture frame; Comparative result according to web member region proportion and the 3rd predetermined threshold value in the second predeterminable area judges whether the type of glasses is the black surround glasses.
Preferably, the type according to the first predeterminable area judgement glasses comprises: the first predeterminable area is carried out the Sobel operator filtering process; The first predeterminable area after processing through the Sobel operator filtering is carried out binary conversion treatment; Process carrying out morphology through the first predeterminable area after binary conversion treatment, extract one or more connected regions; One or more connected regions are carried out integral projection calculate, judge whether the type of glasses is the glasses of the other types except sunglasses or black surround glasses.
Preferably, after the type of judging glasses is the glasses of black surround glasses or the other types except sunglasses or black surround glasses, judge glasses reflective comprising whether under light irradiation: intercepting the 3rd predeterminable area on the first predeterminable area, wherein, the coverage of the 3rd predeterminable area comprises: human eye area, and the 3rd predeterminable area is less than the first predeterminable area; Determine respectively left eye region and right eye region in the 3rd predeterminable area; Add up respectively in left eye region and right eye region gray-scale value greater than the number of the pixel of the 4th predetermined threshold value; Choose the 5th predetermined threshold value N from 0 to 255, begin to choose successively each positive integer to 255 end from N again, calculate respectively the number of pixel of the positive integer that in left eye region and right eye region, gray-scale value equals to choose at every turn and the product of this positive integer, and calculate the summation of whole result of product, then adopt the summation calculate divided by the area of left eye region and right eye region, summation is carried out normalized, and wherein, N is 0 or positive integer and N≤255; According to the gray-scale value that counts greater than the number of the pixel of the 4th predetermined threshold value whether greater than the 6th predetermined threshold value and the normalization result that calculates whether greater than the 7th predetermined threshold value, judge that the glasses in described facial image are reflective whether.
The identification device of glasses in a kind of recognition of face is provided according to a further aspect in the invention.
Comprise according to the identification device of glasses in recognition of face of the present invention: acquisition module, be used for obtaining facial image, and in the facial image that gets the intercepting the first predeterminable area, wherein, the coverage of the first predeterminable area comprises: the some or all of zone that human eye area and glasses cover; Judge module is used for the type according to the first predeterminable area judgement glasses.
Preferably, judge module comprises: the first statistic unit is used for statistics in the number of the first predeterminable area gray-scale value less than the pixel of the first predetermined threshold value; The first judging unit is used for judging according to less than the ratio of the number of the number of the pixel of the first predetermined threshold value and the pixel in the first predeterminable area and the comparative result of the second predetermined threshold value whether the type of glasses is sunglasses.
Preferably, judge module comprises: the first processing unit is used for that the first predeterminable area is carried out homomorphic filtering and processes; The second processing unit is used for the first predeterminable area after processing through homomorphic filtering is carried out the disposal of gentle filter; The 3rd processing unit is used for processing carrying out neighborhood minimum filtering through the first predeterminable area after the disposal of gentle filter; Fourth processing unit is used for the first predeterminable area after processing through neighborhood minimum filtering is fixed the ratio binary conversion treatment; The first interception unit, be used for intercepting the second predeterminable area on through the first predeterminable area after the fixed proportion binary conversion treatment, wherein, the second predeterminable area is about people's face axis left-right symmetric, and the second predeterminable area comprises: the web member between left eye picture frame and right eye picture frame; The second judging unit is used for the comparative result according to web member region proportion and the 3rd predetermined threshold value in the second predeterminable area, judges whether the type of glasses is the black surround glasses.
Preferably, judge module comprises: the 5th processing unit is used for that the first predeterminable area is carried out the Sobel operator filtering and processes; The 6th processing unit is used for the first predeterminable area after processing through the Sobel operator filtering is carried out binary conversion treatment; Extraction unit is used for processing carrying out morphology through the first predeterminable area after binary conversion treatment, extracts one or more connected regions; The 3rd judging unit is used for that one or more connected regions are carried out integral projection and calculates, and judges whether the type of glasses is the glasses of the other types except sunglasses or black surround glasses.
Preferably, judge module, also be used for after the type of judging glasses is the glasses of black surround glasses or the other types except sunglasses or black surround glasses, judge whether the glasses in described facial image are reflective, judge module also comprises: the second interception unit is used for intercepting the 3rd predeterminable area on the first predeterminable area, wherein, the coverage of the 3rd predeterminable area comprises: human eye area, and the 3rd predeterminable area is less than the first predeterminable area; Determining unit is used for determining respectively left eye region and right eye region at the 3rd predeterminable area; The second statistic unit is used for adding up respectively in left eye region and right eye region gray-scale value greater than the number of the pixel of the 4th predetermined threshold value; The 3rd statistic unit, be used for from 0 to 255 and choose the 5th predetermined threshold value N, begin to choose successively each positive integer to 255 end from N again, calculate respectively the number of pixel of the positive integer that in left eye region and right eye region, gray-scale value equals to choose at every turn and the product of this positive integer, and calculate the summation of whole result of product, then adopt the summation calculate divided by the area of left eye region and right eye region, summation is carried out normalized, wherein, N is 0 or positive integer and N≤255; The 4th judging unit, be used for according to the gray-scale value that counts greater than the number of the pixel of the 4th predetermined threshold value whether greater than the 6th predetermined threshold value and the normalization result that calculates whether greater than the 7th predetermined threshold value, judge whether the glasses in described facial image reflective.
By the present invention, adopt and obtain facial image, and intercept the first predeterminable area in the facial image that gets, wherein, the coverage of the first predeterminable area comprises: the some or all of zone that human eye area and glasses cover; Whether the type and/or the glasses that judge glasses are reflective under the light irradiation, solved lack in the correlation technique in face recognition process judge glasses whether reflective before to the type of human eye wearing spectacles and the glasses problem of the reflective technical scheme of differentiating whether, and then can judge quickly and accurately wearing spectacles and reflective facial image.State to eyes in the human eye position fixing process of recognition of face is classified, and adopts diverse ways to position for the human eye of different situations, thereby has improved speed and the accuracy of human eye location.
