CN104484858B - Character image processing method and processing device - Google Patents

Character image processing method and processing device Download PDF

Info

Publication number
CN104484858B
CN104484858B CN201410854277.0A CN201410854277A CN104484858B CN 104484858 B CN104484858 B CN 104484858B CN 201410854277 A CN201410854277 A CN 201410854277A CN 104484858 B CN104484858 B CN 104484858B
Authority
CN
China
Prior art keywords
face
image
correction angle
character image
pending character
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.)
Active
Application number
CN201410854277.0A
Other languages
Chinese (zh)
Other versions
CN104484858A (en
Inventor
陈志军
张涛
关亚勇
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.)
Xiaomi Inc
Original Assignee
Xiaomi Inc
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 Xiaomi Inc filed Critical Xiaomi Inc
Priority to CN201410854277.0A priority Critical patent/CN104484858B/en
Publication of CN104484858A publication Critical patent/CN104484858A/en
Application granted granted Critical
Publication of CN104484858B publication Critical patent/CN104484858B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00Geometric image transformation in the plane of the image
    • G06T3/60Rotation of a whole image or part thereof

Abstract

The disclosure is directed to character image processing method and processing device, for being adjusted to character face's direction.The described method includes:Face-image is extracted from pending character image, the facial threedimensional model of personage in the pending character image is built according to the face-image;Face correction angle is obtained, according to the face correction angle rotation facial threedimensional model, obtains the corresponding face-image of the face correction angle;The corresponding face-image of the face correction angle is synthesized with getting rid of the remainder after the face-image in the pending character image.The disclosure can be adjusted character face's direction in character image, and then meet the requirement in image procossing to character image.

