CN107832692A - A kind of face image processing process and device - Google Patents

A kind of face image processing process and device Download PDF

Info

Publication number
CN107832692A
CN107832692A CN201711043786.5A CN201711043786A CN107832692A CN 107832692 A CN107832692 A CN 107832692A CN 201711043786 A CN201711043786 A CN 201711043786A CN 107832692 A CN107832692 A CN 107832692A
Authority
CN
China
Prior art keywords
color
feature
pixel
feature contour
facial image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201711043786.5A
Other languages
Chinese (zh)
Inventor
张家重
董毅
王玉奎
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Inspur Financial Information Technology Co Ltd
Original Assignee
Inspur Financial Information Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Inspur Financial Information Technology Co Ltd filed Critical Inspur Financial Information Technology Co Ltd
Priority to CN201711043786.5A priority Critical patent/CN107832692A/en
Publication of CN107832692A publication Critical patent/CN107832692A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/162—Detection; Localisation; Normalisation using pixel segmentation or colour matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships

Landscapes

  • Engineering & Computer Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Library & Information Science (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention provides a kind of face image processing process and device, wherein, this method includes：Data space is pre-created, in addition to：Obtain pending facial image；Determine the color-values and positional information of each pixel in the pending facial image；According to the color-values and positional information of each pixel in the pending facial image, each pixel in the pending facial image is loaded into the data space, generates at least two color layers；According at least two color layer, at least one feature contour is determined；At least one condition code is generated for feature contour each described.Scheme provided by the invention can reduce the data volume after pending face image processing.