Description of drawings
Accompanying drawing described herein is used to provide a further understanding of the present invention, consists of the application's a part, and illustrative examples of the present invention and explanation thereof are used for explaining the present invention, do not consist of improper restriction of the present invention.In the accompanying drawings:
Fig. 1 is the process flow diagram according to the discrimination method of glasses in the recognition of face of the embodiment of the present invention;
Fig. 2 is the schematic diagram according to the first untreated predeterminable area of the preferred embodiment of the present invention one;
Fig. 3 is the schematic diagram according to the first predeterminable area of the process homomorphic filtering processing of the preferred embodiment of the present invention one;
Fig. 4 is the schematic diagram according to the first predeterminable area of the process neighborhood minimum filtering processing of the preferred embodiment of the present invention one;
Fig. 5 is the first predeterminable area contrast schematic diagram in process fixed proportion binary conversion treatment according to the preferred embodiment of the present invention one;
Fig. 6 a is the schematic diagram according to the first untreated predeterminable area of the preferred embodiment of the present invention two;
Fig. 6 b is the schematic diagram according to the first untreated predeterminable area of the preferred embodiment of the present invention three;
Fig. 7 a carries out to Fig. 6 a the schematic diagram that the Sobel operator filtering is processed according to the preferred embodiment of the present invention two;
Fig. 7 b carries out to Fig. 6 b the schematic diagram that the Sobel operator filtering is processed according to the preferred embodiment of the present invention three;
Fig. 8 a carries out the schematic diagram of binary conversion treatment according to the preferred embodiment of the present invention two to Fig. 7 a;
Fig. 8 b carries out the schematic diagram of binary conversion treatment according to the preferred embodiment of the present invention three to Fig. 7 b;
Fig. 9 a carries out to Fig. 8 a the schematic diagram that morphology is processed according to the preferred embodiment of the present invention two;
Fig. 9 b carries out to Fig. 8 b the schematic diagram that morphology is processed according to the preferred embodiment of the present invention three;
Figure 10 is the schematic diagram of untreated according to the preferred embodiment of the invention the 3rd predeterminable area;
Figure 11 is the process flow diagram of the determination methods of glasses and glasses reflection in face recognition process according to the preferred embodiment of the invention;
Figure 12 is the structured flowchart according to the identification device of glasses in the recognition of face of the embodiment of the present invention;
Figure 13 is the structured flowchart of the identification device of glasses in recognition of face according to the preferred embodiment of the invention.
Embodiment
Hereinafter also describe in conjunction with the embodiments the present invention in detail with reference to accompanying drawing.Need to prove, in the situation that do not conflict, embodiment and the feature in embodiment in the application can make up mutually.
Fig. 1 is the process flow diagram according to the discrimination method of glasses in the recognition of face of the embodiment of the present invention.As shown in Figure 1, the method can comprise following treatment step:
Step S102: obtain facial image, and intercept the first predeterminable area in the facial image that gets, wherein, the coverage of the first predeterminable area comprises: the some or all of zone that human eye area and glasses cover;
Step S104: according to the type of the first described glasses of predeterminable area judgement.
In correlation technique, lack in face recognition process in the technical scheme that judges that whether reflective glasses differentiated the type of human eye wearing spectacles before.Adopt method as shown in Figure 1, adopt and obtain facial image, and intercept the first predeterminable area in the facial image that gets, wherein, the coverage of the first predeterminable area comprises: the some or all of zone that human eye area and glasses cover; Type according to the glasses in the first described facial image of predeterminable area judgement, solved the problem that lacks in the correlation technique in face recognition process judging the technical scheme that whether reflective glasses differentiated the type of human eye wearing spectacles before, and then can judge quickly and accurately wearing spectacles and further determine reflective facial image, state to eyes in the human eye position fixing process of recognition of face is classified, human eye for different situations adopts diverse ways to position, thereby has improved speed and the accuracy of human eye location.
In a preferred embodiment, Fig. 2 is the schematic diagram according to the first untreated predeterminable area of the preferred embodiment of the present invention one.As shown in Figure 2, intercepting the first predeterminable area can adopt two straight lines being parallel to each other vertical with people's face axis to be set in respectively above brows and below the bridge of the nose in the facial image that gets, and the zone between two straight lines is above-mentioned the first predeterminable area.The size of supposing facial image is M * N, and the size of the first predeterminable area is M' * N ' so, and M ' can get
With
Between part, and N' can get the part between 1 to N.The intercepting of certain the first predeterminable area can also be adopted other modes, as long as can comprise the some or all of zone that human eye area and glasses cover, repeats no more herein.
Preferably, in step S104, judge that according to the first predeterminable area the type of glasses can comprise following operation:
Step S1: the statistics in the first predeterminable area gray-scale value less than the number of the pixel of the first predetermined threshold value;
Gray scale refers to the color depth of black white image mid point, scope generally from 0 to 255, and white is 255, black is 0, therefore black and white picture also claims gray level image, has widely in medical science, field of image recognition and uses.
Step S2: according to less than the ratio of the number of the number of the pixel of the first predetermined threshold value and the pixel in the first predeterminable area and the comparative result of the second predetermined threshold value, judge whether the type of glasses is sunglasses.
In a preferred embodiment, less than the ratio of the number of the pixel in the number of the pixel of the first predetermined threshold value and the ocular that is covered by glasses during greater than the second predetermined threshold value, the type that can judge glasses is sunglasses.
In a preferred embodiment, after the type of judging glasses is sunglasses, because sunglasses can cause carrying out recognition of face, will directly export judged result this moment, and need not to judge the whether follow-up flow process such as reflective of glasses again.
Preferably, in step S104, judge that according to the first predeterminable area the type of glasses can comprise the following steps:
Step S3: the first predeterminable area is carried out homomorphic filtering process;
In a preferred embodiment, homomorphic filtering is a kind of image processing method with frequency is filtered and greyscale transformation combines, it relies on the illumination of image or the basis that Reflectivity Model is processed as frequency domain, utilizes the compression brightness range and strengthens the quality that contrast is improved image.Use the method that image is processed and meet human eye for the nonlinear characteristic of luminosity response, thereby avoid directly image being carried out the distortion that Fourier transform processing causes.
Fig. 3 is the schematic diagram according to the first predeterminable area of the process homomorphic filtering processing of the preferred embodiment of the present invention one.The gray scale of image f (x, y) can be decomposed into: f (x, y)=i (x, y) r (x, y)
In the preferred embodiment, the image of f (x, y) expression the first predeterminable area in following formula, wherein, the character of i (x, y) depends on irradiation source, be grading function, and r (x, y) depends on the characteristic of imaging object, is reflective function.