Description

Character image processing method and processing device
Technical field
This disclosure relates to technical field of image processing, more particularly to character image processing method and processing device.
Background technology
When handling character image, it is sometimes desirable to which the direction of face in character image is adjusted;For example, When personage in multiple pictures is synthesized to a pictures, the technical solution of correlation technique is extracted respectively from multiple pictures Character image, the character image of extraction is added in background picture.Due to can not be adjusted to the direction of face in character image It is whole so that the face orientation of personage lacks harmony in each character image.Therefore, need offer one kind can in correlation technique Adjust the character image processing method of character face's direction.
The content of the invention
To overcome problem present in correlation technique, the embodiment of the present disclosure provides character image processing method and processing device, uses It is adjusted in character face's direction.
According to the first aspect of the embodiment of the present disclosure, there is provided a kind of character image processing method, including:
Face-image is extracted from pending character image, the pending character image is built according to the face-image The facial threedimensional model of middle personage;
Face correction angle is obtained, according to the face correction angle rotation facial threedimensional model, obtains the people The corresponding face-image of face correction angle;
The face will be got rid of in the corresponding face-image of the face correction angle and the pending character image Remainder after image is synthesized.
In one embodiment, it is described according to the face correction angle rotation facial threedimensional model, obtain the people The corresponding face-image of face correction angle, it may include:
Judge the angle value of the face correction angle and the facial orientation of the pending character image septum reset image Angle value between difference whether be less than predetermined angle threshold value;
It is three-dimensional according to the face correction angle rotation face when the difference is less than the predetermined angle threshold value Model, obtains the corresponding face-image of the face correction angle.
In one embodiment, it is described by the corresponding face-image of the face correction angle and the pending character image In get rid of the remainder after the face-image and synthesized, it may include:
The corresponding face-image of the face correction angle is added in the remainder;
The white space between the corresponding face-image of the face correction angle and the remainder is determined, to the sky White region is into row interpolation.
In one embodiment, the method may also include:
Judge the direction of the face correction angle and the facial orientation of the pending character image septum reset image Whether direction is opposite;
When the direction and the side of the facial orientation of the pending character image septum reset image of the face correction angle To it is opposite when, the remainder after the face-image will be got rid of in the pending character image and carries out mirror image conversion;
It is described will get rid of in the corresponding face-image of the face correction angle and the pending character image it is described Remainder after face-image is synthesized, including:
The corresponding face-image of the face correction angle is synthesized with the transformed remainder of the mirror image.
In one embodiment, it is described to extract face-image from pending character image, built according to the face-image The facial threedimensional model of personage in the pending character image, it may include:
Using face recognition face-image is extracted from the pending character image;
Characteristic point in the face-image is extracted, the characteristic point of extraction is positioned;
The facial threedimensional model of personage in the pending character image is built according to the characteristic point of positioning.
According to the second aspect of the embodiment of the present disclosure, there is provided a kind of character image processing unit, including:
Module is built, for extracting face-image from pending character image, according to face-image structure The facial threedimensional model of personage in pending character image;
Rotary module, for obtaining face correction angle, according to the three-dimensional mould of the face correction angle rotation face Type, obtains the corresponding face-image of the face correction angle;
Synthesis module, for by the corresponding face-image of the face correction angle with the pending character image The remainder after the face-image is removed to be synthesized.
In one embodiment, the rotary module, it may include:
Judging submodule, for the angle value for judging the face correction angle and the pending character image septum reset Whether difference is less than predetermined angle threshold value between the angle value of the facial orientation of image;
Submodule is rotated, for when the difference is less than the predetermined angle threshold value, according to the face correction angle The facial threedimensional model is rotated, obtains the corresponding face-image of the face correction angle.
In one embodiment, the synthesis module, it may include:
Submodule is added, for the corresponding face-image of the face correction angle to be added in the remainder;
Interpolation submodule, for determining the sky between the corresponding face-image of the face correction angle and the remainder White region, to the white space into row interpolation.
In one embodiment, described device may also include:
Judgment module, for the direction for judging the face correction angle and the pending character image septum reset image Facial orientation direction it is whether opposite;
Mirror module, for the direction when the face correction angle and the pending character image septum reset image When the direction of facial orientation is opposite, the remainder after the face-image will be got rid of in the pending character image and is carried out Mirror image is changed;
The synthesis module, including:
Submodule is synthesized, for by the corresponding face-image of the face correction angle and the transformed residue of the mirror image Part is synthesized.
In one embodiment, the structure module, it may include:
Extracting sub-module, for extracting face-image from the pending character image using face recognition;
Submodule is positioned, for extracting characteristic point in the face-image, the characteristic point of extraction is positioned;
Submodule is built, the face for building personage in the pending character image according to the characteristic point of positioning is three-dimensional Model.
According to the third aspect of the embodiment of the present disclosure, there is provided a kind of character image processing unit, including:
Processor;
For storing the memory of processor-executable instruction;
Wherein, the processor is configured as:
Face-image is extracted from pending character image, the pending character image is built according to the face-image The facial threedimensional model of middle personage;
Face correction angle is obtained, according to the face correction angle rotation facial threedimensional model, obtains the people The corresponding face-image of face correction angle;