Description

A kind of face image processing process and device
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of face image processing process and device.
Background technology
In recent years, recognition of face turns into a kind of important way for safeguarding information security.However, with facial image to be identified Quantity increases, the key factor for being treated as influenceing recognition of face efficiency of facial image, gradually causes the pass of technical staff Note.
In the prior art, typically by face image processing into gray-scale figure, for image recognition.
But the data volume for the gray-scale figure for handling to obtain by this method is larger.
The content of the invention
The embodiments of the invention provide a kind of face image processing process and device, the feature for handling to obtain by this method The data volume of code is smaller than the data volume of gray-scale figure.
In a first aspect, the embodiments of the invention provide a kind of face image processing process, data space is pre-created, is wrapped Include：
Obtain pending facial image；
Determine the color-values and positional information of each pixel in the pending facial image；
According to the color-values and positional information of each pixel in the pending facial image, by the pending face figure Each pixel is loaded into the data space as in, generates at least two color layers；
According at least two color layer, at least one feature contour is determined；
At least one condition code is generated for feature contour each described.
Preferably,
The data space includes the space coordinates being made up of X-axis, Y-axis, Z axis；
The color-values and positional information according to each pixel in the pending facial image, by the pending people Each pixel is loaded into the data space in face image, generates at least two color layers, including：
For each pixel in the pending facial image, it is performed both by：According to the color-values of current pixel, it is determined that described The Z axis coordinate of current pixel；According to the positional information of the current pixel, the X-axis coordinate and Y-axis for determining the current pixel are sat Mark；According to the X-axis coordinate, Y-axis coordinate and Z axis coordinate, the current pixel is loaded into the data space, generation is extremely Few two color layers；
Wherein, color-values identical pixel is located at same color layer.
Preferably,
The pending facial image, including：Black white image；
The color-values, including：0th, 1, wherein, described 0 is used to characterize black, and described 1 is used to characterize white；
It is described that at least one feature contour is determined according at least two color layer, including：
In at least two color layer, the color layer that color-values are 0 is determined；
Determine at least one feature contour that the color layer that color-values are 0 is formed.
Preferably,
It is described to generate at least one condition code for each described feature contour, including：
For feature contour each described, it is performed both by：The parameter information of current signature profile is determined, is determined described current The related information of feature contour, believed according to the association of the parameter information of the current signature profile and the current signature profile Breath, it is that each described feature contour generates at least one condition code；
Wherein, the parameter information includes：The Breadth Maximum of feature contour, the maximum height of feature contour, the spy Levy the Breadth Maximum of the profile and ratio of maximum height of the feature contour, the area of the shape of feature contour and feature contour In the combination of any one or more；
The related information includes：Distance with fisrt feature profile, with the distance of second feature profile and it is described with The combination of any one or more in the distance of fisrt feature profile and the described and ratio of the distance of second feature profile.
Preferably,
Further comprise：Pre-set the corresponding relation of condition code section and label；
It is described generate at least one condition code for each described feature contour after, further comprise：
For feature contour each described, it is performed both by：Determine the feature where each condition code of current signature profile Code section, according to described document information and the corresponding relation of label, determines label corresponding to each condition code of current signature profile；
According to label corresponding to each condition code of each feature contour, rope is established for the pending facial image Draw.
Second aspect, the embodiments of the invention provide a kind of face image processing device, including：
Creating unit, for creating data space,
Determining unit, for obtaining pending facial image, determine the color of each pixel in the pending facial image Coloured silk value and positional information；
Loading unit, the color for each pixel in the pending facial image that is determined according to the determining unit Value and positional information, the data that each pixel in the pending facial image is loaded into the creating unit establishment are empty Between in, generate at least two color layers；
Processing unit, at least two color layer generated according to the loading unit, determine at least one spy Profile is levied, is that each described feature contour generates at least one condition code.
Preferably,
The data space includes the space coordinates being made up of X-axis, Y-axis, Z axis；
The loading unit, for for each pixel in the pending facial image, being performed both by：According to current pixel Color-values, determine the Z axis coordinate of the current pixel；According to the positional information of the current pixel, the current picture is determined The X-axis coordinate and Y-axis coordinate of element；According to the X-axis coordinate, Y-axis coordinate and Z axis coordinate, the current pixel is loaded into institute State in data space, generate at least two color layers；Wherein, color-values identical pixel is located at same color layer.
Preferably,
The pending facial image, including：Black white image；
The color-values, including：0th, 1, wherein, described 0 is used to characterize black, and described 1 is used to characterize white；
The processing unit, at least two color layer, determine color-values be 0 color layer；Determine color At least one feature contour that the color layer that coloured silk value is 0 is formed.
Preferably,
The processing unit, for for feature contour each described, being performed both by：Determine the parameter of current signature profile Information, the related information of the current signature profile is determined, according to the parameter information of the current signature profile and described current The related information of feature contour, it is that each described feature contour generates at least one condition code；
Wherein, the parameter information includes：The Breadth Maximum of feature contour, the maximum height of feature contour, the spy Levy the Breadth Maximum of the profile and ratio of maximum height of the feature contour, the area of the shape of feature contour and feature contour In the combination of any one or more；
The related information includes：Distance with fisrt feature profile, with the distance of second feature profile and it is described with The combination of any one or more in the distance of fisrt feature profile and the described and ratio of the distance of second feature profile.
Preferably,
Further comprise：
Setting unit, for setting the corresponding relation in condition code section and label；
Indexing units, for for feature contour each described, being performed both by：Determine each feature of current signature profile Condition code section where code, the described document information and the corresponding relation of label set according to the setting unit, it is determined that currently Label corresponding to each condition code of feature contour；According to label corresponding to each condition code of each feature contour, it is The pending facial image establishes index.
The embodiments of the invention provide a kind of face image processing process and device, wherein, this method is according to pending people The color-values and positional information of each pixel of face image, pending facial image is loaded into data space, formation and color-values Corresponding color layer, at least one feature contour of pending facial image is determined by different color layers, and is each The feature contour generates at least one condition code.In summary, by this method can by pending face image processing into Different condition codes, the data volume of this feature code is smaller than the data volume of gray-scale figure, can reduce carrying cost, improves image recognition Efficiency.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are the present invention Some embodiments, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis These accompanying drawings obtain other accompanying drawings.
Fig. 1 is a kind of flow chart for face image processing process that one embodiment of the invention provides；
Fig. 2 is a kind of flow chart for face image processing process that another embodiment of the present invention provides；
Fig. 3 is a kind of structural representation for face image processing device that one embodiment of the invention provides；
Fig. 4 is a kind of structural representation for face image processing device that another embodiment of the present invention provides.
Embodiment
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is Part of the embodiment of the present invention, rather than whole embodiments, based on the embodiment in the present invention, those of ordinary skill in the art The every other embodiment obtained on the premise of creative work is not made, belongs to the scope of protection of the invention.
As shown in figure 1, the embodiments of the invention provide a kind of face image processing process, this method can include following step Suddenly：
Step 101：Create data space；
Step 102：Obtain pending facial image；
Step 103：Determine the color-values and positional information of each pixel in pending facial image；
Step 104：According to the color-values and positional information of each pixel in pending facial image, by pending face figure Each pixel is loaded into data space as in, generates at least two color layers；
Step 105：According at least two color layers, at least one feature contour is determined；
Step 106：At least one condition code is generated for each feature contour.
In the embodiment of the present invention shown in Fig. 1, this method according to the color-values of each pixel of pending facial image and Positional information, pending facial image is loaded into data space, color layer corresponding with color-values is formed, passes through different colors Color layer determines at least one feature contour of pending facial image, and generates at least one feature for each feature contour Code.To sum up, can be by pending face image processing into different condition codes by this method, the data volume of this feature code is than ash The data volume of rank figure is small, can reduce carrying cost, improves the efficiency of image recognition.
In one embodiment of the invention, in order to be made a distinction according to color-values to pixel, it has been determined that each organ pair The feature contour answered, data space include the space coordinates being made up of X-axis, Y-axis, Z axis；
, will be each in pending facial image according to the color-values and positional information of each pixel in pending facial image Pixel is loaded into data space, generates at least two color layers, including：
For each pixel in pending facial image, it is performed both by：According to the color-values of current pixel, current pixel is determined Z axis coordinate；According to the positional information of current pixel, the X-axis coordinate and Y-axis coordinate of current pixel are determined；According to X-axis coordinate, Y Axial coordinate and Z axis coordinate, current pixel is loaded into data space, generates at least two color layers；
Wherein, color-values identical pixel is located at same color layer.
Because the color-values of pixel can be indicated by binary number, therefore, in practical application scene, Ke Yitong The difference of color-values is crossed, different pixels is divided into different color layers.
Further, in one embodiment of the invention, pending facial image, including：Black white image；
Color-values, including：0th, 1, wherein, 0 is used to characterize black, and 1 is used to characterize white；
According at least two color layers, at least one feature contour is determined, including：
In at least two color layers, the color layer that color-values are 0 is determined；
Determine at least one feature contour that the color layer that color-values are 0 is formed.
Pending facial image can be photochrome, or gray-scale figure, or black-and-white photograph, in practical application field Photochrome is typically processed into gray-scale figure or black-and-white photograph in scape.Black-and-white photograph only has two kinds of color-values, and respectively 0 and 1, Corresponding two color layers, and gray-scale figure may have multiple color-values, for example, 00,01,10 and 11, corresponding four color layers.Often One color layer can form at least one feature contour.
In one embodiment of the invention, in order to characterize each feature contour, for each feature contour generate to A few condition code, including：
For each feature contour, it is performed both by：The parameter information of current signature profile is determined, determines current signature profile Related information, be each feature wheel according to the parameter information of current signature profile and the related information of current signature profile Exterior feature generates at least one condition code；
Wherein, parameter information includes：The Breadth Maximum of feature contour, the maximum height of feature contour, feature contour Any one in the ratio of the maximum height of Breadth Maximum and feature contour, the shape of feature contour and the area of feature contour or A variety of combinations；
Related information includes：Distance with fisrt feature profile, distance and and fisrt feature with second feature profile The distance of profile with the combination of any one or more in the ratio of the distance of second feature profile.
Feature contour includes：The face contour of people, eye profile, nasal contours, mouth profile, ear's profile etc..
By taking eye as an example, parameter information includes：Eye is high, eye is wide and eye is high and the wide ratio of eye；Related information includes：Two Between the distance between the distance between distance, two centres and place between the eyebrows ratio, eyes and nose between ratio, eyes and mouth away from From ratio.Then the condition code of eye can include：Eye is high, eye is wide, eye is high and the wide ratio of eye, two interocular distances, two centres It is any one in the distance between the distance between the distance between place between the eyebrows ratio, eyes and nose ratio, eyes and mouth ratio Kind or a variety of combinations.For example, corresponding two condition codes of eye are the high A1 of the eye and wide A2 of eye.
In one embodiment of the invention, for the ease of being retrieved according to the condition code of each feature contour, improve The efficiency of image recognition, pre-set the corresponding relation of condition code section and label；
After at least one condition code is generated for each feature contour, further comprise：
For each feature contour, it is performed both by：Determine the condition code area where each condition code of current signature profile Between, according to condition code and the corresponding relation of label, determine label corresponding to each condition code of current signature profile；
According to label corresponding to each condition code of each feature contour, index is established for pending facial image.
One feature contour can include multiple labels, for example, eye label includes：Peach blossom eye, apricot eye, slim eye etc., Facial label includes：State's word face, oval face etc..
By taking eye profile as an example, eye corresponding to peach blossom eye high with the wide ratio section of eye be a-b, eye corresponding to apricot eye it is high and The wide ratio section of eye be c-d, and eye corresponding to slim eye is high and the wide ratio section of eye is e-f, the eye of pending facial image The high and wide ratio of eye is x, and x is located at a-b, then is that the eye of pending facial image adds label peach blossom eye.The like, treat The different characteristic profile of processing facial image can correspond to multiple labels, for example, the label of pending facial image includes：Peach blossom Eye, oval face, arched eyebrows.According to the label of each pending facial image, index is established, for example, waiting to locate with peach blossom eye Reason facial image includes S1, S2, S3, and the pending facial image with apricot eye includes S4, has the pending face of slim eye Image includes S5, S6.When user is retrieved using keyword " peach blossom eye ", will retrieve pending facial image S1, S2, S3。
As shown in Fig. 2 the embodiment of the present invention by taking black white image as an example, is carried out in detail to face image processing process Bright, this method includes：
Step 201：The corresponding relation of condition code section and label is set.
For different condition codes, the corresponding relation of corresponding different condition code section and label, for example, the high section of eye with The corresponding relation of the corresponding relation of label, the wide section of eye and label.
The present embodiment illustrates only by taking mouth as an example.
Table 1
Mouth height and the wide ratio section of mouth Label
g-h Square mouth
k-l Blow the fire mouth
m-n Wrinkle mouth
Step 202：Data space is created, data space includes the space coordinates being made up of X-axis, Y-axis, Z axis.
Step 203：Obtain pending facial image.
The pending facial image is black white image.
Step 204：Determine the color-values and positional information of each pixel in pending facial image.
For black white image, color-values, including：0th, 1, wherein, 0 is used to characterize black, and 1 is used to characterize white.
Step 205：For each pixel in pending facial image, it is performed both by：According to the color-values of current pixel, it is determined that The Z axis coordinate of current pixel；According to the positional information of current pixel, the X-axis coordinate and Y-axis coordinate of current pixel are determined；According to X Axial coordinate, Y-axis coordinate and Z axis coordinate, current pixel is loaded into data space, generates two color layers；Wherein, color-values Identical pixel is located at same color layer.
Step 206：According to two color layers, at least one feature contour is determined.
In at least two color layers, the color layer that color-values are 0 is determined；Determine the color layer formation that color-values are 0 At least one feature contour.It should be noted that feature contour can be determined according to any one color layer, still, work as color When layer is more, the feature contour application condition only determined by a color layer is big, can combine different color layers and determine At least one feature contour.
In the present embodiment, feature contour includes：Mouth profile, eye profile, face contour, nasal contours, ear's wheel It is wide.
Step 207：For each feature contour, it is performed both by：The parameter information of current signature profile is determined, it is determined that currently The related information of feature contour, it is each according to the parameter information of current signature profile and the related information of current signature profile Individual feature contour generates at least one condition code.
Wherein, parameter information includes：The Breadth Maximum of feature contour, the maximum height of feature contour, feature contour Any one in the ratio of the maximum height of Breadth Maximum and feature contour, the shape of feature contour and the area of feature contour or A variety of combinations；
Related information includes：Distance with fisrt feature profile, distance and and fisrt feature with second feature profile The distance of profile with the combination of any one or more in the ratio of the distance of second feature profile.
By taking mouth profile as an example, parameter information includes：Mouth height and the wide ratio Y1 of mouth, the high Y2 of mouth, the wide Y3 of mouth；
Related information includes：The distance between eyes and mouth ratio Y4.
The condition code of mouth is the distance between mouth height and the wide ratio Y1 of mouth, the high Y2 of mouth, the wide Y3 of mouth, eyes and mouth ratio Y4。
Step 208：For each feature contour, it is performed both by：Where determining each condition code of current signature profile Condition code section, according to condition code and the corresponding relation of label, determine label corresponding to each condition code of current signature profile.
It is high with exemplified by the wide ratio Y1 of mouth, according to table 1, determining the mouth that section where Y1 is g-h, the then black white image by mouth Portion's label is square mouth.
Step 209：According to label corresponding to each condition code of each feature contour, rope is established for pending facial image Draw.
For example, it is that pending facial image establishes index according to label " square mouth, state's word face, aquiline nose ", i.e., when user is defeated When entering keyword " square mouth ", the pending facial image will be retrieved；Or when facial image to be identified has label When " square mouth ", it will match with the pending facial image.
As shown in figure 3, the embodiments of the invention provide a kind of face image processing device, including：
Creating unit 301, for creating data space,
Determining unit 302, for obtaining pending facial image, determine the color of each pixel in pending facial image Value and positional information；
Loading unit 303, the color-values for each pixel in the pending facial image that is determined according to determining unit 302 And positional information, each pixel in pending facial image is loaded into the data space that creating unit 301 creates, generation is extremely Few two color layers；
Processing unit 304, at least two color layers generated according to loading unit 303, determine at least one feature Profile, at least one condition code is generated for each feature contour.
In one embodiment of the invention, data space includes the space coordinates being made up of X-axis, Y-axis, Z axis；
Loading unit 303, for for each pixel in pending facial image, being performed both by：According to the color of current pixel Coloured silk value, determine the Z axis coordinate of current pixel；According to the positional information of current pixel, the X-axis coordinate and Y-axis of current pixel are determined Coordinate；According to X-axis coordinate, Y-axis coordinate and Z axis coordinate, current pixel is loaded into data space, generates at least two colors Layer；Wherein, color-values identical pixel is located at same color layer.
In one embodiment of the invention, pending facial image, including：Black white image；
Color-values, including：0th, 1, wherein, 0 is used to characterize black, and 1 is used to characterize white；
Processing unit 304, at least two color layers, determine color-values be 0 color layer；Determine that color-values are At least one feature contour that 0 color layer is formed.
In one embodiment of the invention, processing unit 304, for for each feature contour, being performed both by：It is determined that The parameter information of current signature profile, the related information of current signature profile is determined, according to the parameter information of current signature profile With the related information of current signature profile, at least one condition code is generated for each feature contour；
Wherein, parameter information includes：The Breadth Maximum of feature contour, the maximum height of feature contour, feature contour Any one in the ratio of the maximum height of Breadth Maximum and feature contour, the shape of feature contour and the area of feature contour or A variety of combinations；
Related information includes：Distance with fisrt feature profile, distance and and fisrt feature with second feature profile The distance of profile with the combination of any one or more in the ratio of the distance of second feature profile.
In one embodiment of the invention, as shown in figure 4, the device also includes：Setting unit 305, for setting spy Levy the corresponding relation of code section and label；
Indexing units 306, for for each feature contour, being performed both by：Determine each feature of current signature profile Condition code section where code, the condition code and the corresponding relation of label set according to setting unit 305, determines current signature wheel Label corresponding to wide each condition code；It is pending face according to label corresponding to each condition code of each feature contour Image establishes index.
The contents such as the information exchange between each unit, implementation procedure in said apparatus, due to implementing with the inventive method Example is based on same design, and particular content can be found in the narration in the inventive method embodiment, and here is omitted.
The embodiments of the invention provide a kind of computer-readable recording medium, including execute instruction, when the computing device of storage control During execute instruction, the method for any of the above-described embodiment of storage control execution.
The embodiments of the invention provide a kind of storage control, including：Processor, memory and bus；
Memory is used to store execute instruction, and processor is connected with memory by bus, when storage control is run, The execute instruction of computing device memory storage, so that the method that storage control performs any of the above-described embodiment.
To sum up, each embodiment of the present invention at least has the effect that：
1st, in embodiments of the present invention, this method is believed according to the color-values of each pixel of pending facial image and position Breath, pending facial image is loaded into data space, forms color layer corresponding with color-values, it is true by different color layers At least one feature contour of fixed pending facial image, and generate at least one condition code for each feature contour.To sum up, Can be by pending face image processing into different condition codes by this method, the number of the data volume of this feature code than gray-scale figure It is small according to measuring, carrying cost can be reduced, improves the efficiency of image recognition.
2nd, in embodiments of the present invention, profile addition label can be characterized by condition code, and passes through each feature wheel Label corresponding to exterior feature forms index, and the index can provide the user query function, and can improve the efficiency of image recognition.
It should be noted that herein, such as first and second etc relational terms are used merely to an entity Or operation makes a distinction with another entity or operation, and not necessarily require or imply and exist between these entities or operation Any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant be intended to it is non- It is exclusive to include, so that process, method, article or equipment including a series of elements not only include those key elements, But also the other element including being not expressly set out, or also include solid by this process, method, article or equipment Some key elements.In the absence of more restrictions, by sentence " including the key element that a 〃 〃 " is limited, it is not excluded that Other identical factor in the process including the key element, method, article or equipment also be present.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above method embodiment can pass through Programmed instruction related hardware is completed, and foregoing program can be stored in computer-readable storage medium, the program Upon execution, the step of execution includes above method embodiment；And foregoing storage medium includes：ROM, RAM, magnetic disc or light Disk etc. is various can be with the medium of store program codes.
It is last it should be noted that：Presently preferred embodiments of the present invention is the foregoing is only, is merely to illustrate the skill of the present invention Art scheme, is not intended to limit the scope of the present invention.Any modification for being made within the spirit and principles of the invention, Equivalent substitution, improvement etc., are all contained in protection scope of the present invention.

Claims (10)

  1. A kind of 1. face image processing process, it is characterised in that data space is pre-created, in addition to：
    Obtain pending facial image；
    Determine the color-values and positional information of each pixel in the pending facial image；
    According to the color-values and positional information of each pixel in the pending facial image, by the pending facial image Each pixel is loaded into the data space, generates at least two color layers；
    According at least two color layer, at least one feature contour is determined；
    At least one condition code is generated for feature contour each described.
  2. 2. face image processing process according to claim 1, it is characterised in that
    The data space includes the space coordinates being made up of X-axis, Y-axis, Z axis；
    The color-values and positional information according to each pixel in the pending facial image, by the pending face figure Each pixel is loaded into the data space as in, generates at least two color layers, including：
    For each pixel in the pending facial image, it is performed both by：According to the color-values of current pixel, determine described current The Z axis coordinate of pixel；According to the positional information of the current pixel, the X-axis coordinate and Y-axis coordinate of the current pixel are determined； According to the X-axis coordinate, Y-axis coordinate and Z axis coordinate, the current pixel is loaded into the data space, generation is at least Two color layers；
    Wherein, color-values identical pixel is located at same color layer.
  3. 3. face image processing process according to claim 2, it is characterised in that
    The pending facial image, including：Black white image；
    The color-values, including：0th, 1, wherein, described 0 is used to characterize black, and described 1 is used to characterize white；
    It is described that at least one feature contour is determined according at least two color layer, including：
    In at least two color layer, the color layer that color-values are 0 is determined；
    Determine at least one feature contour that the color layer that color-values are 0 is formed.
  4. 4. face image processing process according to claim 1, it is characterised in that
    It is described to generate at least one condition code for each described feature contour, including：
    For feature contour each described, it is performed both by：The parameter information of current signature profile is determined, determines the current signature The related information of profile, according to the parameter information of the current signature profile and the related information of the current signature profile, it is Each described feature contour generates at least one condition code；
    Wherein, the parameter information includes：The Breadth Maximum of feature contour, the maximum height of feature contour, the feature wheel In the area of the ratio of maximum height of wide Breadth Maximum and the feature contour, the shape of feature contour and feature contour times The combination for one or more of anticipating；
    The related information includes：Distance with fisrt feature profile, with the distance of second feature profile and described with first The combination of any one or more in the distance of feature contour and the described and ratio of the distance of second feature profile.
  5. 5. according to any described face image processing process in claim 1-4, it is characterised in that further comprise：In advance The corresponding relation of condition code section and label is set；
    It is described generate at least one condition code for each described feature contour after, further comprise：
    For feature contour each described, it is performed both by：Determine the condition code area where each condition code of current signature profile Between, according to described document information and the corresponding relation of label, determine label corresponding to each condition code of current signature profile；
    According to label corresponding to each condition code of each feature contour, index is established for the pending facial image.
  6. A kind of 6. face image processing device, it is characterised in that including：
    Creating unit, for creating data space,
    Determining unit, for obtaining pending facial image, determine the color-values of each pixel in the pending facial image And positional information；
    Loading unit, for the color-values of each pixel in the pending facial image that is determined according to the determining unit and Positional information, each pixel in the pending facial image is loaded into the data space of the creating unit establishment In, generate at least two color layers；
    Processing unit, at least two color layer generated according to the loading unit, determine at least one feature wheel Exterior feature, it is that each described feature contour generates at least one condition code.
  7. 7. face image processing device according to claim 6, it is characterised in that
    The data space includes the space coordinates being made up of X-axis, Y-axis, Z axis；
    The loading unit, for for each pixel in the pending facial image, being performed both by：According to the color of current pixel Coloured silk value, determine the Z axis coordinate of the current pixel；According to the positional information of the current pixel, the X of the current pixel is determined Axial coordinate and Y-axis coordinate；According to the X-axis coordinate, Y-axis coordinate and Z axis coordinate, the current pixel is loaded into the data In space, at least two color layers are generated；Wherein, color-values identical pixel is located at same color layer.
  8. 8. face image processing device according to claim 7, it is characterised in that
    The pending facial image, including：Black white image；
    The color-values, including：0th, 1, wherein, described 0 is used to characterize black, and described 1 is used to characterize white；
    The processing unit, at least two color layer, determine color-values be 0 color layer；Determine color-values For at least one feature contour of 0 color layer formation.
  9. 9. face image processing device according to claim 6, it is characterised in that
    The processing unit, for for feature contour each described, being performed both by：Determine the parameter letter of current signature profile Breath, the related information of the current signature profile is determined, according to the parameter information of the current signature profile and the current spy The related information of profile is levied, is that each described feature contour generates at least one condition code；
    Wherein, the parameter information includes：The Breadth Maximum of feature contour, the maximum height of feature contour, the feature wheel In the area of the ratio of maximum height of wide Breadth Maximum and the feature contour, the shape of feature contour and feature contour times The combination for one or more of anticipating；
    The related information includes：Distance with fisrt feature profile, with the distance of second feature profile and described with first The combination of any one or more in the distance of feature contour and the described and ratio of the distance of second feature profile.
  10. 10. according to any described face image processing device in claim 6-9, it is characterised in that further comprise：
    Setting unit, for setting the corresponding relation in condition code section and label；
    Indexing units, for for feature contour each described, being performed both by：Determine each condition code institute of current signature profile Condition code section, according to the setting unit set described document information and label corresponding relation, determine current signature Label corresponding to each condition code of profile；It is described according to label corresponding to each condition code of each feature contour Pending facial image establishes index.
CN201711043786.5A 2017-10-31 2017-10-31 A kind of face image processing process and device Pending CN107832692A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711043786.5A CN107832692A (en) 2017-10-31 2017-10-31 A kind of face image processing process and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711043786.5A CN107832692A (en) 2017-10-31 2017-10-31 A kind of face image processing process and device

Publications (1)

Publication Number Publication Date
CN107832692A true CN107832692A (en) 2018-03-23

Family

ID=61650949

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711043786.5A Pending CN107832692A (en) 2017-10-31 2017-10-31 A kind of face image processing process and device

Country Status (1)

Country Link
CN (1) CN107832692A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110706415A (en) * 2019-10-14 2020-01-17 重庆国翰能源发展有限公司 Charging pile control system based on biological recognition and face recognition method thereof

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101477696A (en) * 2009-01-09 2009-07-08 彭振云 Human character cartoon image generating method and apparatus
CN102542299A (en) * 2011-12-07 2012-07-04 惠州Tcl移动通信有限公司 Face recognition method, device and mobile terminal capable of recognizing face
CN105117723A (en) * 2015-08-17 2015-12-02 浪潮软件集团有限公司 Image identification method and device
CN105374055A (en) * 2014-08-20 2016-03-02 腾讯科技（深圳）有限公司 Image processing method and device
CN106682598A (en) * 2016-12-14 2017-05-17 华南理工大学 Multi-pose facial feature point detection method based on cascade regression
CN106874835A (en) * 2016-12-28 2017-06-20 深圳云天励飞技术有限公司 A kind of image processing method and device

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101477696A (en) * 2009-01-09 2009-07-08 彭振云 Human character cartoon image generating method and apparatus
CN102542299A (en) * 2011-12-07 2012-07-04 惠州Tcl移动通信有限公司 Face recognition method, device and mobile terminal capable of recognizing face
CN105374055A (en) * 2014-08-20 2016-03-02 腾讯科技（深圳）有限公司 Image processing method and device
CN105117723A (en) * 2015-08-17 2015-12-02 浪潮软件集团有限公司 Image identification method and device
CN106682598A (en) * 2016-12-14 2017-05-17 华南理工大学 Multi-pose facial feature point detection method based on cascade regression
CN106874835A (en) * 2016-12-28 2017-06-20 深圳云天励飞技术有限公司 A kind of image processing method and device

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110706415A (en) * 2019-10-14 2020-01-17 重庆国翰能源发展有限公司 Charging pile control system based on biological recognition and face recognition method thereof

Similar Documents

Publication Publication Date Title
TWI616762B (en) Dynamic data masking method and data library system
CN109829448B (en) Face recognition method, face recognition device and storage medium
US8509499B2 (en) Automatic face detection and identity masking in images, and applications thereof
JP2015513754A (en) Face recognition method and device
WO2020253304A1 (en) Face recognition device and image processing method, feature extraction model, and storage medium
CN114187633A (en) Image processing method and device, and training method and device of image generation model
CN107395958A (en) Image processing method and device, electronic equipment and storage medium
CN108038475A (en) Facial image recognition method and device, computer-readable storage medium, terminal
CN111428645A (en) Method and device for detecting key points of human body, electronic equipment and storage medium
JP2023501820A (en) Face parsing methods and related devices
CN107818160A (en) Expression label updates and realized method, equipment and the system that expression obtains
CN111488732A (en) Deformed keyword detection method, system and related equipment
CN110717484B (en) Image processing method and system
CN109299692A (en) A kind of personal identification method, computer readable storage medium and terminal device
CN107832692A (en) A kind of face image processing process and device
CN112149605B (en) Face recognition method, device, equipment and storage medium
CN114282258A (en) Screen capture data desensitization method and device, computer equipment and storage medium
CN107305696A (en) A kind of image generating method and device
CN114707017A (en) Visual question answering method and device, electronic equipment and storage medium
CN113378982A (en) Training method and system of image processing model
CN117422796B (en) Text mark generation method and device, electronic equipment and storage medium
CN110049155A (en) Image display method, system, readable storage medium storing program for executing and mobile phone shell
CN110276050A (en) To the method and device of high dimension vector similarity system design
CN111027090A (en) Medical data privacy protection method based on heteroscedastic difference and K-anonymity mechanism
CN108229378A (en) Face image data generation method and device, computer storage media, terminal

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180323