Concrete calculation procedure is as follows:
(1) convert multiplication to addition, carry out natural logarithm (ln) computing:
z(x,y)=lnf(x,y)=lni(x,y)+lnr(x,y)；
Z (x, y) represents the image of above-mentioned f (x, y) through obtaining after logarithm operation;
(2) image is transformed on frequency field, carries out Fourier transform:
Z(u,v)=I(u,v)+R(u,v)；
Z (u, v) represents that above-mentioned z (x, y) through Fourier transform, is changed to the image that obtains after frequency field by transform of spatial domain;
(3) press irradiation component, the spread reflection component, carry out homomorphism and increase clear computing:
H(u,v)Z(u,v)=H(u,v)I(u,v)+H(u,v)R(u,v)；
Wherein, H (u, v) be homomorphic filter, similar with the citation form of ideal highpass filter, can be according to different picture characteristics and needs, select different H (u, v), H (u, v) Z (u, v) represent that above-mentioned Z (u, v) increases through homomorphism the image that obtains after clear computing;
(4) carry out inverse fourier transform, obtain corresponding spatial domain expression formula
i'(x，y)=ifft[H(u，v)I(u，v)]；
r'(x，y)=ifft[H(u，v)R(u，v)]；
(5) carry out the exp computing, obtain net result:
f'(x,y)=i'(x,y)r'(x,y)；
Wherein, i'(x, y) and r'(x, y) be grading function and the reflective function that regenerates; F ' (x, y) is the image that generates after processing through homomorphic filtering.The image that detail contrast is poor, resolution is unclear, after adopting homomorphic filtering to process, the brightness ratio of image is more even, and details can strengthen.
Step S4: the first predeterminable area after processing through homomorphic filtering is carried out the disposal of gentle filter;
In a preferred embodiment, can adopt Gaussian filter to carry out the disposal of gentle filter to the image of the first predeterminable area of process homomorphic filtering.Gaussian filter is to select the linear smoothing wave filter of weights according to the shape of Gaussian function.Gaussian filter has good effect to the noise of removing Normal Distribution.The expression formula of Gaussian filter is as follows:
Step S5: process carrying out neighborhood minimum filtering through the first predeterminable area after the disposal of gentle filter;
In a preferred embodiment, Fig. 4 is the schematic diagram of the first predeterminable area of processing according to the process neighborhood minimum filtering of the preferred embodiment of the present invention one.Neighborhood minimum filtering is that each pixel in image is traveled through, value herein will by this put in certain neighborhood window the minimum pixel value in having a few replace.As shown in Figure 4, after adopting neighborhood minimum filtering to process, the glasses in image and the zone of eyes are more outstanding.Following formula is the neighborhood minimum Filtering Formula.
Wherein, I (x, y) is the pixel value through point (x, y) in the first predeterminable area of gaussian filtering, I'(x, y) be the pixel value after point (x, y) mini-value filtering.
Step S6: the first predeterminable area after processing through neighborhood minimum filtering is fixed the ratio binary conversion treatment;
The fixed proportion binaryzation refers to determine to account for since 0 gray-scale value the proportion of total gray-scale value, utilizes statistics with histogram to be met gray-scale value corresponding when setting proportion, namely obtains cutting apart the threshold value of image.
Step S7: intercepting the second predeterminable area on through the first predeterminable area after the fixed proportion binary conversion treatment, wherein, the second predeterminable area is about people's face axis left-right symmetric, and the second predeterminable area comprises: the web member between left eye picture frame and right eye picture frame;
Step S8: the comparative result according to web member region proportion and the 3rd predetermined threshold value in the second predeterminable area judges whether the type of glasses is the black surround glasses.
In a preferred embodiment, Fig. 5 is the contrast schematic diagram at the first predeterminable area that passes through the fixed proportion binary conversion treatment according to the preferred embodiment of the present invention one.The web member of black zone in the middle of can be clearly seen that in the latter half bianry image of Fig. 5, vertically the center section of the first area after the intercepting binaryzation is as the second predeterminable area (can be the zone that certain pixel is expanded respectively in the longitudinal central axis alignment both sides of the first predeterminable area), when proportion was greater than the 3rd predetermined threshold value in the second predeterminable area the web member region, the type that can judge glasses was the black surround glasses.
Preferably, in step S104, judge that according to the first predeterminable area the type of glasses can comprise following operation:
Step S9: the first predeterminable area is carried out the Sobel operator filtering process; Fig. 6 a is the schematic diagram according to the first untreated predeterminable area of the preferred embodiment of the present invention two.Fig. 6 b is the schematic diagram according to the first untreated predeterminable area of the preferred embodiment of the present invention three.Fig. 7 a carries out to Fig. 6 a the schematic diagram that the Sobel operator filtering is processed according to the preferred embodiment of the present invention two.Fig. 7 b carries out to Fig. 6 b the schematic diagram that the Sobel operator filtering is processed according to the preferred embodiment of the present invention three.As shown in Fig. 7 a and Fig. 7 b.
The Sobel operator refers in the edge detects, a kind of template operator commonly used.The Sobel operator has two: one is the detection level edge, and another is the detection of vertical edge.Operator is as follows:
Step S10: Fig. 8 a carries out the schematic diagram of binary conversion treatment according to the preferred embodiment of the present invention two to Fig. 7 a.Fig. 8 b carries out the schematic diagram of binary conversion treatment according to the preferred embodiment of the present invention three to Fig. 7 b.As shown in Fig. 8 a and Fig. 8 b, the first predeterminable area after processing through the Sobel operator filtering is carried out binary conversion treatment;
Step S11: Fig. 9 a carries out to Fig. 8 a the schematic diagram that morphology is processed according to the preferred embodiment of the present invention two.Fig. 9 b carries out to Fig. 8 b the schematic diagram that morphology is processed according to the preferred embodiment of the present invention three.As shown in Fig. 9 a and Fig. 9 b, process carrying out morphology through the first predeterminable area after binary conversion treatment, extract one or more connected regions;
Step S12: one or more connected regions are carried out integral projection calculate, judge whether the type of glasses is the glasses of the other types except sunglasses or black surround glasses.
Integral projection refers to image is carried out the projection of horizontal and vertical direction, calculates respectively the gray-scale value sum on both direction.
Preferably, in step S104, after the type of judging glasses is the glasses of black surround glasses or the other types except sunglasses or black surround glasses, judge glasses reflective can comprising the following steps whether under light irradiation:
Step S13: intercepting the 3rd predeterminable area on the first predeterminable area, wherein, the coverage of the 3rd predeterminable area comprises: human eye area, and the 3rd predeterminable area is less than the first predeterminable area;
In a preferred embodiment, Figure 10 is the schematic diagram of untreated according to the preferred embodiment of the invention the 3rd predeterminable area.As shown in figure 10, the size of supposing facial image is M * N, and the size of the first predeterminable area is M ' * N', and M ' can get
With
Between part, and N' can get the part between 1 to N, the size of the 3rd predeterminable area is X * Y so, X can get
With
Between part, and Y can get
Arrive
Between part.
Step S14: determine respectively left eye region and right eye region in the 3rd predeterminable area;
In a preferred embodiment, the left eye region is the 3rd predeterminable area left-half
Arrive
Between part, and the right eye region is the 3rd predeterminable area right half part
Arrive
Between part.
Step S15: add up respectively in left eye region and right eye region gray-scale value greater than the number of the pixel of the 4th predetermined threshold value;
Step S16: choose the 5th predetermined threshold value N from 0 to 255, begin to choose successively each positive integer to 255 end from N again, calculate respectively the number of pixel of the positive integer that in left eye region and right eye region, gray-scale value equals to choose at every turn and the product of this positive integer, and calculate the summation of whole result of product, then adopt the summation calculate respectively divided by the area of corresponding left eye region or right eye region, respectively the summation of left eye region and right eye region is carried out normalized, wherein, N is 0 or positive integer and N≤255;
In a preferred embodiment, suppose that N gets 245, the statistics gray-scale value is that the pixel number of 245 o'clock is n
1Individual, gray-scale value is that the pixel number of 246 o'clock is n
2Individual, gray-scale value is that the pixel number of 247 o'clock is n
3Individual ... the number of 245 pixel and 245 product will be equaled so for the first time, will equal for the second time the number of 246 pixel and 246 product, the number of 247 pixel and 247 product will be equaled for the third time, the rest may be inferred, until calculate and 255 product, then with the addition of each time result of product and then obtain summation, i.e. the result of calculation of each time product addition summation is 245 * n
1+ 246 * n
2+ 247 * n
3+ ..., then also will be correspondingly (for example: left eye region area is divided by the area of left eye region or right eye region
M is that length, the N of facial image is the wide of facial image) carry out normalized.
Step S17: according to the gray-scale value that counts greater than the number of the pixel of the 4th predetermined threshold value whether greater than the 6th predetermined threshold value and the normalization result that calculates whether greater than the 7th predetermined threshold value, judge whether the glasses in facial image reflective.
In a preferred embodiment, when the gray-scale value that counts greater than the number of the pixel of the 4th predetermined threshold value greater than the 6th predetermined threshold value and the normalization result that calculates greater than the 7th predetermined threshold value, can judge the glasses reflection in facial image.
Below in conjunction with preferred implementation shown in Figure 11, above-mentioned preferred implementation process is further described.
Figure 11 is the process flow diagram of the determination methods of glasses and glasses reflection in face recognition process according to the preferred embodiment of the invention.As shown in figure 11, the method can comprise the following steps:
Step S1102: judge that whether facial image wears sunglasses, specifically can comprise the following steps:
Step S11021: the middle ocular (being equivalent to above-mentioned the first predeterminable area) that comprises glasses according to the size intercepting of facial image;
Step S11022: add up above-mentioned in the middle of the ocular gray-scale value less than the number of the pixel of predetermined threshold value (for example: 50, be equivalent to above-mentioned the first predetermined threshold value);
Step S11023: calculate this area grayscale value and account for the ratio of whole area pixel point number less than the number of 50 pixel, if greater than threshold value T(for example: T can value be middle ocular area
Be equivalent to above-mentioned the second predetermined threshold value), think and wear sunglasses, otherwise, think and do not wear sunglasses, can continue execution in step S1104;
Step S1104: in the middle of judgement, whether ocular wears the black surround glasses, specifically can comprise the following steps:
Step S11041: the middle ocular that gets is carried out homomorphic filtering process, strengthen contrast;
Step S11042: utilize Gaussian filter to carry out smothing filtering to the middle ocular after homomorphic filtering is processed through step S11041, eliminate the interference of noise, adopt subsequently the neighborhood minimum wave filter to travel through each pixel in this centre ocular, outstanding target;
Step S11043: will be through the greyscale transformation of the middle ocular after the disposal of gentle filter to [0,1], corresponding gray-scale value T when utilizing statistic histogram to be met proportion
0, and adopt T
0To carrying out binary conversion treatment through the middle ocular after the disposal of gentle filter;
Step S11044: intercept center section (being equivalent to above-mentioned the second predeterminable area) on through the middle ocular after binary conversion treatment, wherein, can comprise: connect the web member that is stuck between left eye picture frame and right eye picture frame on the bridge of the nose, compare in the center section of above-mentioned intercepting shared proportion and predetermined threshold value (being equivalent to above-mentioned the 3rd predetermined threshold value) by calculating the web member region, and then judge and whether wear the black surround glasses; When in the center section of web member region in above-mentioned intercepting, proportion was greater than predetermined threshold value, the type that can judge glasses was the black surround glasses;
Step S1106: in the middle of judgement, whether ocular wears other common spectacles except sunglasses and black surround glasses, specifically can comprise the following steps:
Step S11061: utilize the Sobel operator filtering, middle ocular is carried out binary conversion treatment, obtain binary image img_bw;
Step S11062: img_bw is carried out morphological operation, with the part deletion that in the img_bw image, area is less, remove the part interference region; Again middle ocular is carried out closed operation, the spaced point that will close on connects into connected region, the profile of smoothed image;
Step S11063: ocular in the middle of the later binaryzation of morphological operation in step S11062 is extracted connected component, determine size and the position of connected component;
Step S11064: get rid of and disturb connected region, further get rid of interference region, judge the position of each connected region in image by mark value, if this connected region contains more pixel near the image boundary position, delete this connected region, if connected region contains less pixel, delete this connected region;
Step S11065: calculate integral projection, namely calculate respectively the middle ocular of binaryzation in the horizontal direction
Deng the value of the integral projection at three places, and horizontal integral projection is greater than zero number, and finds out the longest connected region of horizontal length in this centre ocular according to the size of integral projection;
Step S11066: comprehensively judge whether to wear common spectacles, meet one of following three kinds of situations and can be judged as and wear common spectacles:
If situation one horizontal direction
Perhaps horizontal direction
The integral projection value at place greater than 2 and the number of connected region more than or equal to 4;
The gray-scale value of situation two, image central region be 1 number more than or equal to 5, horizontal integral projection is greater than half greater than picturedeep of zero number, and the number of connected region is more than or equal to 2;
The longest connected region of situation three, horizontal length is greater than half of picturewide.
Step S1108: judge that whether glasses are reflective, specifically can comprise the following steps:
Step S11081: intercept retroreflective regions (being equivalent to above-mentioned the 3rd predeterminable area) on middle ocular, wherein, the coverage of retroreflective regions comprises: human eye area, and retroreflective regions is less than middle ocular;
Step S11082: determine respectively left eye region and right eye region in retroreflective regions;
The number of pixel step S11083: count respectively that in left eye region, right eye region, gray-scale value is equivalent to above-mentioned the 4th predetermined threshold value greater than 250() is the number of reflective spot;
Step S11084: the histogram of adding up respectively left eye region, right eye region, for reflective picture, in histogram, the number of pixels of high grade grey level or frequency are relatively large, utilize the histogram of high grade grey level to multiply by gray level to calculate reflective degree; For example: above-mentioned the 5th predetermined threshold value gets 245, since 245 to 255 finish to choose successively each positive integer carries out respectively product calculation, then the last summation of calculating again each result of product utilizes above-mentioned summation divided by the area of left eye region, right eye region, carries out normalized;
Step S11085: can judge according to the result in above-mentioned steps S11083 and step S11084 and setting threshold whether middle ocular is reflective, the gray-scale value that namely ought count greater than the number of 250 pixel greater than predetermined threshold value (being equivalent to above-mentioned the 6th predetermined threshold value) and the normalization result that calculates greater than predetermined threshold value (being equivalent to above-mentioned the 7th predetermined threshold value), can judge that glasses are reflective under the light irradiation;
Step S1110: whether output glasses type and/or glasses reflective judged result.
In a preferred embodiment, above-mentioned judged result can include but not limited to one of following: sunglasses, black surround glasses, common spectacles, black surround glasses and reflective, common spectacles and reflective.
Figure 12 is the structured flowchart according to the identification device of glasses in the recognition of face of the embodiment of the present invention.As shown in figure 12, in this recognition of face, the identification device of glasses can comprise: acquisition module 10, be used for obtaining facial image, and in the facial image that gets the intercepting the first predeterminable area, wherein, the coverage of the first predeterminable area comprises: the some or all of zone that human eye area and glasses cover; Judge module 20 is used for the type according to the first predeterminable area judgement glasses.
Adopt device as shown in figure 12, solved the problem that lacks in the correlation technique in face recognition process judging the technical scheme that whether reflective glasses differentiated the type of human eye wearing spectacles before, and then can judge quickly and accurately wearing spectacles and reflective facial image, state to eyes in the human eye position fixing process of recognition of face is classified, human eye for different situations adopts diverse ways to position, thereby has improved speed and the accuracy of human eye location.
Preferably, as shown in figure 13, judge module 20 can comprise: the first statistic unit 200 is used for statistics in the number of the first predeterminable area gray-scale value less than the pixel of the first predetermined threshold value; The first judging unit 202 is used for judging according to less than the ratio of the number of the number of the pixel of the first predetermined threshold value and the pixel in the first predeterminable area and the comparative result of the second predetermined threshold value whether the type of glasses is sunglasses.
Preferably, as shown in figure 13, judge module 20 can also comprise: the first processing unit 204 is used for that the first predeterminable area is carried out homomorphic filtering and processes; The second processing unit 206 is used for the first predeterminable area after processing through homomorphic filtering is carried out the disposal of gentle filter; The 3rd processing unit 208 is used for processing carrying out neighborhood minimum filtering through the first predeterminable area after the disposal of gentle filter; Fourth processing unit 210 is used for the first predeterminable area after processing through neighborhood minimum filtering is fixed the ratio binary conversion treatment; The first interception unit 212, be used for intercepting the second predeterminable area on through the first predeterminable area after the fixed proportion binary conversion treatment, wherein, the second predeterminable area is about people's face axis left-right symmetric, and the second predeterminable area comprises: the web member between left eye picture frame and right eye picture frame; The second judging unit 214 is used for the comparative result according to web member region proportion and the 3rd predetermined threshold value in the second predeterminable area, judges whether the type of glasses is the black surround glasses.
Preferably, as shown in figure 13, judge module 20 can also comprise: the 5th processing unit 216 is used for that the first predeterminable area is carried out the Sobel operator filtering and processes; The 6th processing unit 218 is used for the first predeterminable area after processing through the Sobel operator filtering is carried out binary conversion treatment; Extraction unit 220 is used for processing carrying out morphology through the first predeterminable area after binary conversion treatment, extracts one or more connected regions; The 3rd judging unit 222 is used for that one or more connected regions are carried out integral projection and calculates, and judges whether the type of glasses is the glasses of the other types except sunglasses or black surround glasses.
Preferably, as shown in figure 13, judge module 20, also be used for judging whether the glasses in described facial image are reflective after the type of judging glasses is the glasses of black surround glasses or the other types except sunglasses or black surround glasses, judge module 20 can also comprise: the second interception unit 224, be used for intercepting the 3rd predeterminable area on the first predeterminable area, wherein, the coverage of the 3rd predeterminable area comprises: human eye area, and the 3rd predeterminable area is less than the first predeterminable area; Determining unit 226 is used for determining respectively left eye region and right eye region at the 3rd predeterminable area; The second statistic unit 228 is used for adding up respectively in left eye region and right eye region gray-scale value greater than the number of the pixel of the 4th predetermined threshold value; The 3rd statistic unit 230, be used for gray-scale value as: from 0 to 255 chooses the 5th predetermined threshold value N, begin to 255 end from N again, choose successively each positive integer, calculate respectively the number of pixel of the positive integer that in left eye region and right eye region, gray-scale value equals to choose at every turn and the product of this positive integer, and calculate the summation of whole result of product, then adopt the summation calculate divided by the area of left eye region and right eye region, summation is carried out normalized, wherein, N is 0 or positive integer and N≤255; The 4th judging unit 232, be used for according to the gray-scale value that counts greater than the number of the pixel of the 4th predetermined threshold value whether greater than the 6th predetermined threshold value and the normalization result that calculates whether greater than the 7th predetermined threshold value, judge whether the glasses in facial image reflective under light shines.
From above description, can find out, above-described embodiment has been realized following technique effect (need to prove that these effects are effects that some preferred embodiment can reach): technical scheme provided by the present invention can be judged quickly and accurately and wear glasses and reflective facial image, during human eye is located, the state of eyes is classified, human eye for different situations adopts diverse ways to position, thereby has improved speed and the accuracy of human eye location.
obviously, those skilled in the art should be understood that, above-mentioned each module of the present invention or each step can realize with general calculation element, they can concentrate on single calculation element, perhaps be distributed on the network that a plurality of calculation elements form, alternatively, they can be realized with the executable program code of calculation element, thereby, they can be stored in memory storage and be carried out by calculation element, and in some cases, can carry out step shown or that describe with the order that is different from herein, perhaps they are made into respectively each integrated circuit modules, perhaps a plurality of modules in them or step being made into the single integrated circuit module realizes.Like this, the present invention is not restricted to any specific hardware and software combination.
The above is only the preferred embodiments of the present invention, is not limited to the present invention, and for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (10)
1. the discrimination method of glasses in a recognition of face, is characterized in that, comprising:
Obtain facial image, and intercept the first predeterminable area in the described facial image that gets, wherein, the coverage of described the first predeterminable area comprises: the some or all of zone that human eye area and glasses cover;
Type according to described the first described glasses of predeterminable area judgement.
2. method according to claim 1, is characterized in that, judges that according to described the first predeterminable area the type of described glasses comprises:
Statistics in described the first predeterminable area gray-scale value less than the number of the pixel of the first predetermined threshold value;
According to less than the ratio of the number of the number of the pixel of described the first predetermined threshold value and the pixel in described the first predeterminable area and the comparative result of the second predetermined threshold value, judge whether the type of described glasses is sunglasses.
3. method according to claim 1, is characterized in that, judges that according to described the first predeterminable area the type of described glasses comprises:
Described the first predeterminable area is carried out homomorphic filtering to be processed;
The first predeterminable area after processing through described homomorphic filtering is carried out the disposal of gentle filter;
Process carrying out neighborhood minimum filtering through the first predeterminable area after described the disposal of gentle filter;
The first predeterminable area after processing through described neighborhood minimum filtering is fixed the ratio binary conversion treatment;
Intercept the second predeterminable area on through the first predeterminable area after described fixed proportion binary conversion treatment, wherein, described the second predeterminable area is about people's face axis left-right symmetric, and described the second predeterminable area comprises: the web member between left eye picture frame and right eye picture frame;
Comparative result according to described web member region proportion and the 3rd predetermined threshold value in described the second predeterminable area judges whether the type of described glasses is the black surround glasses.
4. method according to claim 1, is characterized in that, judges that according to described the first predeterminable area the type of described glasses comprises:
Described the first predeterminable area is carried out Sobel Sobel operator filtering to be processed;
The first predeterminable area after processing through described Sobel operator filtering is carried out binary conversion treatment;
Process carrying out morphology through the first predeterminable area after described binary conversion treatment, extract one or more connected regions;
Described one or more connected regions are carried out integral projection calculate, judge whether the type of described glasses is the glasses of the other types except sunglasses or black surround glasses.
5. according to claim 3 or 4 described methods, it is characterized in that, after the type of judging described glasses is the glasses of described black surround glasses or the other types except described sunglasses or described black surround glasses, judge glasses reflective the comprising whether in described facial image:
Intercepting the 3rd predeterminable area on described the first predeterminable area, wherein, the coverage of described the 3rd predeterminable area comprises: human eye area, and described the 3rd predeterminable area is less than described the first predeterminable area;
Determine respectively left eye region and right eye region in described the 3rd predeterminable area;
Add up respectively in described left eye region and described right eye region gray-scale value greater than the number of the pixel of the 4th predetermined threshold value;
Choose the 5th predetermined threshold value N from 0 to 255, begin to choose successively each positive integer to 255 end from N again, calculate respectively the number of pixel of the positive integer that in described left eye region and described right eye region, gray-scale value equals to choose at every turn and the product of this positive integer, and calculate the summation of whole result of product, then adopt the described summation calculate divided by the area of described left eye region and described right eye region, described summation is carried out normalized, wherein, N is 0 or positive integer and N≤255;
According to the described gray-scale value that counts greater than the number of the pixel of the 4th predetermined threshold value whether greater than the 6th predetermined threshold value and the described normalization result that calculates whether greater than the 7th predetermined threshold value, judge whether the glasses in described facial image reflective.
6. the identification device of glasses in a recognition of face, is characterized in that, comprising:
Acquisition module is used for obtaining facial image, and intercepts the first predeterminable area in the described facial image that gets, and wherein, the coverage of described the first predeterminable area comprises: the some or all of zone that human eye area and glasses cover;
Judge module is used for the type according to described the first described glasses of predeterminable area judgement.
7. device according to claim 6, is characterized in that, described judge module comprises:
The first statistic unit is used for statistics in the number of described the first predeterminable area gray-scale value less than the pixel of the first predetermined threshold value;
The first judging unit is used for judging according to less than the ratio of the number of the number of the pixel of described the first predetermined threshold value and the pixel in described the first predeterminable area and the comparative result of the second predetermined threshold value whether the type of described glasses is sunglasses.
8. device according to claim 6, is characterized in that, described judge module comprises:
The first processing unit is used for that described the first predeterminable area is carried out homomorphic filtering and processes;
The second processing unit is used for the first predeterminable area after processing through described homomorphic filtering is carried out the disposal of gentle filter;
The 3rd processing unit is used for processing carrying out neighborhood minimum filtering through the first predeterminable area after described the disposal of gentle filter;
Fourth processing unit is used for the first predeterminable area after processing through described neighborhood minimum filtering is fixed the ratio binary conversion treatment;
The first interception unit, be used for intercepting the second predeterminable area on through the first predeterminable area after described fixed proportion binary conversion treatment, wherein, described the second predeterminable area is about people's face axis left-right symmetric, and described the second predeterminable area comprises: the web member between left eye picture frame and right eye picture frame;
The second judging unit is used for the comparative result according to described web member region proportion and the 3rd predetermined threshold value in described the second predeterminable area, judges whether the type of described glasses is the black surround glasses.
9. device according to claim 6, is characterized in that, described judge module comprises:
The 5th processing unit is used for that described the first predeterminable area is carried out Sobel Sobel operator filtering and processes;
The 6th processing unit is used for the first predeterminable area after processing through described Sobel operator filtering is carried out binary conversion treatment;
Extraction unit is used for processing carrying out morphology through the first predeterminable area after described binary conversion treatment, extracts one or more connected regions;
The 3rd judging unit is used for that described one or more connected regions are carried out integral projection and calculates, and judges whether the type of described glasses is the glasses of the other types except sunglasses or black surround glasses.
10. according to claim 8 or 9 described devices, it is characterized in that, described judge module, also be used for after the type of judging described glasses is the glasses of described black surround glasses or the other types except described sunglasses or described black surround glasses, judge whether the glasses in described facial image are reflective, and described judge module also comprises:
The second interception unit is used for intercepting the 3rd predeterminable area on described the first predeterminable area, and wherein, the coverage of described the 3rd predeterminable area comprises: human eye area, and described the 3rd predeterminable area is less than described the first predeterminable area;
Determining unit is used for determining respectively left eye region and right eye region at described the 3rd predeterminable area;
The second statistic unit is used for adding up respectively in described left eye region and described right eye region gray-scale value greater than the number of the pixel of the 4th predetermined threshold value;
The 3rd statistic unit, be used for from 0 to 255 and choose the 5th predetermined threshold value N, begin to choose successively each positive integer to 255 end from N again, calculate respectively the number of pixel of the positive integer that in described left eye region and described right eye region, gray-scale value equals to choose at every turn and the product of this positive integer, and calculate the summation of whole result of product, then adopt the described summation calculate divided by the area of described left eye region and described right eye region, described summation is carried out normalized, wherein, N is 0 or positive integer and N≤255;
The 4th judging unit, be used for according to the described gray-scale value that counts greater than the number of the pixel of the 4th predetermined threshold value whether greater than the 6th predetermined threshold value and the described normalization result that calculates whether greater than the 7th predetermined threshold value, judge whether the glasses in described facial image reflective.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310027751.8A CN103093210B (en) | 2013-01-24 | 2013-01-24 | Method and device for glasses identification in face identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310027751.8A CN103093210B (en) | 2013-01-24 | 2013-01-24 | Method and device for glasses identification in face identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103093210A true CN103093210A (en) | 2013-05-08 |
| CN103093210B CN103093210B (en) | 2017-02-08 |
Family
ID=48205758
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310027751.8A Active CN103093210B (en) | 2013-01-24 | 2013-01-24 | Method and device for glasses identification in face identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103093210B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103465825A (en) * | 2013-08-15 | 2013-12-25 | 苏州佳世达光电有限公司 | Vehicle-mounted system and control method thereof |
| WO2015165365A1 (en) * | 2014-04-29 | 2015-11-05 | 华为技术有限公司 | Facial recognition method and system |
| CN105184253A (en) * | 2015-09-01 | 2015-12-23 | 北京旷视科技有限公司 | Face identification method and face identification system |
| CN105335695A (en) * | 2015-08-19 | 2016-02-17 | 华南理工大学 | Glasses detection based eye positioning method |
| CN106155280A (en) * | 2015-03-30 | 2016-11-23 | 北京智谷睿拓技术服务有限公司 | Exchange method, interactive device and subscriber equipment |
| CN106503611A (en) * | 2016-09-09 | 2017-03-15 | 西安理工大学 | Facial image eyeglass detection method based on marginal information projective iteration mirror holder crossbeam |
| 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 |
| CN108492421A (en) * | 2018-03-29 | 2018-09-04 | 成都惠网远航科技有限公司 | Low-power consumption face identification method |
| CN108564540A (en) * | 2018-03-05 | 2018-09-21 | 广东欧珀移动通信有限公司 | Remove image processing method, device and the terminal device that eyeglass is reflective in image |
| CN108600555A (en) * | 2018-06-15 | 2018-09-28 | 努比亚技术有限公司 | A kind of screen color method of adjustment, mobile terminal and computer readable storage medium |
| CN109036332A (en) * | 2018-09-14 | 2018-12-18 | 奇酷互联网络科技（深圳）有限公司 | Intelligent terminal and its adjusting method of screen intensity, the device with store function |
| CN109657652A (en) * | 2019-01-16 | 2019-04-19 | 平安科技（深圳）有限公司 | A kind of face identification method and device |
| CN109902561A (en) * | 2019-01-16 | 2019-06-18 | 平安科技（深圳）有限公司 | A kind of face identification method and device, robot applied to robot |
| CN111179880A (en) * | 2019-12-26 | 2020-05-19 | 恒大新能源汽车科技(广东)有限公司 | Brightness adjusting method and device of display screen, electronic equipment and system |
| CN111488843A (en) * | 2020-04-16 | 2020-08-04 | 贵州安防工程技术研究中心有限公司 | Face sunglasses distinguishing method based on step-by-step inhibition of missing report and false report rate |
| CN112149580A (en) * | 2020-09-25 | 2020-12-29 | 江苏邦融微电子有限公司 | Image processing method for distinguishing real human face from photo |
| CN112733570A (en) * | 2019-10-14 | 2021-04-30 | 北京眼神智能科技有限公司 | Glasses detection method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101499127A (en) * | 2008-02-03 | 2009-08-05 | 上海银晨智能识别科技有限公司 | Method for preventing trouble in human face recognition caused by interference |
| CN102034079A (en) * | 2009-09-24 | 2011-04-27 | 汉王科技股份有限公司 | Method and system for identifying faces shaded by eyeglasses |
| CN102262727A (en) * | 2011-06-24 | 2011-11-30 | 常州锐驰电子科技有限公司 | Method for monitoring face image quality at client acquisition terminal in real time |
| CN102324166A (en) * | 2011-09-19 | 2012-01-18 | 深圳市汉华安道科技有限责任公司 | Fatigue driving detection method and device |
-
2013
- 2013-01-24 CN CN201310027751.8A patent/CN103093210B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101499127A (en) * | 2008-02-03 | 2009-08-05 | 上海银晨智能识别科技有限公司 | Method for preventing trouble in human face recognition caused by interference |
| CN102034079A (en) * | 2009-09-24 | 2011-04-27 | 汉王科技股份有限公司 | Method and system for identifying faces shaded by eyeglasses |
| CN102262727A (en) * | 2011-06-24 | 2011-11-30 | 常州锐驰电子科技有限公司 | Method for monitoring face image quality at client acquisition terminal in real time |
| CN102324166A (en) * | 2011-09-19 | 2012-01-18 | 深圳市汉华安道科技有限责任公司 | Fatigue driving detection method and device |
Non-Patent Citations (1)
| Title |
|---|
| XIAODONG JIA,ET AL.: "Eyeglasses Removal From Facial Image Based On Phase Congruency", 《2010 3RD INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING(CISP2010)》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103465825A (en) * | 2013-08-15 | 2013-12-25 | 苏州佳世达光电有限公司 | Vehicle-mounted system and control method thereof |
| WO2015165365A1 (en) * | 2014-04-29 | 2015-11-05 | 华为技术有限公司 | Facial recognition method and system |
| CN106155280A (en) * | 2015-03-30 | 2016-11-23 | 北京智谷睿拓技术服务有限公司 | Exchange method, interactive device and subscriber equipment |
| CN105335695A (en) * | 2015-08-19 | 2016-02-17 | 华南理工大学 | Glasses detection based eye positioning method |
| CN105184253A (en) * | 2015-09-01 | 2015-12-23 | 北京旷视科技有限公司 | Face identification method and face identification system |
| CN106503611B (en) * | 2016-09-09 | 2019-11-22 | 西安理工大学 | Facial image eyeglass detection method based on marginal information projective iteration mirror holder crossbeam |
| CN106503611A (en) * | 2016-09-09 | 2017-03-15 | 西安理工大学 | Facial image eyeglass detection method based on marginal information projective iteration mirror holder crossbeam |
| 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 |
| CN107808120B (en) * | 2017-09-30 | 2018-08-31 | 平安科技（深圳）有限公司 | Glasses localization method, device and storage medium |
| CN108564540A (en) * | 2018-03-05 | 2018-09-21 | 广东欧珀移动通信有限公司 | Remove image processing method, device and the terminal device that eyeglass is reflective in image |
| CN108564540B (en) * | 2018-03-05 | 2020-07-17 | Oppo广东移动通信有限公司 | Image processing method and device for removing lens reflection in image and terminal equipment |
| CN108492421A (en) * | 2018-03-29 | 2018-09-04 | 成都惠网远航科技有限公司 | Low-power consumption face identification method |
| CN108600555A (en) * | 2018-06-15 | 2018-09-28 | 努比亚技术有限公司 | A kind of screen color method of adjustment, mobile terminal and computer readable storage medium |
| CN109036332A (en) * | 2018-09-14 | 2018-12-18 | 奇酷互联网络科技（深圳）有限公司 | Intelligent terminal and its adjusting method of screen intensity, the device with store function |
| CN109902561A (en) * | 2019-01-16 | 2019-06-18 | 平安科技（深圳）有限公司 | A kind of face identification method and device, robot applied to robot |
| CN109657652A (en) * | 2019-01-16 | 2019-04-19 | 平安科技（深圳）有限公司 | A kind of face identification method and device |
| CN112733570A (en) * | 2019-10-14 | 2021-04-30 | 北京眼神智能科技有限公司 | Glasses detection method and device, electronic equipment and storage medium |
| CN111179880A (en) * | 2019-12-26 | 2020-05-19 | 恒大新能源汽车科技(广东)有限公司 | Brightness adjusting method and device of display screen, electronic equipment and system |
| CN111488843A (en) * | 2020-04-16 | 2020-08-04 | 贵州安防工程技术研究中心有限公司 | Face sunglasses distinguishing method based on step-by-step inhibition of missing report and false report rate |
| CN112149580A (en) * | 2020-09-25 | 2020-12-29 | 江苏邦融微电子有限公司 | Image processing method for distinguishing real human face from photo |
| CN112149580B (en) * | 2020-09-25 | 2024-05-14 | 江苏邦融微电子有限公司 | Image processing method for distinguishing real face from photo |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103093210B (en) | 2017-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103093210A (en) | Method and device for glasses identification in face identification | |
| Galbally et al. | Iris liveness detection based on quality related features | |
| CN101999900B (en) | Living body detecting method and system applied to human face recognition | |
| RU2431190C2 (en) | Facial prominence recognition method and device | |
| Chen et al. | Liveness detection for iris recognition using multispectral images | |
| CN105139003B (en) | A kind of dynamic human face recognition system and method | |
| Saha et al. | Mutual spectral residual approach for multifocus image fusion | |
| US20070274570A1 (en) | Iris recognition system having image quality metrics | |
| CN103632132A (en) | Face detection and recognition method based on skin color segmentation and template matching | |
| CN103473564B (en) | A kind of obverse face detection method based on sensitizing range | |
| CN103679118A (en) | Human face in-vivo detection method and system | |
| CN103020579A (en) | Face recognition method and system, and removing method and device for glasses frame in face image | |
| Alheeti | Biometric iris recognition based on hybrid technique | |
| CN101923640A (en) | Method for distinguishing false iris images based on robust texture features and machine learning | |
| CN101615241B (en) | Method for screening certificate photos | |
| CN102629320A (en) | Ordinal measurement statistical description face recognition method based on feature level | |
| Li et al. | Robust iris segmentation based on learned boundary detectors | |
| CN105426843A (en) | Single-lens palm vein and palmprint image acquisition apparatus and image enhancement and segmentation method | |
| CN106214166A (en) | One is worn glasses Driver Fatigue Detection | |
| CN109255319A (en) | For the recognition of face payment information method for anti-counterfeit of still photo | |
| CN103729646B (en) | Eye image validity detection method | |
| Zhao et al. | Robust eye detection under active infrared illumination | |
| Lovish et al. | Robust contact lens detection using local phase quantization and binary gabor pattern | |
| Kaudki et al. | A robust iris recognition approach using fuzzy edge processing technique | |
| Tallapragada et al. | Morphology based non ideal iris recognition using decision tree classifier |
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 |