The face will be got rid of in the corresponding face-image of the face correction angle and the pending character image Remainder after image is synthesized.
The technical scheme provided by this disclosed embodiment can include the following benefits:In the disclosure technical solution according to Face-image builds the facial threedimensional model of personage in pending character image, rotates the three-dimensional mould of face according to face correction angle Type, obtains the corresponding face-image of face correction angle, by the corresponding face-image of face correction angle and pending figure map The remainder after face-image is got rid of as in be synthesized;It so, it is possible to carry out character face's direction in character image Adjustment, and then meet the requirement in image procossing to character image.
It should be appreciated that the general description and following detailed description of the above are only exemplary and explanatory, not The disclosure can be limited.
Brief description of the drawings
Attached drawing herein is merged in specification and forms the part of this specification, shows the implementation for meeting the disclosure Example, and be used to together with specification to explain the principle of the disclosure.
Fig. 1 is the flow chart of the character image processing method according to an exemplary embodiment.
Fig. 2A is the schematic diagram of the pending image according to an exemplary embodiment.
Fig. 2 B are the schematic diagrames of the pending character image of the extraction according to an exemplary embodiment.
Fig. 2 C are the schematic diagrames of the facial image features point location according to an exemplary embodiment.
Fig. 2 D are that the residue after face-image is got rid of in the pending character image according to an exemplary embodiment Partial schematic diagram.
Fig. 3 is the flow chart of the character image processing method according to an exemplary embodiment one.
Fig. 4 is a kind of block diagram of character image processing unit according to an exemplary embodiment.
Fig. 5 is the block diagram of another character image processing unit according to an exemplary embodiment.
Fig. 6 is the block diagram of another character image processing unit according to an exemplary embodiment.
Fig. 7 is the block diagram of another character image processing unit according to an exemplary embodiment.
Fig. 8 is the block diagram of another character image processing unit according to an exemplary embodiment.
Fig. 9 is a kind of block diagram suitable for character image processing unit according to an exemplary embodiment.
Embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Following description is related to During attached drawing, unless otherwise indicated, the same numbers in different attached drawings represent the same or similar key element.Following exemplary embodiment Described in embodiment do not represent all embodiments consistent with the disclosure.On the contrary, they be only with it is such as appended The example of the consistent apparatus and method of some aspects be described in detail in claims, the disclosure.
Fig. 1 is a kind of flow chart of character image processing method according to an exemplary embodiment, as shown in Figure 1, The character image processing method is used in equipment, in PC, server, mobile phone, tablet computer, comprises the following steps S101-S103:
In step S101, face-image is extracted from pending character image, pending people is built according to face-image The facial threedimensional model of personage in object image.
For example, pending character image can be extracted from pending image, for example, as shown in Figure 2 A, treating Selection target prospect in image is handled, using image segmentation algorithm according to the target prospect of selection by character image and background image Separation, extracts pending character image, the pending character image extracted is as shown in Figure 2 B.
In one embodiment, above-mentioned steps S101 may include steps of A1-A3:
In step A1, face-image is extracted from pending character image using face recognition.
In step A2, characteristic point in face-image is extracted, the characteristic point of extraction is positioned.
For example, as shown in Figure 2 C, ASM (active shape model, active shape models) algorithm can be utilized Extract characteristic point in face-image.Then, the characteristic point of extraction is positioned.Facial figure is got rid of in pending character image Remainder as after, as shown in Figure 2 D.
In step A3, the facial threedimensional model of personage in pending character image is built according to the characteristic point of positioning.
For example, the characteristic point of positioning and the three-dimensional universal model of face can be utilized, is generated according to human face three-dimensional model Technology, constructs the facial threedimensional model of personage in pending character image.
In step s 102, face correction angle is obtained, facial threedimensional model is rotated according to face correction angle, obtains people The corresponding face-image of face correction angle.
For example, there is provided the input frame of face correction angle, obtains face correction angle input by user in input frame, Or user is adjusted the angle of facial threedimensional model by mouse, when the angle that user determines currently to be adjusted to is desired Angle when click on determination key, using definite angle as face correction angle.The face correction angle includes angle value and side To.
In one embodiment, above-mentioned steps S102 may include following steps B1-B2:
In step bl is determined, the angle value of face correction angle and the face court of pending character image septum reset image are judged To angle value between difference whether be less than predetermined angle threshold value.
For example, using facial orientation identification technology, can be determined according to the characteristic point positioned in face-image The angle value of facial orientation and direction in the face-image.
In step B2, when difference is less than predetermined angle threshold value, facial threedimensional model is rotated according to face correction angle, Obtain the corresponding face-image of face correction angle.
It is above-mentioned to may include according to the facial threedimensional model of face correction angle rotation:According to organization of human body, using neck as Axis, rotates facial threedimensional model by face correction angle.
For example, for the facial orientation of pending character image septum reset image to be 40 degree left, face correction angle is the right side 30 degree, predetermined angle threshold value is 15 degree, 30 degree of the angle value of face correction angle and pending character image septum reset image Difference is 10 degree between 40 degree of the angle value of facial orientation, which is less than 15 degree of predetermined angle threshold value, and then is corrected according to face The facial threedimensional model of angle rotation, obtains the corresponding face-image of face correction angle.
Because in subsequent step, it is necessary to by the corresponding face-image of face correction angle and pending character image Get rid of the remainder after face-image to be synthesized, if face correction angle and pending character image septum reset image Facial orientation angle value between difference it is excessive, then can cause the corresponding face-image of face correction angle and pending personage Get rid of in image in the image after the synthesis of the remainder after face-image and be lack of consistency between the two parts.Therefore, at this In embodiment, between the angle value of the facial orientation of angle value and pending character image septum reset image to face correction angle Difference is limited, and when difference is less than predetermined angle threshold value, is just rotated facial threedimensional model according to face correction angle, is obtained The corresponding face-image of face correction angle so that the corresponding face-image of face correction angle with pending character image Removing the image after the synthesis of the remainder after face-image has preferable uniformity.
In step s 103, face will be got rid of in the corresponding face-image of face correction angle and pending character image Remainder after image is synthesized.
In one embodiment, above-mentioned steps S103 may include following steps C1-C2:
In step C1, the corresponding face-image of face correction angle is added in remainder.
In step C2, the white space between the corresponding face-image of face correction angle and remainder is determined, to sky White region is into row interpolation.
Because face-image was adjusted, so the corresponding face-image of face correction angle and pending character image In get rid of and will not fit like a glove between the remainder after face-image, white space occurs between the two, in the present embodiment In to white space into row interpolation, come region of plugging a gap.It so, it is possible further to improve the image of synthesis.
In one embodiment, the above method may also include the steps of D1-D2:
In step D 1, the direction of face correction angle and the face court of pending character image septum reset image are judged To direction it is whether opposite.
In step d 2, the direction when face correction angle and the facial orientation of pending character image septum reset image When direction is opposite, the remainder after face-image will be got rid of in pending character image and carries out mirror image conversion.
Above-mentioned steps S103 may include:By the corresponding face-image of face correction angle and the transformed remainder of mirror image Synthesized.
For example, for the facial orientation of pending character image septum reset image to be 40 degree left, face correction angle is the right side 30 degree, the remainder after face-image will be got rid of in pending character image and carries out mirror image conversion so that in remainder Then image will synthesize, at acquisition towards the right side towards right body part images face-image corresponding with face correction angle Character image after reason.
In one embodiment, the character image after synthesis can be added in target image, for example, by multiple pictures Character image after processing is added in a picture, by above-mentioned processing, can cause in the picture between each personage Harmony is more preferable.
The technical scheme provided by this disclosed embodiment can include the following benefits:In the disclosure technical solution according to Face-image builds the facial threedimensional model of personage in pending character image, rotates the three-dimensional mould of face according to face correction angle Type, obtains the corresponding face-image of face correction angle, by the corresponding face-image of face correction angle and pending figure map The remainder after face-image is got rid of as in be synthesized;It so, it is possible to carry out character face's direction in character image Adjustment, and then meet the requirement in image procossing to character image.
Embodiment one
Fig. 3 is the flow chart of the character image processing method according to an exemplary embodiment one.Side in embodiment one Method is applied in following scene:Pending character image, pending character image septum reset image are extracted from pending image Facial orientation be left 40 degree, according in target image to character image it needs to be determined that go out face correction angle for 30 degree of the right side, Predetermined angle threshold value is 15 degree.As shown in figure 3, the character image processing method is used in PC, include the following steps:
In step S301, face-image is extracted from pending character image using face recognition.
In step s 302, characteristic point in face-image is extracted, the characteristic point of extraction is positioned.
In step S303, the facial threedimensional model of personage in pending character image is built according to the characteristic point of positioning.
In step s 304, face correction angle is obtained, judges the angle value of face correction angle and pending figure map As the facial orientation of septum reset image angle value between difference whether be less than predetermined angle threshold value.
In step S305, when difference is less than predetermined angle threshold value, the three-dimensional mould of face is rotated according to face correction angle Type, obtains the corresponding face-image of face correction angle.
In step S306, the direction of face correction angle and the face court of pending character image septum reset image are judged To direction it is whether opposite.
In step S307, direction and the facial orientation of pending character image septum reset image when face correction angle Direction it is opposite when, the remainder after face-image will be got rid of in pending character image and carries out mirror image conversion.
In step S308, the corresponding face-image of face correction angle and the transformed remainder of mirror image are closed Into.
In step S309, determine between the corresponding face-image of face correction angle and the transformed remainder of mirror image White space, to white space into row interpolation.
After the completion of character image processing, the character image after synthesis is added in target image.
The beneficial effect for the technical solution that embodiment of the disclosure one provides is:Can be to character face in character image Direction is adjusted, and then meets the requirement in image procossing to character image.
Fig. 4 is a kind of block diagram of character image processing unit according to an exemplary embodiment, as shown in figure 4, should Character image processing unit is used in equipment, in PC, server, mobile phone, tablet computer, including:
Structure module 41 is configured as extracting face-image from pending character image, is built according to face-image and waits to locate Manage the facial threedimensional model of personage in character image;
Rotary module 42 is configured as obtaining face correction angle, rotates facial threedimensional model according to face correction angle, Obtain the corresponding face-image of face correction angle;
Synthesis module 43 is configured as the corresponding face-image of face correction angle with being removed in pending character image Fall the remainder after face-image to be synthesized.
In one embodiment, as shown in figure 5, rotary module 42 may include:
Judging submodule 51 is configured as judging the angle value of face correction angle and pending character image septum reset figure Whether difference is less than predetermined angle threshold value between the angle value of the facial orientation of picture;
It is facial according to the rotation of face correction angle when rotation submodule 52 is configured as difference and is less than predetermined angle threshold value Threedimensional model, obtains the corresponding face-image of face correction angle.
In one embodiment, as shown in fig. 6, synthesis module 43 may include:
Addition submodule 61 is configured as the corresponding face-image of face correction angle being added in remainder;
Interpolation submodule 62 is configured to determine that the blank between the corresponding face-image of face correction angle and remainder Region, to white space into row interpolation.
In one embodiment, as shown in fig. 7, device further includes:
Judgment module 71 is configured as judging the direction of face correction angle and pending character image septum reset image Whether the direction of facial orientation is opposite;
Mirror module 72 is configured as the direction of face correction angle and the people of pending character image septum reset image When the direction of face direction is opposite, the remainder after face-image will be got rid of in pending character image and carries out mirror image conversion;
Synthesis module 43 may include:
Synthesis submodule 73 is configured as the corresponding face-image of face correction angle and the transformed remainder of mirror image Divide and synthesized.
In one embodiment, as shown in figure 8, structure module 41 may include:
Extracting sub-module 81 is configured as extracting face-image from pending character image using face recognition;
Positioning submodule 82 is configured as characteristic point in extraction face-image, and the characteristic point of extraction is positioned;
Structure submodule 83 is configured as building the face three of personage in pending character image according to the characteristic point of positioning Dimension module.
On the device in above-described embodiment, wherein modules perform the concrete mode of operation in related this method Embodiment in be described in detail, explanation will be not set forth in detail herein.
The technical scheme provided by this disclosed embodiment can include the following benefits:In the disclosure technical solution according to Face-image builds the facial threedimensional model of personage in pending character image, rotates the three-dimensional mould of face according to face correction angle Type, obtains the corresponding face-image of face correction angle, by the corresponding face-image of face correction angle and pending figure map The remainder after face-image is got rid of as in be synthesized;It so, it is possible to carry out character face's direction in character image Adjustment, and then meet the requirement in image procossing to character image.
Fig. 9 is a kind of block diagram for character image processing unit 1200 according to an exemplary embodiment, the dress Put and be suitable for terminal device.For example, device 1200 can be mobile phone, computer, digital broadcast terminal, information receiving and transmitting sets It is standby, game console, tablet device, Medical Devices, body-building equipment, personal digital assistant etc..
With reference to Fig. 9, device 1200 can include following one or more assemblies:Processing component 1202, memory 1204, electricity Source component 1206, multimedia component 1208, audio component 1210, the interface 1212 of input/output (I/O), sensor component 1214, and communication component 1216.
The integrated operation of the usual control device 1200 of processing component 1202, such as with display, call, data communication, The operation that camera operation and record operation are associated.Treatment element 1202 can be performed including one or more processors 1220 Instruction, to complete all or part of step of above-mentioned method.In addition, processing component 1202 can include one or more moulds Block, easy to the interaction between processing component 1202 and other assemblies.For example, processing component 1202 can include multi-media module, To facilitate the interaction between multimedia component 1208 and processing component 1202.
Memory 1204 is configured as storing various types of data to support the operation in equipment 1200.These data Example includes being used for the instruction of any application program or method operated on device 1200, contact data, telephone book data, Message, picture, video etc..Memory 1204 can by any kind of volatibility or non-volatile memory device or they Combination is realized, such as static RAM (SRAM), electrically erasable programmable read-only memory (EEPROM), it is erasable can Program read-only memory (EPROM), programmable read only memory (PROM), read-only storage (ROM), magnetic memory, flash memory Reservoir, disk or CD.
Electric power assembly 1206 provides electric power for the various assemblies of device 1200.Electric power assembly 1206 can include power management System, one or more power supplys, and other components associated with generating, managing and distributing electric power for device 1200.
Multimedia component 1208 is included in the screen of one output interface of offer between described device 1200 and user. In some embodiments, screen can include liquid crystal display (LCD) and touch panel (TP).If screen includes touch panel, Screen may be implemented as touch-screen, to receive input signal from the user.Touch panel includes one or more touch and passes Sensor is to sense the gesture on touch, slip and touch panel.The touch sensor can not only sense touch or slide dynamic The border of work, but also detection and the duration and pressure associated with the touch or slide operation.In certain embodiments, it is more Media component 1208 includes a front camera and/or rear camera.When equipment 1200 is in operator scheme, mould is such as shot When formula or video mode, front camera and/or rear camera can receive exterior multi-medium data.Each preposition shooting Head and rear camera can be a fixed optical lens system or have focusing and optical zoom capabilities.
Audio component 1210 is configured as output and/or input audio signal.For example, audio component 1210 includes a wheat Gram wind (MIC), when device 1200 is in operator scheme, during such as call model, logging mode and speech recognition mode, microphone quilt It is configured to receive external audio signal.The received audio signal can be further stored in memory 1204 or via communication Component 1216 is sent.In certain embodiments, audio component 1210 further includes a loudspeaker, for exports audio signal.
I/O interfaces 1212 provide interface, above-mentioned peripheral interface module between processing component 1202 and peripheral interface module Can be keyboard, click wheel, button etc..These buttons may include but be not limited to:Home button, volume button, start button and Locking press button.
Sensor component 1214 includes one or more sensors, and the state for providing various aspects for device 1200 is commented Estimate.For example, sensor component 1214 can detect opening/closed mode of equipment 1200, the relative positioning of component, such as institute The display and keypad that component is device 1200 are stated, sensor component 1214 can be with detection device 1200 or device 1,200 1 The position of a component changes, the existence or non-existence that user contacts with device 1200,1200 orientation of device or acceleration/deceleration and dress Put 1200 temperature change.Sensor component 1214 can include proximity sensor, be configured in no any physics Presence of nearby objects is detected during contact.Sensor component 1214 can also include optical sensor, as CMOS or ccd image are sensed Device, for being used in imaging applications.In certain embodiments, which can also include acceleration sensing Device, gyro sensor, Magnetic Sensor, pressure sensor or temperature sensor.
Communication component 1216 is configured to facilitate the communication of wired or wireless way between device 1200 and other equipment.Dress The wireless network based on communication standard, such as WiFi, 2G or 3G, or combinations thereof can be accessed by putting 1200.It is exemplary at one In embodiment, communication component 1216 receives broadcast singal or broadcast correlation from external broadcasting management system via broadcast channel Information.In one exemplary embodiment, the communication component 1216 further includes near-field communication (NFC) module, to promote short distance Communication.For example, radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra wide band can be based in NFC module (UWB) technology, bluetooth (BT) technology and other technologies are realized.
In the exemplary embodiment, device 1200 can be by one or more application application-specific integrated circuit (ASIC), numeral Signal processor (DSP), digital signal processing appts (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), controller, microcontroller, microprocessor or other electronic components are realized, for performing the above method.
In the exemplary embodiment, a kind of non-transitorycomputer readable storage medium including instructing, example are additionally provided Such as include the memory 1204 of instruction, above-metioned instruction can be performed to complete the above method by the processor 820 of device 1200.Example Such as, the non-transitorycomputer readable storage medium can be ROM, it is random access memory (RAM), CD-ROM, tape, soft Disk and optical data storage devices etc..
A kind of character image processing unit, including:
Processor;
For storing the memory of processor-executable instruction;
Wherein, processor is configured as:
Face-image is extracted from pending character image, the pending character image is built according to the face-image The facial threedimensional model of middle personage;
Face correction angle is obtained, according to the face correction angle rotation facial threedimensional model, obtains the people The corresponding face-image of face correction angle;
The face will be got rid of in the corresponding face-image of the face correction angle and the pending character image Remainder after image is synthesized.
The processor is configured as:Judge the angle value of the face correction angle and face in the pending character image Whether difference is less than predetermined angle threshold value between the angle value of the facial orientation of portion's image;When the difference is less than the predetermined angle During threshold value, according to the face correction angle rotation facial threedimensional model, the corresponding face of the face correction angle is obtained Portion's image.
The processor is configured as:The corresponding face-image of the face correction angle is added to the remainder In;The white space between the corresponding face-image of the face correction angle and the remainder is determined, to the clear area Domain is into row interpolation.
The processor is additionally configured to:Judge the direction of the face correction angle and face in the pending character image Whether the direction of the facial orientation of portion's image is opposite;When in the direction of the face correction angle and the pending character image It is surplus after the face-image by being got rid of in the pending character image when direction of the facial orientation of face-image is opposite Remaining part point carries out mirror image conversion;By the corresponding face-image of the face correction angle and the transformed remainder of the mirror image Synthesized.
The processor is additionally configured to:Using face recognition face-image is extracted from the pending character image;Carry Characteristic point in the face-image is taken, the characteristic point of extraction is positioned;Built according to the characteristic point of positioning described pending The facial threedimensional model of personage in character image.
A kind of non-transitorycomputer readable storage medium, when the instruction in the storage medium is by the processing of mobile terminal When device performs so that mobile terminal is able to carry out a kind of character image processing method, the described method includes:
Face-image is extracted from pending character image, the pending character image is built according to the face-image The facial threedimensional model of middle personage;
Face correction angle is obtained, according to the face correction angle rotation facial threedimensional model, obtains the people The corresponding face-image of face correction angle;
The face will be got rid of in the corresponding face-image of the face correction angle and the pending character image Remainder after image is synthesized.
It is described that the facial threedimensional model is rotated according to the face correction angle, obtain the face correction angle and correspond to Face-image, it may include:
Judge the angle value of the face correction angle and the facial orientation of the pending character image septum reset image Angle value between difference whether be less than predetermined angle threshold value;
It is three-dimensional according to the face correction angle rotation face when the difference is less than the predetermined angle threshold value Model, obtains the corresponding face-image of the face correction angle.
It is described will get rid of in the corresponding face-image of the face correction angle and the pending character image it is described Remainder after face-image is synthesized, it may include:
The corresponding face-image of the face correction angle is added in the remainder;
The white space between the corresponding face-image of the face correction angle and the remainder is determined, to the sky White region is into row interpolation.
The method may also include:
Judge the direction of the face correction angle and the facial orientation of the pending character image septum reset image Whether direction is opposite;
When the direction and the side of the facial orientation of the pending character image septum reset image of the face correction angle To it is opposite when, the remainder after the face-image will be got rid of in the pending character image and carries out mirror image conversion;
It is described will get rid of in the corresponding face-image of the face correction angle and the pending character image it is described Remainder after face-image is synthesized, it may include:
The corresponding face-image of the face correction angle is synthesized with the transformed remainder of the mirror image.
It is described to extract face-image from pending character image, the pending personage is built according to the face-image The facial threedimensional model of personage in image, it may include:
Using face recognition face-image is extracted from the pending character image;
Characteristic point in the face-image is extracted, the characteristic point of extraction is positioned;
The facial threedimensional model of personage in the pending character image is built according to the characteristic point of positioning.
Those skilled in the art will readily occur to the disclosure its after considering specification and putting into practice disclosure disclosed herein Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or Person's adaptive change follows the general principle of the disclosure and including the undocumented common knowledge in the art of the disclosure Or conventional techniques.Description and embodiments are considered only as exemplary, and the true scope and spirit of the disclosure are by following Claim is pointed out.
It should be appreciated that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by appended claim.

Claims (10)

  1. A kind of 1. character image processing method, it is characterised in that including:
    Face-image is extracted from pending character image, people in the pending character image is built according to the face-image The facial threedimensional model of thing;
    Face correction angle is obtained, according to the face correction angle rotation facial threedimensional model, the face is obtained and rectifys The corresponding face-image of positive-angle;
    The face-image will be got rid of in the corresponding face-image of the face correction angle and the pending character image Remainder afterwards is synthesized;
    The method further includes:
    Judge the direction of the face correction angle and the direction of the facial orientation of the pending character image septum reset image It is whether opposite;
    Direction and the direction phase of the facial orientation of the pending character image septum reset image when the face correction angle Inverse time, will get rid of the remainder after the face-image and carries out mirror image conversion in the pending character image;
    It is described to get rid of the face in the corresponding face-image of the face correction angle and the pending character image Remainder after image is synthesized, including:
    The corresponding face-image of the face correction angle is synthesized with the transformed remainder of the mirror image.
  2. 2. the method as described in claim 1, it is characterised in that described to rotate described facial three according to the face correction angle Dimension module, obtains the corresponding face-image of the face correction angle, including:
    Judge the angle of the angle value of the face correction angle and the facial orientation of the pending character image septum reset image Whether difference is less than predetermined angle threshold value between angle value;
    When the difference is less than the predetermined angle threshold value, according to the three-dimensional mould of the face correction angle rotation face Type, obtains the corresponding face-image of the face correction angle.
  3. 3. the method as described in claim 1, it is characterised in that it is described by the corresponding face-image of the face correction angle with The remainder after the face-image is got rid of in the pending character image to be synthesized, including:
    The corresponding face-image of the face correction angle is added in the remainder;
    The white space between the corresponding face-image of the face correction angle and the remainder is determined, to the clear area Domain is into row interpolation.
  4. 4. the method as described in claim 1, it is characterised in that described that face-image, root are extracted from pending character image The facial threedimensional model of personage in the pending character image is built according to the face-image, including:
    Using face recognition face-image is extracted from the pending character image;
    Characteristic point in the face-image is extracted, the characteristic point of extraction is positioned;
    The facial threedimensional model of personage in the pending character image is built according to the characteristic point of positioning.
  5. A kind of 5. character image processing unit, it is characterised in that including:
    Module is built, for extracting face-image from pending character image, waits to locate according to face-image structure Manage the facial threedimensional model of personage in character image;
    Rotary module, for obtaining face correction angle, according to the face correction angle rotation facial threedimensional model, is obtained Obtain the corresponding face-image of the face correction angle;
    Synthesis module, for by the corresponding face-image of the face correction angle with being got rid of in the pending character image Remainder after the face-image is synthesized;
    Described device further includes:
    Judgment module, for judging the direction of the face correction angle and the people of the pending character image septum reset image Whether the direction of face direction is opposite;
    Mirror module, for the direction when the face correction angle and the face of the pending character image septum reset image When the direction of direction is opposite, the remainder after the face-image will be got rid of in the pending character image and carries out mirror image Conversion;
    The synthesis module, including:
    Submodule is synthesized, for by the corresponding face-image of the face correction angle and the transformed remainder of the mirror image Synthesized.
  6. 6. device as claimed in claim 5, it is characterised in that the rotary module, including:
    Judging submodule, for the angle value for judging the face correction angle and the pending character image septum reset image Facial orientation angle value between difference whether be less than predetermined angle threshold value;
    Submodule is rotated, for when the difference is less than the predetermined angle threshold value, being rotated according to the face correction angle The face threedimensional model, obtains the corresponding face-image of the face correction angle.
  7. 7. device as claimed in claim 5, it is characterised in that the synthesis module, including:
    Submodule is added, for the corresponding face-image of the face correction angle to be added in the remainder;
    Interpolation submodule, for determining the clear area between the corresponding face-image of the face correction angle and the remainder Domain, to the white space into row interpolation.
  8. 8. device as claimed in claim 5, it is characterised in that the structure module, including:
    Extracting sub-module, for extracting face-image from the pending character image using face recognition;
    Submodule is positioned, for extracting characteristic point in the face-image, the characteristic point of extraction is positioned;
    Submodule is built, the three-dimensional mould of the face for building personage in the pending character image according to the characteristic point of positioning Type.
  9. A kind of 9. character image processing unit, it is characterised in that including:
    Processor;
    For storing the memory of processor-executable instruction;
    Wherein, the processor is configured as:
    Face-image is extracted from pending character image, people in the pending character image is built according to the face-image The facial threedimensional model of thing;
    Face correction angle is obtained, according to the face correction angle rotation facial threedimensional model, the face is obtained and rectifys The corresponding face-image of positive-angle;
    The face-image will be got rid of in the corresponding face-image of the face correction angle and the pending character image Remainder afterwards is synthesized;
    The processor is additionally configured to:
    Judge the direction of the face correction angle and the direction of the facial orientation of the pending character image septum reset image It is whether opposite;
    Direction and the direction phase of the facial orientation of the pending character image septum reset image when the face correction angle Inverse time, will get rid of the remainder after the face-image and carries out mirror image conversion in the pending character image;
    It is described to get rid of the face in the corresponding face-image of the face correction angle and the pending character image Remainder after image is synthesized, including:
    The corresponding face-image of the face correction angle is synthesized with the transformed remainder of the mirror image.
  10. 10. a kind of computer-readable recording medium, is stored thereon with computer instruction, it is characterised in that the instruction is by processor The step of the claims 1-4 the methods are realized during execution.
CN201410854277.0A 2014-12-31 2014-12-31 Character image processing method and processing device Active CN104484858B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410854277.0A CN104484858B (en) 2014-12-31 2014-12-31 Character image processing method and processing device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410854277.0A CN104484858B (en) 2014-12-31 2014-12-31 Character image processing method and processing device

Publications (2)

Publication Number Publication Date
CN104484858A CN104484858A (en) 2015-04-01
CN104484858B true CN104484858B (en) 2018-05-08

Family

ID=52759398

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410854277.0A Active CN104484858B (en) 2014-12-31 2014-12-31 Character image processing method and processing device

Country Status (1)

Country Link
CN (1) CN104484858B (en)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105260732A (en) * 2015-11-26 2016-01-20 小米科技有限责任公司 Image processing method and device
CN107733874B (en) * 2017-09-20 2021-03-30 平安科技(深圳)有限公司 Information processing method, information processing device, computer equipment and storage medium
CN108446675A (en) * 2018-04-28 2018-08-24 北京京东金融科技控股有限公司 Face-image recognition methods, device electronic equipment and computer-readable medium
CN108921795A (en) * 2018-06-04 2018-11-30 腾讯科技(深圳)有限公司 A kind of image interfusion method, device and storage medium
WO2020037679A1 (en) * 2018-08-24 2020-02-27 太平洋未来科技(深圳)有限公司 Video processing method and apparatus, and electronic device
CN111353336A (en) * 2018-12-21 2020-06-30 华为技术有限公司 Image processing method, device and equipment
CN109829847B (en) * 2018-12-27 2023-09-01 深圳云天励飞技术有限公司 Image synthesis method and related product
CN112543343B (en) * 2020-11-27 2024-02-23 广州华多网络科技有限公司 Live broadcast picture processing method and device based on live broadcast with wheat
CN115239576B (en) * 2022-06-15 2023-08-04 荣耀终端有限公司 Photo optimization method, electronic equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1659578A (en) * 2002-06-03 2005-08-24 皇家飞利浦电子股份有限公司 Face-recognition using half-face images
CN1787012A (en) * 2004-12-08 2006-06-14 索尼株式会社 Method,apparatua and computer program for processing image
CN104156993A (en) * 2014-07-18 2014-11-19 小米科技有限责任公司 Method and device for switching face image in picture

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101561874B (en) * 2008-07-17 2011-10-26 清华大学 Method for recognizing face images
JP2011119997A (en) * 2009-12-03 2011-06-16 Sony Computer Entertainment Inc Image processing apparatus and image processing method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1659578A (en) * 2002-06-03 2005-08-24 皇家飞利浦电子股份有限公司 Face-recognition using half-face images
CN1787012A (en) * 2004-12-08 2006-06-14 索尼株式会社 Method,apparatua and computer program for processing image
CN104156993A (en) * 2014-07-18 2014-11-19 小米科技有限责任公司 Method and device for switching face image in picture

Also Published As

Publication number Publication date
CN104484858A (en) 2015-04-01

Similar Documents

Publication Publication Date Title
CN104484858B (en) Character image processing method and processing device
CN104243819B (en) Photo acquisition methods and device
KR102018887B1 (en) Image preview using detection of body parts
CN108712603B (en) Image processing method and mobile terminal
CN105205479A (en) Human face value evaluation method, device and terminal device
CN105512605A (en) Face image processing method and device
CN104301610B (en) Image taking control metho and device
CN104156915A (en) Skin color adjusting method and device
CN104156947A (en) Image segmentation method, mechanism and device
CN107122679A (en) Image processing method and device
CN107330868A (en) image processing method and device
CN103970500A (en) Method and device for displaying picture
CN105469356A (en) Human face image processing method and apparatus thereof
CN105653032A (en) Display adjustment method and apparatus
CN104182967B (en) image processing method, device and terminal
EP3328062A1 (en) Photo synthesizing method and device
CN107888984A (en) Short video broadcasting method and device
CN107958223A (en) Face identification method and device, mobile equipment, computer-readable recording medium
CN104408404A (en) Face identification method and apparatus
CN105354793A (en) Facial image processing method and device
CN104077563A (en) Human face recognition method and device
CN104156695A (en) Method and device for aligning face image
CN108154466A (en) Image processing method and device
CN106503682A (en) Crucial independent positioning method and device in video data
CN107992811A (en) Face identification method and device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant