CN107516067A - A kind of human-eye positioning method and system based on Face Detection - Google Patents
A kind of human-eye positioning method and system based on Face Detection Download PDFInfo
- Publication number
- CN107516067A CN107516067A CN201710600994.4A CN201710600994A CN107516067A CN 107516067 A CN107516067 A CN 107516067A CN 201710600994 A CN201710600994 A CN 201710600994A CN 107516067 A CN107516067 A CN 107516067A
- Authority
- CN
- China
- Prior art keywords
- human eye
- block
- colour
- undetermined
- note
- 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
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
- G06V40/18—Eye characteristics, e.g. of the iris
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses a kind of human-eye positioning method and system based on Face Detection, belongs to technical field of image processing, and the inventive method designs a kind of human eye location technology, to lift the ageing of human eye video location technology using Face Detection reduction hunting zone.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of human-eye positioning method based on Face Detection and it is
System.
Background technology
With developing rapidly for multimedia technology and computer networking technology, the main flow that video is increasingly becoming information propagation carries
One of body.Either face video retrieval or Online Video U.S. face, accurate quickly human eye location technology can all strengthen its thing
The effect of half work(times.The ad hoc eye image location technology of main flow at present, it is computationally intensive, constrain the online of algorithm and use and two
Secondary development efficiency.
The content of the invention
The purpose of the embodiment of the present invention is to propose a kind of human-eye positioning method based on Face Detection, it is intended to solves existing
Technology eye image location technology, it is computationally intensive, constrain the online of algorithm and use and secondary development efficiency.
The embodiment of the present invention is achieved in that a kind of human-eye positioning method based on Face Detection, and methods described includes
Following steps：
For each block in present image, corresponding colour of skin identifier is set；
If the colour of skin identifier of all pieces of present image is 0, positions without human eye, directly terminate；
Human eye region undetermined is searched in present image, and corresponding determinating mode is set；
Human eye positioning, mark are carried out according to determinating mode.
The another object of the embodiment of the present invention is to propose a kind of human eye alignment system based on Face Detection, the system
Including：
Colour of skin block judging treatmenting module, for judging whether each block is colour of skin block in present image, if bkt(i,j)
It is determined as colour of skin block, then it is 1 to set the block colour of skin identifier, i.e. notet(i, j)=1；Otherwise, note is sett(i, j)=0；
Wherein, bkt(i, j) represent present image the i-th row jth block, bkw, bkh represent respectively image division it is blocking with
Afterwards, columns and line number of the image in units of block；notet(i, j) represents the colour of skin identifier of the i-th row jth block of present image.
Colour of skin identifier judge module, if for judging that the colour of skin identifier of all pieces of present image is 0, need not
Human eye positions, and directly terminates；
Human eye regional search device undetermined, human eye region undetermined is searched in present image, and corresponding judgement mould is set
Formula；
Human eye positions and identity device, for carrying out human eye positioning, mark according to determinating mode.
Beneficial effects of the present invention
The present invention proposes a kind of human-eye positioning method and system based on Face Detection.The inventive method utilizes Face Detection
Reduce hunting zone, a kind of human eye location technology is designed, to lift the ageing of human eye video location technology.
Brief description of the drawings
Fig. 1 is a kind of human-eye positioning method flow chart based on Face Detection of the preferred embodiment of the present invention；
Fig. 2 is Step3 method detaileds flow chart in Fig. 1；
Fig. 3 is determinating mode method detailed flow chart in side in Step4 in Fig. 1；
Fig. 4 is determinating mode method detailed flow chart in front in Step4 in Fig. 1；
Fig. 5 is a kind of human eye positioning system structure figure based on Face Detection of the preferred embodiment of the present invention；
Fig. 6 is human eye regional search structure drawing of device undetermined in Fig. 5；
Fig. 7 be in Fig. 5 human eye positioning and identity device in front decision maker structure chart；
Fig. 8 be in Fig. 5 human eye positioning and identity device in side decision maker structure chart.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and examples
The present invention is further elaborated, and for convenience of description, illustrate only the part related to the embodiment of the present invention.It should manage
Solution, the specific embodiment that this place is described, it is used only for explaining the present invention, is not intended to limit the invention.
Present invention method proposes a kind of human-eye positioning method and system based on Face Detection.The inventive method profit
Reduce hunting zone with Face Detection, a kind of human eye location technology is designed, to lift the ageing of human eye video location technology.
Embodiment one
Fig. 1 is a kind of human-eye positioning method flow chart based on Face Detection of the preferred embodiment of the present invention；Methods described bag
Include following steps：
Step1：For each block in present image, corresponding colour of skin identifier is set；
Specially：Judge whether each block is colour of skin block in present image, if bkt(i, j) is determined as colour of skin block, then sets
It is 1 to put the block colour of skin identifier, i.e. notet(i, j)=1；Otherwise, note is sett(i, j)=0.
Wherein, the decision method of colour of skin block is the disclosed colour of skin decision method in units of block in the industry, no longer superfluous herein
State.
Wherein, bkt(i, j) represents the i-th row jth block (the big I of block is the block of the sizes such as 16x16) of present image,
After bkw, bkh represent that image division is blocking respectively, columns and line number of the image in units of block；notet(i, j) represents current
The colour of skin identifier of i-th row jth block of image.
Step2：If the colour of skin identifier of all pieces of present image is 0, positions without human eye, directly terminate.
Step3：Human eye region undetermined is searched in present image, and corresponding determinating mode is set；
Fig. 2 is Step3 method detaileds flow chart in Fig. 1, is comprised the following steps：
Step31：First look for whether there is and meet condition：notet(i, j)=0 and notet(i-1, j)=1 and notet
The block of (i, j-1)=1 (is designated as sbkt(is, js), referred to as human eye originate decision block, and is, js represent that human eye originates decision block respectively
Ranks number), if then entering Step32；If otherwise terminate.
Wherein, notet(i-1, j) represents the colour of skin identifier of the i-th -1 row jth block of present image；
notet(i, j-1) represents the colour of skin identifier of the i-th -1 piece of row jth of present image；
Step32：Row where human eye originates decision block, which searches whether to exist, meets condition：
notet(i, j)=0 and notet(i-1, j)=1 and notetThe block of (i, j+1)=1 (is designated as dbkt(id, jd) claims
Stop decision block for human eye, id, jd represent that human eye stops the ranks number of decision block respectively), if then entering Step33, otherwise enter
Enter Step34；
Wherein, notet(i, j+1) represents the colour of skin identifier of the i-th+1 piece of row jth of present image；Step33, enter first
The fusion in row region to be determined, i.e., the non-colour of skin block of adjoining that human eye is originated to decision block merge into human eye the firstth area undetermined together
Domain, the non-colour of skin block that human eye is then stopped to decision block adjoining merge into human eye second area undetermined together, then set and judge
Pattern is front determinating mode, subsequently enters Step4.
Step34:The fusion in region to be determined is carried out first, i.e., human eye is originated into the non-colour of skin block of adjoining of decision block together
Human eye first area undetermined is merged into, it is side determinating mode then to set determinating mode；Subsequently enter Step4.
Step4：Human eye positioning, mark are carried out according to determinating mode.
Side determinating mode：
Fig. 3 is determinating mode method detailed flow chart in side in Step4 in Fig. 1；Comprise the following steps：
Step C1：Calculate the brightness Distribution value of human eye first area undetermined
P (k)=sum (sign (y (m, n)=k | y (m, n) ∈ human eyes first area undetermined)).
Wherein, p (k) identifies brightness value k distribution；Sum (variable) represents to sum to variable；Y (m, n) represents m rows n-th
The brightness value of row；
Step C2：The maximum of the brightness Distribution value of eye of asking for help first area undetermined and time maximum, and find corresponding
Brightness value.
Perk1 (k)=max (p (k)), kmax1=arg (k | perk1 (k)),
Perk2 (k)=max (p (k) | p (k) ≠ perk1 (k)), kmax2=arg (k | perk2 (k)).
Wherein, perk1 (k), kmax1Represent that the maximum of brightness Distribution value and the maximum of brightness Distribution value correspond to respectively
Brightness value；perk2(k)、kmax2Represent that the secondary maximum of brightness Distribution value and the secondary maximum of brightness Distribution value correspond to respectively
Brightness value；kmax1=arg (k | perk1 (k)) represent first to seek perk1 (k), then by k values corresponding to perk1 (k), it is assigned to
kmax1, kmax2=arg (k | perk2 (k)) represent first to seek perk2 (k), then by k values corresponding to perk2 (k), it is assigned to kmax2；
max(Variable|Condition) represent to meet the variable maximizing of condition, max (Variable) represent variable maximizing.
Step C3：If abs (kmax1-kmax2)>Thres, then judge that human eye first area undetermined is human eye, and identify and be somebody's turn to do
All pieces are human eye in region, otherwise, are identified as non-human eye.
That is sbkt(i, j)=sign (bkt(i, j) | human eye identification condition), wherein human eye identification condition：
abs(kmax1-kmax2)>Thres and bkt(i, j) ∈ human eyes first area undetermined.
Wherein, abs (variable) represents to take absolute value to variable；sbkt(i, j) represents block bktThe human eye mark ginseng of (i, j)
Number；Thres represents threshold value, typically desirable Thres>50.
Front determinating mode：
Fig. 4 is determinating mode method detailed flow chart in front in Step4 in Fig. 1；Comprise the following steps：
Step Z1：Side is carried out respectively to human eye first area undetermined, human eye second area undetermined to judge, and by phase
The result answered makes a check mark.
Step Z2：If it is human eye that human eye first area undetermined, human eye second area undetermined, which all have block identification, do into
One step confirms.I.e. if lbk1-lbk2=0 and L2-R1≥max(1,1/2*lbk1), then complete human eye positioning；Otherwise, mark figure
As existing without human eye.
Wherein, lbk1、lbk2Represent respectively using block as unit human eye first area undetermined, the row of human eye second area undetermined
Width；L2、R1Represent respectively using block as row number, human eye first area right side row number undetermined on the left of unit human eye second area undetermined.
Embodiment two
Fig. 5 is a kind of human eye positioning system structure figure based on Face Detection of the preferred embodiment of the present invention, the system bag
Include：
Colour of skin block judging treatmenting module, for setting corresponding colour of skin identifier for each block in present image；
Specially：Judge whether each block is colour of skin block in present image, if bkt(i, j) is determined as colour of skin block, then sets
It is 1 to put the block colour of skin identifier, i.e. notet(i, j)=1；Otherwise, note is sett(i, j)=0.
Wherein, the decision method of colour of skin block is the disclosed colour of skin decision method in units of block in the industry, no longer superfluous herein
State.
Wherein, bkt(i, j) represents the i-th row jth block (the big I of block is the block of the sizes such as 16x16) of present image,
After bkw, bkh represent that image division is blocking respectively, columns and line number of the image in units of block；notet(i, j) represents current
The colour of skin identifier of i-th row jth block of image.
Colour of skin identifier judge module, if for judging that the colour of skin identifier of all pieces of present image is 0, need not
Human eye positions, and directly terminates；
Human eye regional search device undetermined, for searching human eye region undetermined in present image, and set and sentence accordingly
Mould-fixed；
Human eye positions and identity device, for carrying out human eye positioning, mark according to determinating mode.
Further, Fig. 6 is human eye regional search structure drawing of device undetermined in Fig. 5；Described device includes：
Human eye starting decision block searches judge module, meets condition for searching whether to exist：notet(i, j)=0 and
notet(i-1, j)=1 and notetThe block of (i, j-1)=1 (is designated as sbkt(is, js), referred to as human eye originate decision block, is, js
The ranks number of human eye starting decision block are represented respectively), search judge module if then entering human eye and stopping decision block；If otherwise tie
Beam.
Wherein, notet(i-1, j) represents the colour of skin identifier of the i-th -1 row jth block of present image；notet(i, j-1) table
Show the colour of skin identifier of the i-th -1 piece of row jth of present image；
Human eye stops decision block and searches judge module, searches whether exist completely for the row where originating decision block in human eye
Sufficient condition：notet(i, j)=0 and notet(i-1, j)=1 and notetThe block of (i, j+1)=1 (is designated as dbkt(id, jd) is referred to as
Human eye stops decision block, and id, jd represent that human eye stops the ranks number of decision block respectively), if then being set into front determinating mode
Module is put, otherwise into side determinating mode setup module；
Wherein, notet(i, j+1) represents the colour of skin identifier of the i-th+1 piece of row jth of present image；
Front determinating mode setup module, for carrying out the fusion in region to be determined first, i.e., originates decision block by human eye
The non-colour of skin block of adjoining merge into human eye first area undetermined together, then by human eye stop decision block adjoining non-colour of skin block one
Rise and merge into human eye second area undetermined, it is front determinating mode then to set determinating mode.
Side determinating mode setup module, for carrying out the fusion in region to be determined first, i.e., originates decision block by human eye
The non-colour of skin block of adjoining merge into human eye first area undetermined together, then set determinating mode be side determinating mode；
Further, the human eye positioning and identity device include front decision maker and side judgment means；Further
Ground, Fig. 7 be in Fig. 5 human eye positioning and identity device in front decision maker structure chart；The front decision maker includes：
Human eye brightness value distribution calculation module in first area undetermined, for calculating human eye first area undetermined
Brightness value distribution p (k)=sum (sign (y (m, n)=k | y (m, n) ∈ human eyes first area undetermined)).
Wherein, p (k) identifies brightness value k distribution；Sum (variable) represents to sum to variable；Y (m, n) represents m rows n-th
The brightness value of row；
Brightness Distribution value is maximum, brightness value acquisition module corresponding to secondary maximum, for eye of asking for help first area undetermined
The maximum of brightness Distribution value and time maximum, and find corresponding brightness value.
Perk1 (k)=max (p (k)), kmax1=arg (k | perk1 (k)),
Perk2 (k)=max (p (k) | p (k) ≠ perk1 (k)), kmax2=arg (k | perk2 (k)).
Wherein, perk1 (k), kmax1Represent that the maximum of brightness Distribution value and the maximum of brightness Distribution value correspond to respectively
Brightness value；perk2(k)、kmax2Represent that the secondary maximum of brightness Distribution value and the secondary maximum of brightness Distribution value correspond to respectively
Brightness value；kmax1=arg (k | perk1 (k)) represent first to seek perk1 (k), then by k values corresponding to perk1 (k), it is assigned to
kmax1, kmax2=arg (k | perk2 (k)) represent first to seek perk2 (k), then by k values corresponding to perk2 (k), it is assigned to kmax2；
max(Variable|Condition) represent to meet the variable maximizing of condition, max (Variable) represent variable maximizing.
First human eye mark module, if for judging abs (kmax1-kmax2)>Thres, then judge human eye the firstth area undetermined
Domain is human eye, and it is human eye to identify in the region all pieces, otherwise, is identified as non-human eye.That is sbkt(i, j)=sign (bkt(i,
J) | human eye identification condition), wherein human eye identification condition：abs(kmax1-kmax2)>Thres and bkt(i, j) ∈ human eyes undetermined first
Region.
Wherein, abs (variable) represents to take absolute value to variable；sbkt(i, j) represents block bktThe human eye mark ginseng of (i, j)
Number；Thres represents threshold value, typically desirable Thres>50.
Further, Fig. 8 be in Fig. 5 human eye positioning and identity device in side decision maker structure chart, the side
Decision maker includes：
Human eye first, second region undetermined side judges mark module, for undetermined to human eye first area undetermined, human eye
Second area carries out a side and judged respectively, and corresponding result is made a check mark.
Second human eye mark module, if for judging that human eye first area undetermined, human eye second area undetermined are all present
Block identification is human eye, then further confirms that.I.e. if lbk1-lbk2=0 and L2-R1≥max(1,1/2*lbk1), then complete people
Eye positioning；Otherwise, identification image exists without human eye.
Wherein, lbk1、lbk2Represent respectively using block as unit human eye first area undetermined, the row of human eye second area undetermined
Width；L2、R1Represent respectively using block as row number, human eye first area right side row number undetermined on the left of unit human eye second area undetermined.
Can it will be understood by those skilled in the art that realizing that all or part of step in above-described embodiment method is
So that by programmed instruction related hardware, come what is completed, described program can be stored in a computer read/write memory medium,
Described storage medium can be ROM, RAM, disk, CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (10)
1. a kind of human-eye positioning method based on Face Detection, it is characterised in that the described method comprises the following steps：
For each block in present image, corresponding colour of skin identifier is set；
If the colour of skin identifier of all pieces of present image is 0, positions without human eye, directly terminate；
Human eye region undetermined is searched in present image, and corresponding determinating mode is set；
Human eye positioning, mark are carried out according to determinating mode.
2. the human-eye positioning method based on Face Detection as claimed in claim 1, it is characterised in that
Described is that the corresponding colour of skin identifier of each block setting is specially in present image：
Judge whether each block is colour of skin block in present image, if bkt(i, j) is determined as colour of skin block, then sets the block colour of skin mark
It is 1 to know symbol, i.e. notet(i, j)=1；Otherwise, note is sett(i, j)=0；
Wherein, bktAfter (i, j) represents that the i-th row jth block of present image, bkw, bkh represent that image division is blocking respectively, image
Columns and line number in units of block；notet(i, j) represents the colour of skin identifier of the i-th row jth block of present image.
3. the human-eye positioning method based on Face Detection as claimed in claim 1, it is characterised in that
It is described that human eye region undetermined is searched in present image, and set the corresponding determinating mode to be specially：
Step31：First look for whether there is and meet condition：notet(i, j)=0 and notet(i-1, j)=1 and notet(i,j-
1) block=1, if the block then is designated as into sbk firstt(is, js), referred to as human eye originate decision block, subsequently into Step32；
If otherwise terminate；
Wherein, is, js represent the ranks number of human eye starting decision block, note respectivelyt(i-1, j) represents the i-th -1 row of present image
The colour of skin identifier of jth block；notet(i, j-1) represents the colour of skin identifier of the i-th -1 piece of row jth of present image；
Step32：Row where human eye originates decision block, which searches whether to exist, meets condition：notet(i, j)=0 and notet
(i-1, j)=1 and notetThe block of (i, j+1)=1, if the block then is designated as into dbk firstt(id, jd), referred to as human eye stop to sentence
Block is determined, subsequently into Step33, if otherwise entering Step34；
Wherein, id, jd represent that human eye stops the ranks number of decision block, note respectivelyt(i, j+1) represents the i-th row the of present image
The colour of skin identifier of j+1 blocks；
Step33, carries out the fusion in region to be determined first, i.e., the non-colour of skin block of adjoining that human eye is originated to decision block merges together
For human eye first area undetermined, the non-colour of skin block that human eye is then stopped to decision block adjoining merges into human eye the secondth area undetermined together
Domain, it is front determinating mode then to set determinating mode, is subsequently entered " carrying out human eye positioning, mark according to determinating mode "；
Step34:The fusion in region to be determined is carried out first, i.e., the non-colour of skin block of adjoining that human eye is originated to decision block merges together
For human eye first area undetermined, it is side determinating mode then to set determinating mode, subsequently enters and " enters pedestrian according to determinating mode
Eye positioning, mark ".
4. the human-eye positioning method based on Face Detection as claimed in claim 1, it is characterised in that
The determinating mode enters including side judgment model and front determinating mode.
5. the human-eye positioning method based on Face Detection as claimed in claim 4, it is characterised in that
Side determinating mode comprises the following steps：
Step C1：Calculate the brightness Distribution value of human eye first area undetermined
P (k)=sum (sign (y (m, n)=k | y (m, n) ∈ human eyes first area undetermined))；
Wherein, p (k) identifies brightness value k distribution；Sum (variable) represents to sum to variable；Y (m, n) represents the row of m rows n-th
Brightness value；
Step C2：The maximum of the brightness Distribution value of eye of asking for help first area undetermined and time maximum, and find corresponding brightness
Value；
Perk1 (k)=max (p (k)), kmax1=arg (k | perk1 (k)),
Perk2 (k)=max (p (k) | p (k) ≠ perk1 (k)), kmax2=arg (k | perk2 (k))；
Wherein, perk1 (k), kmax1Brightness corresponding to the maximum of brightness Distribution value and the maximum of brightness Distribution value is represented respectively
Value；perk2(k)、kmax2Brightness corresponding to the secondary maximum of brightness Distribution value and the secondary maximum of brightness Distribution value is represented respectively
Value；kmax1=arg (k | perk1 (k)) represent first to seek perk1 (k), then by k values corresponding to perk1 (k), it is assigned to kmax1,
kmax2=arg (k | perk2 (k)) represent first to seek perk2 (k), then by k values corresponding to perk2 (k), it is assigned to kmax2；max
(Variable|Condition) represent to meet the variable maximizing of condition, max (Variable) represent variable maximizing；
Step C3：If abs (kmax1-kmax2)>Thres, then judge that human eye first area undetermined is human eye, and identify the region
Interior all pieces are human eye, otherwise, are identified as non-human eye；
Specially：sbkt(i, j)=sign (bkt(i, j) | human eye identification condition), wherein human eye identification condition：abs(kmax1-
kmax2)>Thres and bkt(i, j) ∈ human eyes first area undetermined；
Wherein, abs (variable) represents to take absolute value to variable；sbkt(i, j) represents block bktThe human eye identification parameter of (i, j)；
Thres represents threshold value, Thres>50.
6. the human-eye positioning method based on Face Detection as claimed in claim 4, it is characterised in that
Front determinating mode comprises the following steps：
Step Z1：A side is carried out respectively to human eye first area undetermined, human eye second area undetermined to judge, and will be corresponding
As a result make a check mark；
Step Z2：If it is human eye that human eye first area undetermined, human eye second area undetermined, which all have block identification, do further
Confirm；Specially：If lbk1-lbk2=0 and L2-R1≥max(1,1/2*lbk1), then complete human eye positioning；Otherwise, mark figure
As existing without human eye；
Wherein, lbk1、lbk2Represent respectively using block as unit human eye first area undetermined, the column width of human eye second area undetermined；
L2、R1Represent respectively using block as row number, human eye first area right side row number undetermined on the left of unit human eye second area undetermined.
7. a kind of human eye alignment system based on Face Detection, it is characterised in that the system includes：
Colour of skin block judging treatmenting module, for judging whether each block is colour of skin block in present image, if bkt(i, j) is determined as
Colour of skin block, then it is 1 to set the block colour of skin identifier, i.e. notet(i, j)=1；Otherwise, note is sett(i, j)=0；
Wherein, bktAfter (i, j) represents that the i-th row jth block of present image, bkw, bkh represent that image division is blocking respectively, image
Columns and line number in units of block；notet(i, j) represents the colour of skin identifier of the i-th row jth block of present image.
Colour of skin identifier judge module, if for judging that the colour of skin identifier of all pieces of present image is 0, without human eye
Positioning, directly terminates；
Human eye regional search device undetermined, human eye region undetermined is searched in present image, and corresponding determinating mode is set；
Human eye positions and identity device, for carrying out human eye positioning, mark according to determinating mode.
8. the human eye alignment system based on Face Detection as claimed in claim 7, it is characterised in that human eye regional search undetermined
Device includes：
Human eye starting decision block searches judge module, meets condition for searching whether to exist：notet(i, j)=0 and notet
(i-1, j)=1 and notetThe block of (i, j-1)=1, is designated as sbkt(is, js), referred to as human eye originate decision block, if then entering
Human eye stops decision block and searches judge module；If otherwise terminate；
Wherein, is, js represent the ranks number of human eye starting decision block, note respectivelyt(i-1, j) represents the i-th -1 row of present image
The colour of skin identifier of jth block；notet(i, j-1) represents the colour of skin identifier of the i-th -1 piece of row jth of present image；
Human eye stops decision block and searches judge module, meets bar for searching whether to exist in the row where human eye starting decision block
Part：notet(i, j)=0 and notet(i-1, j)=1 and notetThe block of (i, j+1)=1, is designated as dbkt(id, jd), referred to as people
Eye stops decision block, if then entering front determinating mode setup module, otherwise into side determinating mode setup module；
Wherein, id, jd represent that human eye stops the ranks number of decision block, note respectivelyt(i, j+1) represents the i-th row the of present image
The colour of skin identifier of j+1 blocks；
Front determinating mode setup module, for carrying out the fusion in region to be determined first, i.e., human eye is originated to the neighbour of decision block
Connect non-colour of skin block and merge into human eye first area undetermined together, the non-colour of skin block that human eye is then stopped to decision block adjoining is closed together
And be human eye second area undetermined, it is front determinating mode then to set determinating mode；
Side determinating mode setup module, for carrying out the fusion in region to be determined first, i.e., human eye is originated to the neighbour of decision block
Connect non-colour of skin block and merge into human eye first area undetermined together, it is side determinating mode then to set determinating mode.
9. the human eye alignment system based on Face Detection as claimed in claim 7, it is characterised in that the human eye positioning and mark
Identification device includes front decision maker and side judgment means.
10. the human eye alignment system based on Face Detection as claimed in claim 9, it is characterised in that
The front decision maker includes：
Human eye brightness value distribution calculation module in first area undetermined, for calculating the brightness value distribution p of human eye first area undetermined
(k)=sum (sign (y (m, n)=k | y (m, n) ∈ human eyes first area undetermined))；
Wherein, p (k) identifies brightness value k distribution；Sum (variable) represents to sum to variable；Y (m, n) represents the row of m rows n-th
Brightness value；
Brightness Distribution value is maximum, brightness value acquisition module corresponding to secondary maximum, the brightness for eye of asking for help first area undetermined
The maximum of Distribution value and time maximum, and find corresponding brightness value；
Perk1 (k)=max (p (k)), kmax1=arg (k | perk1 (k)),
Perk2 (k)=max (p (k) | p (k) ≠ perk1 (k)), kmax2=arg (k | perk2 (k)).
Wherein, perk1 (k), kmax1Brightness corresponding to the maximum of brightness Distribution value and the maximum of brightness Distribution value is represented respectively
Value；perk2(k)、kmax2Brightness corresponding to the secondary maximum of brightness Distribution value and the secondary maximum of brightness Distribution value is represented respectively
Value；kmax1=arg (k | perk1 (k)) represent first to seek perk1 (k), then by k values corresponding to perk1 (k), it is assigned to kmax1,
kmax2=arg (k | perk2 (k)) represent first to seek perk2 (k), then by k values corresponding to perk2 (k), it is assigned to kmax2；max
(Variable|Condition) represent to meet the variable maximizing of condition, max (Variable) represent variable maximizing；
First human eye mark module, if for judging abs (kmax1-kmax2)>Thres, then judge that human eye first area undetermined is
Human eye, and it is human eye to identify in the region all pieces, otherwise, is identified as non-human eye；
Specially：sbkt(i, j)=sign (bkt(i, j) | human eye identification condition), wherein human eye identification condition：
abs(kmax1-kmax2)>Thres and bkt(i, j) ∈ human eyes first area undetermined；
Wherein, abs (variable) represents to take absolute value to variable；sbkt(i, j) represents block bktThe human eye identification parameter of (i, j)；
Thres represents threshold value, Thres>50.
Side decision maker includes：
Human eye first, second region undetermined side judges mark module, for human eye first area undetermined, human eye undetermined second
Region carries out a side and judged respectively, and corresponding result is made a check mark；
Second human eye mark module, if for judging that human eye first area undetermined, human eye second area undetermined all have block mark
Know for human eye, then further confirm that, be specially：If lbk1-lbk2=0 and L2-R1≥max(1,1/2*lbk1), then complete
Human eye positions；Otherwise, identification image exists without human eye；
Wherein, lbk1、lbk2Represent respectively using block as unit human eye first area undetermined, the column width of human eye second area undetermined；
L2、R1Represent respectively using block as row number, human eye first area right side row number undetermined on the left of unit human eye second area undetermined.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710600994.4A CN107516067B (en) | 2017-07-21 | 2017-07-21 | Human eye positioning method and system based on skin color detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710600994.4A CN107516067B (en) | 2017-07-21 | 2017-07-21 | Human eye positioning method and system based on skin color detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107516067A true CN107516067A (en) | 2017-12-26 |
| CN107516067B CN107516067B (en) | 2020-08-04 |
Family
ID=60722650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710600994.4A Active CN107516067B (en) | 2017-07-21 | 2017-07-21 | Human eye positioning method and system based on skin color detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107516067B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110781840A (en) * | 2019-10-29 | 2020-02-11 | 深圳市梦网百科信息技术有限公司 | Nose positioning method and system based on skin color detection |
| CN111461073A (en) * | 2020-05-06 | 2020-07-28 | 深圳市梦网视讯有限公司 | Reverse face detection method, system and equipment based on nose positioning |
| CN111626143A (en) * | 2020-05-06 | 2020-09-04 | 深圳市梦网视讯有限公司 | Reverse face detection method, system and equipment based on eye positioning |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1686051A (en) * | 2005-05-08 | 2005-10-26 | 上海交通大学 | Canthus and pupil location method based on VPP and improved SUSAN |
| CN101059836A (en) * | 2007-06-01 | 2007-10-24 | 华南理工大学 | Human eye positioning and human eye state recognition method |
| CN103218615A (en) * | 2013-04-17 | 2013-07-24 | 哈尔滨工业大学深圳研究生院 | Face judgment method |
| CN104463102A (en) * | 2014-11-07 | 2015-03-25 | 中国石油大学(华东) | Human eye positioning method based on point-by-point scanning |
| CN106682094A (en) * | 2016-12-01 | 2017-05-17 | 深圳百科信息技术有限公司 | Human face video retrieval method and system |
-
2017
- 2017-07-21 CN CN201710600994.4A patent/CN107516067B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1686051A (en) * | 2005-05-08 | 2005-10-26 | 上海交通大学 | Canthus and pupil location method based on VPP and improved SUSAN |
| CN101059836A (en) * | 2007-06-01 | 2007-10-24 | 华南理工大学 | Human eye positioning and human eye state recognition method |
| CN103218615A (en) * | 2013-04-17 | 2013-07-24 | 哈尔滨工业大学深圳研究生院 | Face judgment method |
| CN104463102A (en) * | 2014-11-07 | 2015-03-25 | 中国石油大学(华东) | Human eye positioning method based on point-by-point scanning |
| CN106682094A (en) * | 2016-12-01 | 2017-05-17 | 深圳百科信息技术有限公司 | Human face video retrieval method and system |
Non-Patent Citations (2)
| Title |
|---|
| 全星慧: "基于肤色模型与眼睛定位的人脸检测方法", 《科学技术与工程》 * |
| 王罡: "一种有效的唇部特征定位算法", 《科技资讯》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110781840A (en) * | 2019-10-29 | 2020-02-11 | 深圳市梦网百科信息技术有限公司 | Nose positioning method and system based on skin color detection |
| CN110781840B (en) * | 2019-10-29 | 2022-08-26 | 深圳市梦网视讯有限公司 | Nose positioning method and system based on skin color detection |
| CN111461073A (en) * | 2020-05-06 | 2020-07-28 | 深圳市梦网视讯有限公司 | Reverse face detection method, system and equipment based on nose positioning |
| CN111626143A (en) * | 2020-05-06 | 2020-09-04 | 深圳市梦网视讯有限公司 | Reverse face detection method, system and equipment based on eye positioning |
| CN111626143B (en) * | 2020-05-06 | 2023-12-08 | 深圳市梦网视讯有限公司 | Reverse face detection method, system and equipment based on eye positioning |
| CN111461073B (en) * | 2020-05-06 | 2023-12-08 | 深圳市梦网视讯有限公司 | Reverse face detection method, system and equipment based on nose positioning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107516067B (en) | 2020-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359552B (en) | Efficient cross-camera bidirectional pedestrian tracking method | |
| Tang et al. | Weakly supervised salient object detection with spatiotemporal cascade neural networks | |
| CN107516067A (en) | A kind of human-eye positioning method and system based on Face Detection | |
| CN108830252B (en) | Convolutional neural network human body action recognition method fusing global space-time characteristics | |
| CN109635728B (en) | Heterogeneous pedestrian re-identification method based on asymmetric metric learning | |
| CN107506691A (en) | A kind of lip localization method and system based on Face Detection | |
| CN109784130A (en) | Pedestrian recognition methods and its device and equipment again | |
| Biel et al. | You are known by how you vlog: Personality impressions and nonverbal behavior in youtube | |
| CN107563278A (en) | A kind of quick eye lip localization method and system based on Face Detection | |
| JP2019075116A (en) | Method for acquiring bounding box corresponding to object on image by using cnn (convolutional neural network) including tracking network | |
| CN105117692A (en) | Real-time face identification method and system based on deep learning | |
| CN105095870A (en) | Pedestrian re-recognition method based on transfer learning | |
| CN110807402B (en) | Facial feature positioning method, system and terminal equipment based on skin color detection | |
| CN102708182A (en) | Rapid video concentration abstracting method | |
| CN109934104A (en) | The pedestrian retrieval method and system across camera lens identified again based on pedestrian | |
| CN107481222A (en) | A kind of quick eye lip video locating method and system based on Face Detection | |
| Ding et al. | Towards universal physical attacks on single object tracking | |
| Yan et al. | Automatic annotation of tennis games: An integration of audio, vision, and learning | |
| CN109446967A (en) | A kind of method for detecting human face and system based on compression information | |
| CN110390308A (en) | It is a kind of to fight the video behavior recognition methods for generating network based on space-time | |
| CN109871790A (en) | A kind of video decolorizing method based on hybrid production style | |
| CN106991358A (en) | The algorithm that automatic identification football match based on panoramic video is scored | |
| CN109697727A (en) | Method for tracking target, system and storage medium based on correlation filtering and metric learning | |
| Fang et al. | Traffic police gesture recognition by pose graph convolutional networks | |
| Zhao et al. | Saliency-guided video classification via adaptively weighted learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 518057 Guangdong city of Shenzhen province Nanshan District Guangdong streets high in the four Longtaili Technology Building Room 325 No. 30 Applicant after: Shenzhen mengwang video Co., Ltd Address before: 518057 Guangdong city of Shenzhen province Nanshan District Guangdong streets high in the four Longtaili Technology Building Room 325 No. 30 Applicant before: SHENZHEN MONTNETS ENCYCLOPEDIA INFORMATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |