WO2020135286A1 - Shaping simulation method and system, readable storage medium and device - Google Patents
Shaping simulation method and system, readable storage medium and device Download PDFInfo
- Publication number
- WO2020135286A1 WO2020135286A1 PCT/CN2019/127251 CN2019127251W WO2020135286A1 WO 2020135286 A1 WO2020135286 A1 WO 2020135286A1 CN 2019127251 W CN2019127251 W CN 2019127251W WO 2020135286 A1 WO2020135286 A1 WO 2020135286A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- data
- face
- face feature
- shaping
- Prior art date
Links
- 238000004088 simulation Methods 0.000 title claims abstract description 136
- 238000007493 shaping process Methods 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000004458 analytical method Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000005192 partition Methods 0.000 claims description 176
- 230000001815 facial effect Effects 0.000 claims description 49
- 230000004048 modification Effects 0.000 claims description 39
- 238000012986 modification Methods 0.000 claims description 39
- 238000010191 image analysis Methods 0.000 claims description 13
- 230000000694 effects Effects 0.000 abstract description 21
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000002316 cosmetic surgery Methods 0.000 description 17
- 210000001508 eye Anatomy 0.000 description 15
- 230000006870 function Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 3
- 210000004709 eyebrow Anatomy 0.000 description 3
- 210000001061 forehead Anatomy 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- 230000003796 beauty Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 210000001331 nose Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 239000002537 cosmetic Substances 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 210000000720 eyelash Anatomy 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000003032 molecular docking Methods 0.000 description 1
- 210000000214 mouth Anatomy 0.000 description 1
- 229920001690 polydopamine Polymers 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/18—Image warping, e.g. rearranging pixels individually
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/04—Context-preserving transformations, e.g. by using an importance map
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Definitions
- the present invention relates to the field of image processing technology, and in particular, to a plastic modeling method, system, readable storage medium, and device.
- image processing software can use various image processing software and tools to perform image processing on self-portraits to achieve the effect of plastic simulation, which enriches daily life.
- Users of image processing software often use the software to perform image stretching on the eyes, nose, face, chin (chin), etc. in the image, such as eye enlargement, chin stretching, face thinning, nose stretching, etc., traditional
- the image processing method is usually to extract part features of the user's static original image, and then use simple image blur calculation processing to make a certain feature point of the image change. This method only performs image processing according to the user's preferences and simulates the resulting image It is difficult to have a preoperative reference for plastic surgery.
- a shaping simulation method includes the following steps:
- the original image is simulated and adjusted according to the face feature adjustment value to obtain a plastic analog image.
- the shaping simulation method it is to obtain the original image of the object to be shaped, perform face recognition on the original image to obtain face feature data; perform matching analysis on the face feature data and the preset shaped face feature database to obtain the person Face feature adjustment value; simulate and adjust the original image according to the face feature adjustment value to obtain a plastic analog image.
- the adjustment value of the face feature obtained by matching the face feature data with the data of the plastic face feature database, the simulation adjustment of the original image is more in line with the needs of plastic surgery, and it can obtain a relatively close to real and more intuitive plastic simulation effect, improve plastic surgery Pre-operative reference function of simulated images.
- the original image of the object to be shaped is acquired, and the step of performing face recognition on the original image includes the following steps:
- the step of acquiring face feature data of the object to be shaped includes the following steps:
- the feature points of the face area of the object to be shaped partition the face according to the feature points of the face area, and obtain the feature data of each area and the contour data of the face; where each area includes the eye, nose, mouth, For the face and chin, the feature data includes position data of the current partition and relative position data between the current partition and other partitions.
- the step of performing matching analysis on the face feature data and the preset plastic face feature database includes the following steps:
- the step of obtaining the adjustment value of face features also includes the following steps:
- the step of performing matching analysis on the face feature data and the preset plastic face feature database includes the following steps:
- the shaping simulation method further includes the following steps:
- the shaping simulation method further includes the following steps:
- the target partition image is fused to the position of the second target partition in the original image.
- the step of fusing the target partition image to the position of the second target partition in the original image includes the following steps:
- the shaping simulation method further includes the following steps:
- a shaping simulation system including:
- the image recognition unit is used to obtain the original image of the object to be shaped, perform face recognition on the original image, and obtain the facial feature data of the object to be shaped;
- the image analysis unit is used to perform matching analysis on the face feature data and the preset plastic face feature database to obtain the face feature adjustment value;
- the image adjustment unit performs analog adjustment on the original image according to the adjustment value of the face feature to obtain a plastic analog image.
- the image recognition unit obtains the original image of the object to be shaped and performs face recognition on the original image to obtain face feature data; the image analysis unit matches the face feature data with the preset shaped face feature database Analyze and obtain the facial feature adjustment value; the image adjustment unit performs analog adjustment on the original image according to the facial feature adjustment value to obtain a plastic analog image.
- the adjustment value of the face feature obtained by matching the face feature data with the data of the plastic face feature database, the simulation adjustment of the original image is more in line with the needs of plastic surgery, and it can obtain a relatively close to real and more intuitive plastic simulation effect, improve plastic surgery Pre-operative reference function of simulated images.
- the image recognition unit acquires a front image and a plurality of side images of the object to be shaped, and performs face recognition on the front image and the plurality of side images.
- the image recognition unit acquires the feature points of the face area of the object to be shaped, partitions the face according to the feature points of the face area, and obtains the feature data of each partition and the contour data of the face; wherein, each partition Including the eyes, nose, mouth, face and chin, the feature data includes the position data of the current partition and the relative position data between the current partition and other partitions.
- the image analysis unit searches for matching data in the plastic face feature database based on the face feature data, wherein the similarity between the match data and the face feature data is greater than or equal to a preset value;
- the image analysis unit obtains the ratio of the face feature data and the matching data, and obtains the face feature adjustment value according to the ratio, where the face feature adjustment value is between the ratio and the value 1.
- the image analysis unit receives the first selection instruction and selects the first target partition among the partitions according to the first selection instruction; according to the feature data of the partitions other than the first target partition, the face features are reshaped
- the database selects a sub-database, and performs matching analysis on the feature data of the first target partition and the sub-database; wherein, the face feature data in the sub-database matches the feature data of the partitions other than the first target partition.
- the shaping simulation system further includes an image modification unit for receiving a modification instruction, fine-tuning the characteristic data of the shaping simulation image according to the modification instruction; or, according to the modification instruction, reselecting the first target partition in each partition.
- the shaping simulation system further includes an image combination unit for receiving a trigger instruction for the second target partition, and selecting a plurality of candidate partition images in the shaping facial feature database according to the trigger instruction, wherein each The partition type of the partition image is the same as the partition type of the second target partition;
- the image combination unit is further used to display the images of each partition, receive the second selection instruction, and select the target partition image among the partition images according to the second selection instruction;
- the image combining unit is also used to fuse the target partition image to the position corresponding to the second target partition in the original image.
- the image combining unit acquires the image size, position and color data of the second target partition, adjusts the target partition image according to the image size, position and color data, and compares the part of the original image corresponding to the second target partition Replace with the adjusted image, and blur the edge of the interface between the adjusted image and the original image.
- the shaping simulation system further includes a data interaction unit for sending the processed image to the shaping server through the server, receiving the modification opinion data returned by the shaping server, and feeding back processing information on the modification opinion data .
- a readable storage medium has stored thereon an executable program, and when the executable program is executed by a processor, the steps of the above-mentioned shaping simulation method are realized.
- the above-mentioned readable storage medium through the executable program stored in it, can achieve the adjustment value of the facial features by matching the facial feature data with the data of the plastic facial feature database, and the analog adjustment of the original image is more in line with the needs of plastic surgery.
- a relatively close to real and more intuitive plastic simulation effect can be obtained, and the preoperative reference function of the plastic simulation image can be improved.
- a shaping simulation device includes a memory and a processor.
- the memory stores an executable program.
- the processor executes the executable program, the steps of the shaping simulation method described above are implemented.
- the above-mentioned shaping simulation device can achieve the adjustment value of the face feature by matching the face feature data with the data of the shaping face feature database by running the executable program on the processor, and the simulation adjustment of the original image is more in line with the needs of shaping , You can get relatively close to the real and more intuitive plastic simulation effect, improve the pre-operative reference role of plastic simulation images.
- FIG. 1 is an application scenario diagram of a shaping simulation method in an embodiment
- FIG. 2 is a schematic flow chart of a method for shaping simulation in an embodiment
- FIG. 3 is an interactive schematic diagram of a shaping simulation method in an embodiment
- FIG. 4 is a schematic structural diagram of a shaping simulation system in an embodiment
- FIG. 5 is a schematic structural diagram of a shaping simulation system in another embodiment
- FIG. 6 is a schematic structural diagram of a shaping simulation system in yet another embodiment
- FIG. 7 is a schematic structural diagram of a shaping simulation system in yet another embodiment
- FIG. 8 is a schematic diagram of a specific application process of the shaping simulation method in an embodiment.
- first ⁇ second involved in the embodiment of the present invention is only to distinguish similar objects, and does not represent a specific order for objects. Understandably, “first ⁇ second” is allowed The specific order or sequence can be interchanged below. It should be understood that the objects distinguished by “first ⁇ second” may be interchanged under appropriate circumstances, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.
- the shaping simulation method provided in this application can be applied in the application environment shown in FIG. 1, the mobile device can obtain the original image of the object to be shaped (ie, the user), perform face recognition on the original image, and obtain face feature data ; Perform matching analysis on the face feature data and the preset plastic face feature database to obtain the face feature adjustment value; simulate and adjust the original image according to the face feature adjustment value to obtain the plastic simulation image.
- the mobile device may be a variety of devices with functions of acquiring user images and image processing, such as personal computers, notebook computers, PDAs, smart phones, tablet computers, and portable wearable devices.
- FIG. 2 it is a schematic flowchart of a shaping simulation method according to an embodiment of the present invention.
- the shaping simulation method in this embodiment includes the following steps:
- Step S110 Obtain the original image of the object to be shaped, perform face recognition on the original image, and obtain the facial feature data of the object to be shaped;
- the original image can be captured by the camera of the electronic device or obtained by scanning; during facial recognition, the characteristics of the human face in the original image can be analyzed to obtain facial feature data;
- Step S120 Perform matching analysis on the face feature data and the preset plastic face feature database to obtain the face feature adjustment value
- the plastic face feature database is a pre-set collection of commonly used face feature material data for plastic surgery.
- the facial feature adjustment value can be obtained.
- the facial feature adjustment value can reduce the feature difference, so that the face in the adjusted image is close to the plastic face to achieve The effect of plastic simulation;
- Step S130 Perform simulation adjustment on the original image according to the face feature adjustment value to obtain a plastic simulation image
- this step when performing analog adjustment according to the face feature adjustment value, it is mainly to adjust the face feature data, and image deformation processing can be performed based on the face feature points.
- the original image of the object to be shaped is obtained, and the original image is subjected to face recognition to obtain face feature data; the face feature data is matched with the preset shaped face feature database to obtain face features Adjustment value; adjust the original image according to the adjustment value of the facial features to obtain the plastic simulation image.
- the adjustment value of the face feature obtained by matching the face feature data with the data of the plastic face feature database, the simulation adjustment of the original image is more in line with the needs of plastic surgery, and it can obtain a relatively close to real and more intuitive plastic simulation effect, improve plastic surgery Pre-operative reference function of simulated images.
- an image facial analysis report can be generated, and the plastic surgery based on the facial feature adjustment value is given in the report It is recommended that after receiving the confirmation information, the original image is automatically simulated and adjusted, and a plastic recommendation report is given after completion, including specific plastic parts, plastic methods and plastic effect description information.
- diffusion, sharpening, and deformation algorithms can be used to process images during simulation adjustment.
- the shooting area can be defined, such as a shooting area similar to the shape of the face, etc.
- the original image is The required face image can reduce the time of face recognition and improve the accuracy of recognition.
- it senses the brightness when shooting, if the brightness is less than the preset brightness value, turn on The flash or the brightness is insufficient; during face recognition, you can also detect the makeup on the face, prompt to clean and then perform plastic simulation, if you detect accessories on the face, prompt to remove the accessories, such as glasses, false eyelashes, Nose nails, etc.
- the original image of the object to be shaped is obtained, and the step of performing face recognition on the original image includes the following steps:
- multiple images of the object to be shaped can be obtained, including a frontal image and a side image.
- the frontal image and the multiple side images are images obtained from different angles, based on which the influence of illumination, angle, etc. can be reduced To make face recognition more accurate.
- a front image of the object to be shaped and two side images at a 45-degree angle can be obtained.
- the 3D original image model can be constructed based on this, and the 3D model algorithm can be used for accurate face recognition.
- the step of acquiring face feature data of the object to be shaped includes the following steps:
- the feature points of the face area of the object to be shaped partition the face according to the feature points of the face area, and obtain the feature data of each area and the contour data of the face; where each area includes the eye, nose, mouth, For the face and chin, the feature data includes position data of the current partition and relative position data between the current partition and other partitions.
- facial region feature points can be obtained, and the feature point distribution of different regions on the human face is different.
- the facial region feature points can be used to partition the facial region to obtain, for example, eye parts. , Nose, mouth, face, chin, etc. and the contour data of the face, the feature data includes the position data of the current face part and the relative position data between the current face part and other parts, In order to simulate and shape different areas of the human face.
- the characteristic regions on the human face may include forehead, eyes, eyebrows, eyelids, nose bridge, nose, nose wings, cheeks, mouth, chin, etc., and also include facial contour data such as the overall contour of the face.
- Feature points to achieve the division of facial feature area parts, when acquiring feature data, not only the data of the feature area parts themselves, but also the position data of the feature area parts and the relative position data with other feature areas, and the feature area parts
- the data such as color and brightness can be integrated in the shaping simulation to improve the coordination of the simulation effect.
- the step of performing matching analysis on the face feature data and the preset plastic face feature database includes the following steps:
- the step of obtaining the adjustment value of face features also includes the following steps:
- the similarity between the face feature data and the data in the plastic face feature database can be used to determine the matching data.
- the person After the similarity matching analysis is performed on the face feature data and the plastic face feature database, the person can be shaped
- the matching data matching the face feature data after image analysis is obtained from the face feature database, but it is different from the face feature data after image analysis.
- the face feature adjustment value may be dynamic data, which is dynamically adjusted between the ratio and the value 1 according to the needs of the object to be shaped.
- the step of performing matching analysis on the face feature data and the preset plastic face feature database includes the following steps:
- the first target partition can be selected through the first selection instruction, and a sub-database can be selected in the plastic face feature database according to the feature data of other partitions, because the face feature data in the sub-database is different from the first target partition
- the feature data of the other partitions of the database match. Therefore, when the feature data of the first target partition and the sub-database are matched and analyzed, the feature adjustment value of the first target partition obtained can make the first target partition coordinate with other partitions and improve the The overall coordination of the plastic simulation of a single partition.
- the shaping simulation method further includes the following steps:
- the image is simulated and adjusted according to the facial feature adjustment value, and after obtaining the plastic simulation image, the plastic simulation image may not meet the requirements of the object to be shaped, at this time, a modification instruction may be received, and the features may be modified according to the modification instruction. Fine-tune the data to meet the specific requirements of the object to be reshaped; or, the current simulation of the first target partition does not meet the requirements of the object to be reshaped. You can select a new first target partition for reshaping simulation, so that you can follow the The requirements of the object to be reshaped adjust the simulated reshaping.
- the shaping simulation method further includes the following steps:
- the target partition image is fused to the position of the second target partition in the original image.
- a second target partition can be selected and triggered, multiple candidate partition images of the same type as the second target partition are selected in the plastic face feature database, and the partition images are displayed for selection of objects to be shaped After the object to be shaped selects the target partition image through the second selection instruction, the target partition image is fused into the original image, so that the object to be shaped can independently select the shaping content and show the effect of shaping the simulated image.
- the second target partition may be a forehead, eyes, eyebrows, nose, mouth, chin, etc.
- selecting an eye part as the second target partition may select and display eye images of different shapes in the plastic face feature database and display For selection of the object to be shaped, and after the determination, the selected new eye shape is merged into the original image of the object to be shaped to form a shaped simulation image.
- the step of fusing the target partition image to the position of the second target partition in the original image includes the following steps:
- the second target partition is a part of the original image, which has attributes such as image size, position, color, etc.
- the target partition image is adjusted according to data such as image size, position, and color, so that the target partition image and the original The image is coordinated.
- the edge of the interface between the adjusted image and the original image is blurred.
- another plastic simulation image can be obtained, which is different from the plastic simulation image obtained by adjusting the original image according to the adjustment value of the face feature; after the fusion and blur processing, The modification instruction may be received, and the obtained image may be fine-tuned for the characteristic data according to the modification instruction; or, the second target partition may be selected again from each partition according to the modification instruction.
- the shaping simulation method further includes the following steps:
- the image after the image is processed, it can be sent to the shaping server through the server, and the shaping server can obtain the modification opinion data for the image and return it; the sending end can feed back the corresponding processing information for the modification opinion data, Through this interactive way, the image can be further adjusted and modified.
- the processed image may be an orthopaedic simulated image obtained by performing simulation adjustment according to the adjustment value of the face feature, or an image obtained by selecting different partitions and performing fusion processing.
- the above processing procedure can be applied to the consulting terminal device on the user side, and the shaping server can be provided on the receiving terminal on the side of the plastic doctor.
- the consulting terminal of the user sends the plastic simulation image to the receiving terminal of the plastic doctor, inviting the doctor Adjust the plastic simulation image and give the modification opinion, the receiving terminal returns the modification opinion data, and the interactive schematic diagram is shown in Figure 3.
- the original image of the object to be reshaped can be directly sent to the reshaping server through the server, receive the modification opinion data returned by the reshaping server, and feed back processing information on the modification opinion data.
- an embodiment of the present invention also provides a shaping simulation system.
- the embodiment of the shaping simulation system of the present invention will be described in detail below.
- FIG. 4 it is a schematic structural diagram of a shaping simulation system according to an embodiment of the present invention.
- the shaping simulation system in this embodiment includes:
- the image recognition unit 210 is used to obtain the original image of the object to be shaped, perform face recognition on the original image, and obtain the facial feature data of the object to be shaped;
- the image analysis unit 220 is used to perform matching analysis on the facial feature data and the preset plastic facial feature database to obtain the facial feature adjustment value;
- the image adjustment unit 230 performs analog adjustment on the original image according to the face feature adjustment value to obtain a plastic analog image.
- the image recognition unit 210 obtains the original image of the object to be shaped, and performs face recognition on the original image to obtain face feature data; the image analysis unit 220 compares the face feature data with the preset shaped face feature database Perform matching analysis to obtain the face feature adjustment value; the image adjustment unit 230 performs analog adjustment on the original image according to the face feature adjustment value to obtain a plastic analog image.
- the adjustment value of the face feature obtained by matching the face feature data with the data of the plastic face feature database, the simulation adjustment of the original image is more in line with the needs of plastic surgery, and it can obtain a relatively close to real and more intuitive plastic simulation effect, improve plastic surgery Pre-operative reference function of simulated images.
- the image recognition unit 210 acquires a front image and multiple side images of the object to be shaped, and performs face recognition on the front image and the multiple side images.
- the image recognition unit 210 acquires the facial region feature points of the object to be shaped, partitions the face according to the facial region feature points, and acquires the feature data of each partition and the contour data of the face; wherein, each partition Including the eyes, nose, mouth, face and chin, the feature data includes the position data of the current partition and the relative position data between the current partition and other partitions.
- the image analysis unit 220 searches for matching data in the plastic face feature database according to the face feature data, where the similarity of the match data and the face feature data is greater than or equal to a preset value;
- the image analysis unit 220 acquires the ratio of the facial feature data to the matching data, and acquires the facial feature adjustment value according to the ratio, where the facial feature adjustment value is between the ratio and the value 1.
- the image analysis unit 220 receives the first selection instruction and selects the first target partition among the partitions according to the first selection instruction; according to the feature data of the partitions other than the first target partition, the face features are reshaped
- the database selects a sub-database, and performs matching analysis on the feature data of the first target partition and the sub-database; wherein, the face feature data in the sub-database matches the feature data of the partitions other than the first target partition.
- the shaping simulation system further includes an image modification unit 240 for receiving a modification instruction, and fine-tuning the characteristic data of the shaping simulation image according to the modification instruction; or, according to the modification instruction, in each partition Select the first target partition.
- the shaping simulation system further includes an image combining unit 250 for receiving a trigger instruction for the second target partition, and selecting a plurality of candidate candidates in the shaping facial feature database according to the trigger instruction Partition images, where the partition type of each partition image is the same as the partition type of the second target partition;
- the image combining unit 250 is further used to display each partition image, receive a second selection instruction, and select a target partition image from each partition image according to the second selection instruction;
- the image combining unit 250 is also used to fuse the target partition image to the position of the original image corresponding to the second target partition.
- the image combining unit 250 acquires the image size, position and color data of the second target partition, adjusts the target partition image according to the image size, position and color data, and compares the part of the original image corresponding to the second target partition Replace with the adjusted image, and blur the edge of the interface between the adjusted image and the original image.
- the shaping simulation system further includes a data interaction unit 270 for sending the shaping simulation image to the shaping server via the server, receiving the modification opinion data returned by the shaping server, and feeding back the modification Processing information of opinion data.
- the shaping simulation system of the present invention corresponds to the shaping simulation method of the present invention, and the technical features and beneficial effects described in the above embodiments of the shaping simulation method are applicable to the embodiments of the shaping simulation system.
- a readable storage medium has stored thereon an executable program, and when the executable program is executed by a processor, the steps of the above-mentioned shaping simulation method are realized.
- the above-mentioned readable storage medium through the executable program stored in it, can achieve the adjustment value of the facial features by matching the facial feature data with the data of the plastic facial feature database, and the analog adjustment of the original image is more in line with the needs of plastic surgery.
- a relatively close to real and more intuitive plastic simulation effect can be obtained, and the preoperative reference function of the plastic simulation image can be improved.
- a shaping simulation device includes a memory and a processor.
- the memory stores an executable program.
- the processor executes the executable program, the steps of the shaping simulation method described above are implemented.
- the above-mentioned shaping simulation device can achieve the adjustment value of the face feature by matching the face feature data with the data of the shaping face feature database by running the executable program on the processor, and the simulation adjustment of the original image is more in line with the needs of shaping , You can get relatively close to the real and more intuitive plastic simulation effect, improve the pre-operative reference role of plastic simulation images.
- the above-mentioned shaping simulation device by running an executable program on the processor, obtains the face feature adjustment value by matching the face feature data with the data of the shaping face feature database, and the simulation adjustment of the original image is more in line with the needs of shaping. Obtain a relatively close to real and more intuitive plastic simulation effect, and improve the preoperative reference function of plastic simulation images.
- the program may be stored in a non-volatile computer-readable storage medium.
- the program may be stored in a storage medium of the computer system and executed by at least one processor in the computer system to implement the process including the embodiment of the above-described shaping simulation method.
- the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM) or a random access memory (Random Access Memory, RAM), etc.
- the shaping simulation device further includes a shaping server device.
- the shaping simulation method can be applied to a mobile device, which can be a personal computer, a notebook computer, a palmtop computer, a smartphone, a tablet computer, a portable wearable device, and the like.
- the flow chart of the shaping simulation method is shown in Figure 8.
- the user can scan or photograph the face through electronic devices such as mobile phones, tablets, cameras, and upload three face images (front and side (45 degrees) two) to establish a 3D original image model. Then perform face recognition on the user's original image model, partition each part of the face into forehead, eye (single eye, including eyes, eyebrows), nose (nose, nose wings), chin, face (both cheeks) ) And other partitions (parts are selected by the user manually setting points), through the face data calculation algorithm, the user's facial features are analyzed, and the preset standard values are compared to obtain a facial analysis report, The user can perform automatic shaping simulation according to the suggestions in the analysis report, and the shaping recommendation report is obtained after completion.
- the user can save the image and report formed by the simulation as a certain shaping reference.
- users can also analyze individual face parts and replace them with images of various parts in the plastic face database to obtain plastic simulation images.
- adjustment data can be obtained to adjust the user's face images to obtain plastic simulation.
- the image can also be replaced with a part image.
- the user can select a part independently and select the same type of part image from the plastic face database for the user to choose. After the user determines the required part image, the selected part image is fused to the user's face In the part of the image, the docking position is simulated to obtain another shape simulation image.
- the user can use the fine-tuning function to process the image of a single part, or reselect the part to perform the shape simulation.
- the original image is subjected to corresponding shaping simulation processing to obtain the final shaped simulation image.
- the user can send this simulation effect image to the online shaping through the online consulting service module (ie, data interaction module) Doctors conduct point-to-point consultations. Online plastic surgeons can fine-tune or rematch each part based on this simulated image to obtain the best plastic simulation image; let the plastic surgeon provide plastic suggestions online and modify customers Simulation data of both sides, so that you can get a plastic simulation image that both parties think is good.
- the user can save the simulation image and print the 3D simulation image.
- the image will be saved in the database of the doctor’s plastic surgery server.
- the doctor can call up the data as a basis for the face consultation to reduce the communication time between the two parties; it can also be shared with friends through instant messaging software such as WeChat and QQ through the sharing function.
- instant messaging software such as WeChat and QQ through the sharing function.
- it can only be achieved through simple Blurred image processing cannot be integrated with medical and cosmetic professional technology, which reduces the user's operation time and improves the efficiency and professionalism of plastic simulation, especially when applied to the customer's face-to-face consultation after medical cosmetic surgery, which can make the user more intuitive in advance Obtain post-operative effect simulation images.
- the program can be stored in a computer-readable storage medium. When this program is executed, it includes the steps described in the above method.
- the storage medium includes: ROM/RAM, magnetic disk, optical disk, etc.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Processing Or Creating Images (AREA)
- Image Processing (AREA)
Abstract
The present invention relates to a shaping simulation method and system, a readable storage medium and a device, belonging to the field of image processing technology. The method comprises: acquiring an original image of an object to be shaped, and performing face recognition on the original image to obtain face feature data; performing matching and analysis between the face feature data and a preset shaped face feature database, to acquire a face feature adjustment value; and performing simulation adjustment on the original image according to the face feature adjustment value, to obtain a shaping simulation image. By means of a face feature adjustment value obtained by performing matching between face feature data and data of a shaped face feature database, simulation adjustment on an original image better conforms to the requirements of shaping, and a shaping simulation effect which is relatively close to reality and is more intuitive can be obtained, improving the pre-operative reference effect of a shaping simulation image.
Description
相关申请Related application
本申请要求2018年12月24日申请的,申请号为201811581506.0,名称为“整形模拟方法、系统、可读存储介质和设备”的中国专利申请的优先权,在此将其全文引入作为参考。This application requires the priority of the Chinese patent application with the application number 201811581506.0 and the name "Shaping Simulation Methods, Systems, Readable Storage Media, and Equipment" that was filed on December 24, 2018, and the entire content of which is hereby incorporated by reference.
本发明涉及图像处理技术领域,特别是涉及一种整形模拟方法、系统、可读存储介质和设备。The present invention relates to the field of image processing technology, and in particular, to a plastic modeling method, system, readable storage medium, and device.
随着社会生活水平的不断提高,求美人士越来越多,促使了医美行业的高速发展。用户可以通过各种图像处理软件及工具对自拍照进行图像处理,以达到整形模拟的效果图像,丰富了日常生活。使用图像处理软件的用户经常通过软件对图像中的眼睛、鼻子、脸部、颏部(下巴)等进行图像拉伸处理,例如眼部放大、下巴拉伸、瘦脸、鼻头拉伸等,传统的图像处理方法通常是,对用户静态原始图像进行部位特征提取,然后运用简单的图像模糊计算处理,使得图像某个特征点产生变化,这种方法只是根据用户的喜好进行了图像处理,模拟结果图像难以具备整形的术前参考作用。With the continuous improvement of social living standards, more and more people seeking beauty have promoted the rapid development of the medical beauty industry. Users can use various image processing software and tools to perform image processing on self-portraits to achieve the effect of plastic simulation, which enriches daily life. Users of image processing software often use the software to perform image stretching on the eyes, nose, face, chin (chin), etc. in the image, such as eye enlargement, chin stretching, face thinning, nose stretching, etc., traditional The image processing method is usually to extract part features of the user's static original image, and then use simple image blur calculation processing to make a certain feature point of the image change. This method only performs image processing according to the user's preferences and simulates the resulting image It is difficult to have a preoperative reference for plastic surgery.
发明内容Summary of the invention
基于此,有必要针对传统的图像处理方式对整形美容的模拟效果难以具备整形的术前参考作用的问题,提供一种整形模拟方法、系统、可读存储介质和设备。Based on this, it is necessary to provide a plastic simulation method, system, readable storage medium, and equipment for the problem that the traditional image processing method can not have the pre-operative reference effect of plastic surgery.
一种整形模拟方法,包括以下步骤:A shaping simulation method includes the following steps:
获取待整形对象的原始图像,对原始图像进行人脸识别,获取待整形对象的人脸特征数据;Obtain the original image of the object to be shaped, perform face recognition on the original image, and obtain the facial feature data of the object to be shaped;
对人脸特征数据与预设的整形人脸特征数据库进行匹配分析,获取人脸特征调整值;Perform matching analysis on the face feature data and the preset plastic face feature database to obtain the face feature adjustment value;
根据人脸特征调整值对原始图像进行模拟调节,获得整形模拟图像。The original image is simulated and adjusted according to the face feature adjustment value to obtain a plastic analog image.
根据上述整形模拟方法,其是获取待整形对象的原始图像,对原始图像进行人脸识别,得到人脸特征数据;对人脸特征数据与预设的整形人脸特征数据库进行匹配分析,获取人脸特征调整值;根据人脸特征调整值对原始图像进行模拟调节,获得整形模拟图像。通过人脸特征数据与整形人脸特征数据库的数据的匹配得到的人脸特征调整值,对原始图像的模拟调节更加符合整形的需要,可以得到相对接近真实且更直观的整形模拟效果,提高整形模拟图像的术前参考作用。According to the above-mentioned shaping simulation method, it is to obtain the original image of the object to be shaped, perform face recognition on the original image to obtain face feature data; perform matching analysis on the face feature data and the preset shaped face feature database to obtain the person Face feature adjustment value; simulate and adjust the original image according to the face feature adjustment value to obtain a plastic analog image. The adjustment value of the face feature obtained by matching the face feature data with the data of the plastic face feature database, the simulation adjustment of the original image is more in line with the needs of plastic surgery, and it can obtain a relatively close to real and more intuitive plastic simulation effect, improve plastic surgery Pre-operative reference function of simulated images.
在其中一个实施例中,获取待整形对象的原始图像,对原始图像进行人脸识别的步骤包括以下步骤:In one of the embodiments, the original image of the object to be shaped is acquired, and the step of performing face recognition on the original image includes the following steps:
获取待整形对象的正面图像和多张侧面图像,对正面图像和多张侧面图像进行人脸识别。Obtain the front image and multiple side images of the object to be shaped, and perform face recognition on the front image and the multiple side images.
在其中一个实施例中,获取待整形对象的人脸特征数据的步骤包括以下步骤:In one of the embodiments, the step of acquiring face feature data of the object to be shaped includes the following steps:
获取待整形对象的脸部区域特征点,根据脸部区域特征点对脸部进行分区,获取各分区的特征数据以及脸部的轮廓数据;其中,各分区包括眼部、鼻部、嘴部、面部和颏部,特征数据包括当前分区的位置数据以及当前分区和其他分区之间的相对位置数据。Obtain the feature points of the face area of the object to be shaped, partition the face according to the feature points of the face area, and obtain the feature data of each area and the contour data of the face; where each area includes the eye, nose, mouth, For the face and chin, the feature data includes position data of the current partition and relative position data between the current partition and other partitions.
在其中一个实施例中,对人脸特征数据与预设的整形人脸特征数据库进行匹配分析的步骤包括以下步骤:In one of the embodiments, the step of performing matching analysis on the face feature data and the preset plastic face feature database includes the following steps:
根据人脸特征数据在整形人脸特征数据库中搜索匹配数据,其中,匹配数据与人脸特征数据的相似度大于或等于预设值;Search matching data in the plastic face feature database according to the face feature data, wherein the similarity between the match data and the face feature data is greater than or equal to a preset value;
获取人脸特征调整值的步骤还包括以下步骤:The step of obtaining the adjustment value of face features also includes the following steps:
获取人脸特征数据与匹配数据的比值,根据比值获取人脸特征调整值,其中,人脸特征调整值在比值和数值1之间。Obtain the ratio of the facial feature data to the matching data, and obtain the facial feature adjustment value according to the ratio, where the facial feature adjustment value is between the ratio and the value 1.
在其中一个实施例中,对人脸特征数据与预设的整形人脸特征数据库进行匹配分析的步骤包括以下步骤:In one of the embodiments, the step of performing matching analysis on the face feature data and the preset plastic face feature database includes the following steps:
接收第一选取指令,根据第一选取指令在各分区中选取第一目标分区;Receiving the first selection instruction, and selecting the first target partition among the partitions according to the first selection instruction;
根据除第一目标分区以外的其他分区的特征数据,在整形人脸特征数据库选取子数据库,其中,子数据库中的人脸特征数据与第一目标分区以外的其他分区的特征数据相匹配;According to the feature data of other partitions except the first target partition, select a sub-database in the plastic face feature database, where the face feature data in the sub-database matches the feature data of other partitions than the first target partition;
对第一目标分区的特征数据与子数据库进行匹配分析。Perform matching analysis on the feature data of the first target partition and the sub-database.
在其中一个实施例中,整形模拟方法还包括以下步骤:In one of the embodiments, the shaping simulation method further includes the following steps:
接收修改指令,根据修改指令对整形模拟图像进行特征数据微调;Receive the modification instruction, and fine-tune the characteristic data of the plastic analog image according to the modification instruction;
或者,根据修改指令重新在各分区中选取第一目标分区。Or, select the first target partition from each partition again according to the modification instruction.
在其中一个实施例中,整形模拟方法还包括以下步骤:In one of the embodiments, the shaping simulation method further includes the following steps:
接收针对第二目标分区的触发指令,根据触发指令在整形人脸特征数据库中选取多个备选的分区图像,其中,各分区图像的分区类型与第二目标分区的分区类型相同;Receiving a trigger instruction for the second target partition, and selecting multiple candidate partition images in the plastic face feature database according to the trigger instruction, wherein the partition type of each partition image is the same as the partition type of the second target partition;
显示各分区图像,接收第二选取指令,根据第二选取指令在各分区图像中选取目标分区图像;Display each partition image, receive the second selection instruction, and select the target partition image from each partition image according to the second selection instruction;
将目标分区图像融合到原始图像中对应第二目标分区的位置。The target partition image is fused to the position of the second target partition in the original image.
在其中一个实施例中,将目标分区图像融合到原始图像中对应第二目标分区的位置的步骤包括以下步骤:In one of the embodiments, the step of fusing the target partition image to the position of the second target partition in the original image includes the following steps:
获取第二目标分区的图像大小、位置和颜色数据,根据图像大小、位置和颜色数据对目标分区图像进行调整,将原始图像中对应第二目标分区的部位替换成调整后的图像,并对调整后的图像与原始图像的对接边缘进行模糊处理。Obtain the image size, position and color data of the second target partition, adjust the target partition image according to the image size, position and color data, replace the part of the original image corresponding to the second target partition with the adjusted image, and adjust The butt edge of the original image and the original image are blurred.
在其中一个实施例中,整形模拟方法还包括以下步骤:In one of the embodiments, the shaping simulation method further includes the following steps:
将处理得到的图像经服务器发送至整形服务端,接收整形服务端返回的修改意见数 据,并反馈对修改意见数据的处理信息。Send the processed image to the shaping server through the server, receive the modification opinion data returned by the shaping server, and feed back the processing information of the modification opinion data.
一种整形模拟系统,包括:A shaping simulation system, including:
图像识别单元,用于获取待整形对象的原始图像,对原始图像进行人脸识别,获取待整形对象的人脸特征数据;The image recognition unit is used to obtain the original image of the object to be shaped, perform face recognition on the original image, and obtain the facial feature data of the object to be shaped;
图像分析单元,用于对人脸特征数据与预设的整形人脸特征数据库进行匹配分析,获取人脸特征调整值;The image analysis unit is used to perform matching analysis on the face feature data and the preset plastic face feature database to obtain the face feature adjustment value;
图像调节单元,根据人脸特征调整值对原始图像进行模拟调节,获得整形模拟图像。The image adjustment unit performs analog adjustment on the original image according to the adjustment value of the face feature to obtain a plastic analog image.
根据上述整形模拟系统,图像识别单元获取待整形对象的原始图像,对原始图像进行人脸识别,得到人脸特征数据;图像分析单元对人脸特征数据与预设的整形人脸特征数据库进行匹配分析,获取人脸特征调整值;图像调节单元根据人脸特征调整值对原始图像进行模拟调节,获得整形模拟图像。通过人脸特征数据与整形人脸特征数据库的数据的匹配得到的人脸特征调整值,对原始图像的模拟调节更加符合整形的需要,可以得到相对接近真实且更直观的整形模拟效果,提高整形模拟图像的术前参考作用。According to the above-mentioned shaping simulation system, the image recognition unit obtains the original image of the object to be shaped and performs face recognition on the original image to obtain face feature data; the image analysis unit matches the face feature data with the preset shaped face feature database Analyze and obtain the facial feature adjustment value; the image adjustment unit performs analog adjustment on the original image according to the facial feature adjustment value to obtain a plastic analog image. The adjustment value of the face feature obtained by matching the face feature data with the data of the plastic face feature database, the simulation adjustment of the original image is more in line with the needs of plastic surgery, and it can obtain a relatively close to real and more intuitive plastic simulation effect, improve plastic surgery Pre-operative reference function of simulated images.
在其中一个实施例中,图像识别单元获取待整形对象的正面图像和多张侧面图像,对正面图像和多张侧面图像进行人脸识别。In one of the embodiments, the image recognition unit acquires a front image and a plurality of side images of the object to be shaped, and performs face recognition on the front image and the plurality of side images.
在其中一个实施例中,图像识别单元获取待整形对象的脸部区域特征点,根据脸部区域特征点对脸部进行分区,获取各分区的特征数据以及脸部的轮廓数据;其中,各分区包括眼部、鼻部、嘴部、面部和颏部,特征数据包括当前分区的位置数据以及当前分区和其他分区之间的相对位置数据。In one of the embodiments, the image recognition unit acquires the feature points of the face area of the object to be shaped, partitions the face according to the feature points of the face area, and obtains the feature data of each partition and the contour data of the face; wherein, each partition Including the eyes, nose, mouth, face and chin, the feature data includes the position data of the current partition and the relative position data between the current partition and other partitions.
在其中一个实施例中,图像分析单元根据人脸特征数据在整形人脸特征数据库中搜索匹配数据,其中,匹配数据与人脸特征数据的相似度大于或等于预设值;In one of the embodiments, the image analysis unit searches for matching data in the plastic face feature database based on the face feature data, wherein the similarity between the match data and the face feature data is greater than or equal to a preset value;
图像分析单元获取人脸特征数据与匹配数据的比值,根据比值获取人脸特征调整值,其中,人脸特征调整值在比值和数值1之间。The image analysis unit obtains the ratio of the face feature data and the matching data, and obtains the face feature adjustment value according to the ratio, where the face feature adjustment value is between the ratio and the value 1.
在其中一个实施例中,图像分析单元接收第一选取指令,根据第一选取指令在各分区中选取第一目标分区;根据除第一目标分区以外的其他分区的特征数据,在整形人脸特征数据库选取子数据库,对第一目标分区的特征数据与子数据库进行匹配分析;其中,子数据库中的人脸特征数据与第一目标分区以外的其他分区的特征数据相匹配。In one of the embodiments, the image analysis unit receives the first selection instruction and selects the first target partition among the partitions according to the first selection instruction; according to the feature data of the partitions other than the first target partition, the face features are reshaped The database selects a sub-database, and performs matching analysis on the feature data of the first target partition and the sub-database; wherein, the face feature data in the sub-database matches the feature data of the partitions other than the first target partition.
在其中一个实施例中,整形模拟系统还包括图像修改单元,用于接收修改指令,根据修改指令对整形模拟图像进行特征数据微调;或者,根据修改指令重新在各分区中选取第一目标分区。In one of the embodiments, the shaping simulation system further includes an image modification unit for receiving a modification instruction, fine-tuning the characteristic data of the shaping simulation image according to the modification instruction; or, according to the modification instruction, reselecting the first target partition in each partition.
在其中一个实施例中,整形模拟系统还包括图像组合单元,用于接收针对第二目标分区的触发指令,根据触发指令在整形人脸特征数据库中选取多个备选的分区图像,其中,各分区图像的分区类型与第二目标分区的分区类型相同;In one of the embodiments, the shaping simulation system further includes an image combination unit for receiving a trigger instruction for the second target partition, and selecting a plurality of candidate partition images in the shaping facial feature database according to the trigger instruction, wherein each The partition type of the partition image is the same as the partition type of the second target partition;
图像组合单元还用于显示各分区图像,接收第二选取指令,根据第二选取指令在各分区图像中选取目标分区图像;The image combination unit is further used to display the images of each partition, receive the second selection instruction, and select the target partition image among the partition images according to the second selection instruction;
图像组合单元还用于将目标分区图像融合到原始图像中对应第二目标分区的位置。The image combining unit is also used to fuse the target partition image to the position corresponding to the second target partition in the original image.
在其中一个实施例中,图像组合单元获取第二目标分区的图像大小、位置和颜色数据,根据图像大小、位置和颜色数据对目标分区图像进行调整,将原始图像中对应第二目标分区的部位替换成调整后的图像,并对调整后的图像与原始图像的对接边缘进行模糊处理。In one of the embodiments, the image combining unit acquires the image size, position and color data of the second target partition, adjusts the target partition image according to the image size, position and color data, and compares the part of the original image corresponding to the second target partition Replace with the adjusted image, and blur the edge of the interface between the adjusted image and the original image.
在其中一个实施例中,整形模拟系统还包括数据交互单元,用于将处理得到的图像经服务器发送至整形服务端,接收整形服务端返回的修改意见数据,并反馈对修改意见数据的处理信息。In one of the embodiments, the shaping simulation system further includes a data interaction unit for sending the processed image to the shaping server through the server, receiving the modification opinion data returned by the shaping server, and feeding back processing information on the modification opinion data .
一种可读存储介质,其上存储有可执行程序,可执行程序被处理器执行时实现上述的整形模拟方法的步骤。A readable storage medium has stored thereon an executable program, and when the executable program is executed by a processor, the steps of the above-mentioned shaping simulation method are realized.
上述可读存储介质,通过其存储的可执行程序,可以实现通过人脸特征数据与整形人脸特征数据库的数据的匹配得到人脸特征调整值,对原始图像的模拟调节更加符合整形的需要,可以得到相对接近真实且更直观的整形模拟效果,提高整形模拟图像的术前参考作用。The above-mentioned readable storage medium, through the executable program stored in it, can achieve the adjustment value of the facial features by matching the facial feature data with the data of the plastic facial feature database, and the analog adjustment of the original image is more in line with the needs of plastic surgery. A relatively close to real and more intuitive plastic simulation effect can be obtained, and the preoperative reference function of the plastic simulation image can be improved.
一种整形模拟设备,包括存储器和处理器,存储器存储有可执行程序,处理器执行可执行程序时实现上述的整形模拟方法的步骤。A shaping simulation device includes a memory and a processor. The memory stores an executable program. When the processor executes the executable program, the steps of the shaping simulation method described above are implemented.
上述整形模拟设备,通过在处理器上运行可执行程序,可以实现通过人脸特征数据与整形人脸特征数据库的数据的匹配得到人脸特征调整值,对原始图像的模拟调节更加符合整形的需要,可以得到相对接近真实且更直观的整形模拟效果,提高整形模拟图像的术前参考作用。The above-mentioned shaping simulation device can achieve the adjustment value of the face feature by matching the face feature data with the data of the shaping face feature database by running the executable program on the processor, and the simulation adjustment of the original image is more in line with the needs of shaping , You can get relatively close to the real and more intuitive plastic simulation effect, improve the pre-operative reference role of plastic simulation images.
图1是一个实施例中整形模拟方法的应用场景图;FIG. 1 is an application scenario diagram of a shaping simulation method in an embodiment;
图2是一个实施例中整形模拟方法的流程示意图;2 is a schematic flow chart of a method for shaping simulation in an embodiment;
图3是一个实施例中整形模拟方法的交互示意图;FIG. 3 is an interactive schematic diagram of a shaping simulation method in an embodiment;
图4是一个实施例中整形模拟系统的结构示意图;4 is a schematic structural diagram of a shaping simulation system in an embodiment;
图5是另一个实施例中整形模拟系统的结构示意图;5 is a schematic structural diagram of a shaping simulation system in another embodiment;
图6是又一个实施例中整形模拟系统的结构示意图;6 is a schematic structural diagram of a shaping simulation system in yet another embodiment;
图7是再一个实施例中整形模拟系统的结构示意图;7 is a schematic structural diagram of a shaping simulation system in yet another embodiment;
图8是一个实施例中整形模拟方法的具体应用流程简图。FIG. 8 is a schematic diagram of a specific application process of the shaping simulation method in an embodiment.
为使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步的详细说明。应当理解,此处所描述的具体实施方式仅仅用以解释本发明,并不限定本发明的保护范围。另外还需要说明的是,为了便于描述,附图中仅示出了与本发明 相关的部分而非全部内容。In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention, and do not limit the protection scope of the present invention. In addition, it should be noted that, in order to facilitate description, the drawings only show parts related to the present invention rather than all contents.
需要说明的是,本发明实施例所涉及的术语“第一\第二”仅仅是区别类似的对象,不代表针对对象的特定排序,可以理解地,“第一\第二”在允许的情况下可以互换特定的顺序或先后次序。应该理解“第一\第二”区分的对象在适当情况下可以互换,以使这里描述的本发明的实施例能够以除了在这里图示或描述的那些以外的顺序实施。It should be noted that the term “first\second” involved in the embodiment of the present invention is only to distinguish similar objects, and does not represent a specific order for objects. Understandably, “first\second” is allowed The specific order or sequence can be interchanged below. It should be understood that the objects distinguished by “first\second” may be interchanged under appropriate circumstances, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.
本申请提供的整形模拟方法,可以应用于如图1所示的应用环境中,移动设备可以获取待整形对象(即使用者)的原始图像,对原始图像进行人脸识别,得到人脸特征数据;对人脸特征数据与预设的整形人脸特征数据库进行匹配分析,获取人脸特征调整值;根据人脸特征调整值对原始图像进行模拟调节,获得整形模拟图像。其中,移动设备可以是各种具备获取使用者图像和图像处理功能的设备,如个人计算机、笔记本电脑、掌上电脑、智能手机、平板电脑、便携式可穿戴设备等。The shaping simulation method provided in this application can be applied in the application environment shown in FIG. 1, the mobile device can obtain the original image of the object to be shaped (ie, the user), perform face recognition on the original image, and obtain face feature data ; Perform matching analysis on the face feature data and the preset plastic face feature database to obtain the face feature adjustment value; simulate and adjust the original image according to the face feature adjustment value to obtain the plastic simulation image. Among them, the mobile device may be a variety of devices with functions of acquiring user images and image processing, such as personal computers, notebook computers, PDAs, smart phones, tablet computers, and portable wearable devices.
参见图2所示,为本发明一个实施例的整形模拟方法的流程示意图。该实施例中的整形模拟方法包括以下步骤:Referring to FIG. 2, it is a schematic flowchart of a shaping simulation method according to an embodiment of the present invention. The shaping simulation method in this embodiment includes the following steps:
步骤S110:获取待整形对象的原始图像,对原始图像进行人脸识别,获取待整形对象的人脸特征数据;Step S110: Obtain the original image of the object to be shaped, perform face recognition on the original image, and obtain the facial feature data of the object to be shaped;
在本步骤中,原始图像可以通过电子设备的摄像头拍摄获得,或者通过扫描获得;人脸识别时可以分析原始图像中的人脸的特征,进而得到人脸特征数据;In this step, the original image can be captured by the camera of the electronic device or obtained by scanning; during facial recognition, the characteristics of the human face in the original image can be analyzed to obtain facial feature data;
步骤S120:对人脸特征数据与预设的整形人脸特征数据库进行匹配分析,获取人脸特征调整值;Step S120: Perform matching analysis on the face feature data and the preset plastic face feature database to obtain the face feature adjustment value;
在本步骤中,整形人脸特征数据库是预先设定的整形常用的人脸特征素材数据的集合,通过实际的人脸特征数据与整形人脸特征数据库的数据的匹配分析,可以得知人脸特征数据与整形人脸的特征差异,依据此种差异可以获取人脸特征调整值,该人脸特征调整值可以减小特征差异,使调整后的图像中的人脸与整形人脸相逼近,实现整形模拟的效果;In this step, the plastic face feature database is a pre-set collection of commonly used face feature material data for plastic surgery. Through the matching analysis of the actual face feature data and the data of the plastic face feature database, you can know the face features The difference between the characteristics of the data and the plastic face. According to this difference, the facial feature adjustment value can be obtained. The facial feature adjustment value can reduce the feature difference, so that the face in the adjusted image is close to the plastic face to achieve The effect of plastic simulation;
步骤S130:根据人脸特征调整值对原始图像进行模拟调节,获得整形模拟图像;Step S130: Perform simulation adjustment on the original image according to the face feature adjustment value to obtain a plastic simulation image;
在本步骤中,在根据人脸特征调整值进行模拟调节时,主要是对人脸特征数据进行调节,可以基于人脸特征点进行图像变形处理。In this step, when performing analog adjustment according to the face feature adjustment value, it is mainly to adjust the face feature data, and image deformation processing can be performed based on the face feature points.
在本实施例中,获取待整形对象的原始图像,对原始图像进行人脸识别,得到人脸特征数据;对人脸特征数据与预设的整形人脸特征数据库进行匹配分析,获取人脸特征调整值;根据人脸特征调整值对原始图像进行模拟调节,获得整形模拟图像。通过人脸特征数据与整形人脸特征数据库的数据的匹配得到的人脸特征调整值,对原始图像的模拟调节更加符合整形的需要,可以得到相对接近真实且更直观的整形模拟效果,提高整形模拟图像的术前参考作用。In this embodiment, the original image of the object to be shaped is obtained, and the original image is subjected to face recognition to obtain face feature data; the face feature data is matched with the preset shaped face feature database to obtain face features Adjustment value; adjust the original image according to the adjustment value of the facial features to obtain the plastic simulation image. The adjustment value of the face feature obtained by matching the face feature data with the data of the plastic face feature database, the simulation adjustment of the original image is more in line with the needs of plastic surgery, and it can obtain a relatively close to real and more intuitive plastic simulation effect, improve plastic surgery Pre-operative reference function of simulated images.
需要说明的是,在对人脸特征数据与预设的整形人脸特征数据库进行匹配分析时,可 以生成一份图像人脸分析报告,在报告中给出以人脸特征调整值为基础的整形建议,在接收到确认信息后,对原始图像进行自动模拟调节,完成后给出整形建议报告,包括具体的整形部位、整形方式以及整形效果描述信息。It should be noted that when matching analysis of the facial feature data and the preset plastic facial feature database, an image facial analysis report can be generated, and the plastic surgery based on the facial feature adjustment value is given in the report It is recommended that after receiving the confirmation information, the original image is automatically simulated and adjusted, and a plastic recommendation report is given after completion, including specific plastic parts, plastic methods and plastic effect description information.
进一步的,在进行模拟调节时可以使用扩散、锐化、变形算法对图像进行处理。Furthermore, diffusion, sharpening, and deformation algorithms can be used to process images during simulation adjustment.
进一步的,在获取待整形对象的原始图像时,可以划定拍摄区域,如与脸部形状相似的拍摄区域等,在待整形对象的脸部进入拍摄区域时进行拍摄,得得到的原始图像就是所需的脸部图像,如此可减少人脸识别的时间,提高识别的准确度;另外,在获取待整形对象的原始图像时,感应拍摄时的亮度,若亮度小于预设亮度值,则开启闪光灯或者提示亮度不足;在进行人脸识别时,还可以检测人脸上的妆容,提示清洁后再进行整形模拟,若检测到人脸上有配饰,提示取下配饰,如眼镜、假睫毛、鼻钉等。Further, when acquiring the original image of the object to be shaped, the shooting area can be defined, such as a shooting area similar to the shape of the face, etc. When the face of the object to be shaped enters the shooting area, the original image is The required face image can reduce the time of face recognition and improve the accuracy of recognition. In addition, when acquiring the original image of the object to be shaped, it senses the brightness when shooting, if the brightness is less than the preset brightness value, turn on The flash or the brightness is insufficient; during face recognition, you can also detect the makeup on the face, prompt to clean and then perform plastic simulation, if you detect accessories on the face, prompt to remove the accessories, such as glasses, false eyelashes, Nose nails, etc.
在一个实施例中,获取待整形对象的原始图像,对原始图像进行人脸识别的步骤包括以下步骤:In an embodiment, the original image of the object to be shaped is obtained, and the step of performing face recognition on the original image includes the following steps:
获取待整形对象的正面图像和多张侧面图像,对正面图像和多张侧面图像进行人脸识别。Obtain the front image and multiple side images of the object to be shaped, and perform face recognition on the front image and the multiple side images.
在本实施例中,可以获取待整形对象的多张图像,包括正面图像和侧面图像,正面图像和多张侧面图像是从不同角度获得的图像,以此为依据可以减小光照、角度等影响,使人脸识别更加准确。In this embodiment, multiple images of the object to be shaped can be obtained, including a frontal image and a side image. The frontal image and the multiple side images are images obtained from different angles, based on which the influence of illumination, angle, etc. can be reduced To make face recognition more accurate.
具体的,在实际操作中,可以获取待整形对象的正面图像和两张侧面45度角的侧面图像。Specifically, in actual operation, a front image of the object to be shaped and two side images at a 45-degree angle can be obtained.
进一步的,在得到正面图像和侧面图像后,可以此为依据构建3D原始图像模型,利用3D模型算法进行准确的人脸识别。Further, after obtaining the front image and the side image, the 3D original image model can be constructed based on this, and the 3D model algorithm can be used for accurate face recognition.
在一个实施例中,获取待整形对象的人脸特征数据的步骤包括以下步骤:In one embodiment, the step of acquiring face feature data of the object to be shaped includes the following steps:
获取待整形对象的脸部区域特征点,根据脸部区域特征点对脸部进行分区,获取各分区的特征数据以及脸部的轮廓数据;其中,各分区包括眼部、鼻部、嘴部、面部和颏部,特征数据包括当前分区的位置数据以及当前分区和其他分区之间的相对位置数据。Obtain the feature points of the face area of the object to be shaped, partition the face according to the feature points of the face area, and obtain the feature data of each area and the contour data of the face; where each area includes the eye, nose, mouth, For the face and chin, the feature data includes position data of the current partition and relative position data between the current partition and other partitions.
在本实施例中,在人脸识别之后,可以获取脸部区域特征点,人脸上不同区域部位的特征点分布不同,利用脸部区域特征点可以对脸部区域进行分区,得到如眼部、鼻部、嘴部、面部、颏部等区域的特征数据以及脸部的轮廓数据,特征数据包括当前人脸部位的位置数据以及当前人脸部位和其他部位之间的相对位置数据,以便于对人脸的不同区域进行模拟整形。In this embodiment, after face recognition, facial region feature points can be obtained, and the feature point distribution of different regions on the human face is different. The facial region feature points can be used to partition the facial region to obtain, for example, eye parts. , Nose, mouth, face, chin, etc. and the contour data of the face, the feature data includes the position data of the current face part and the relative position data between the current face part and other parts, In order to simulate and shape different areas of the human face.
具体的,人脸上的特征区域可以包括额头、眼睛、眉毛、眼睑、鼻梁、鼻头、鼻翼、脸颊、嘴巴、颏部等,还包括脸部整体轮廓等脸型数据,上述特征区域可以构建不同的特征点,实现对人脸特征区域部位的划分,在获取特征数据时,不仅有特征区域部位自身的数据,还有特征区域部位的位置数据以及与其他特征区域的相对位置数据,以及特征区域部位的颜 色、亮度等数据,在整形模拟时综合上述数据可以提高模拟效果的协调性。Specifically, the characteristic regions on the human face may include forehead, eyes, eyebrows, eyelids, nose bridge, nose, nose wings, cheeks, mouth, chin, etc., and also include facial contour data such as the overall contour of the face. Feature points, to achieve the division of facial feature area parts, when acquiring feature data, not only the data of the feature area parts themselves, but also the position data of the feature area parts and the relative position data with other feature areas, and the feature area parts The data such as color and brightness can be integrated in the shaping simulation to improve the coordination of the simulation effect.
进一步的,除了根据人脸识别结果进行脸部区域分区外,还可以手动设置点位进行选取,如接收区域选取指令,在原始图像的人脸上选取指定区域,获取指定区域的特征数据,提高整形模拟的灵活性。Further, in addition to partitioning the face area based on the face recognition results, you can also manually set the points for selection, such as receiving an area selection instruction, selecting a specified area on the face of the original image, and obtaining the characteristic data of the specified area to improve The flexibility of plastic modeling.
进一步的,进行脸部区域分区,并对分区区域的特征数据与预设的整形人脸特征数据库进行匹配分析后,可以获得建议整形的分区区域,获取该分区区域的人脸特征调整值。Further, after partitioning the face area, and matching the feature data of the partition area with the preset plastic face feature database, it is possible to obtain a partition area that is recommended to be shaped and obtain the adjustment value of the face feature of the partition area.
在一个实施例中,对人脸特征数据与预设的整形人脸特征数据库进行匹配分析的步骤包括以下步骤:In one embodiment, the step of performing matching analysis on the face feature data and the preset plastic face feature database includes the following steps:
根据人脸特征数据在整形人脸特征数据库中搜索匹配数据,其中,匹配数据与人脸特征数据的相似度大于或等于预设值;Search matching data in the plastic face feature database according to the face feature data, wherein the similarity between the match data and the face feature data is greater than or equal to a preset value;
获取人脸特征调整值的步骤还包括以下步骤:The step of obtaining the adjustment value of face features also includes the following steps:
获取人脸特征数据与整形人脸特征数据库中的匹配数据的比值,根据比值获取人脸特征调整值,其中,人脸特征调整值在比值和数值1之间。Obtain the ratio of the facial feature data to the matching data in the plastic facial feature database, and obtain the facial feature adjustment value according to the ratio, where the facial feature adjustment value is between the ratio and the value 1.
在本实施例中,可以利用人脸特征数据与整形人脸特征数据库中数据的相似度来确定匹配数据,对人脸特征数据与整形人脸特征数据库进行相似度匹配分析后,可以在整形人脸特征数据库中得到与图像分析后的人脸特征数据相匹配的匹配数据,但与图像分析后的人脸特征数据又不同,计算两者具体特征点的数据的比值,把该比值作为调整值的界限,将人脸特征调整值设置在该比值和数值1之间,利用人脸特征调整值对图像进行模拟调节后,可以将图像中的人脸特征数据与整形人脸数据库中的数据相逼近,实现整形的模拟效果。In this embodiment, the similarity between the face feature data and the data in the plastic face feature database can be used to determine the matching data. After the similarity matching analysis is performed on the face feature data and the plastic face feature database, the person can be shaped The matching data matching the face feature data after image analysis is obtained from the face feature database, but it is different from the face feature data after image analysis. Calculate the ratio of the data of the specific feature points of the two and use the ratio as the adjustment value. Set the face feature adjustment value between this ratio and the value 1, and use the face feature adjustment value to simulate the adjustment of the image. You can compare the face feature data in the image with the data in the plastic face database Approximation, to achieve the simulation effect of plastic surgery.
进一步的,人脸特征调整值可以是动态的数据,根据待整形对象的需要在比值和数值1之间动态调节。Further, the face feature adjustment value may be dynamic data, which is dynamically adjusted between the ratio and the value 1 according to the needs of the object to be shaped.
在一个实施例中,对人脸特征数据与预设的整形人脸特征数据库进行匹配分析的步骤包括以下步骤:In one embodiment, the step of performing matching analysis on the face feature data and the preset plastic face feature database includes the following steps:
接收第一选取指令,根据第一选取指令在各分区中选取第一目标分区;Receiving the first selection instruction, and selecting the first target partition among the partitions according to the first selection instruction;
根据除第一目标分区以外的其他分区的特征数据,在整形人脸特征数据库选取子数据库,其中,子数据库中的人脸特征数据与第一目标分区以外的其他分区的特征数据相匹配;According to the feature data of other partitions except the first target partition, select a sub-database in the plastic face feature database, where the face feature data in the sub-database matches the feature data of other partitions than the first target partition;
对第一目标分区的特征数据与子数据库进行匹配分析。Perform matching analysis on the feature data of the first target partition and the sub-database.
在本实施例中,可以通过第一选取指令选取第一目标分区,并根据其他分区的特征数据在整形人脸特征数据库选取子数据库,由于子数据库中的人脸特征数据与第一目标分区以外的其他分区的特征数据相匹配,因此对第一目标分区的特征数据与子数据库进行匹配分析时,得到的第一目标分区的特征调整值可以使第一目标分区与其他分区相协调,提高对单一分区部位进行整形模拟时的整体协调性。In this embodiment, the first target partition can be selected through the first selection instruction, and a sub-database can be selected in the plastic face feature database according to the feature data of other partitions, because the face feature data in the sub-database is different from the first target partition The feature data of the other partitions of the database match. Therefore, when the feature data of the first target partition and the sub-database are matched and analyzed, the feature adjustment value of the first target partition obtained can make the first target partition coordinate with other partitions and improve the The overall coordination of the plastic simulation of a single partition.
在一个实施例中,整形模拟方法还包括以下步骤:In one embodiment, the shaping simulation method further includes the following steps:
接收修改指令,根据修改指令对整形模拟图像进行特征数据微调;Receive the modification instruction, and fine-tune the characteristic data of the plastic analog image according to the modification instruction;
或者,根据修改指令重新在各分区中选取第一目标分区。Or, select the first target partition from each partition again according to the modification instruction.
在本实施例中,依据人脸特征调整值对图像进行模拟调节,获得整形模拟图像后,该整形模拟图像可能并非符合待整形对像的要求,此时可以接收修改指令,根据修改指令进行特征数据微调,使之符合待整形对像的具体要求;或者,当前第一目标分区的整形模拟不符合待整形对像的要求,可以重新选取新的第一目标分区进行整形模拟,以此可以按照待整形对象的要求对模拟整形进行调节。In this embodiment, the image is simulated and adjusted according to the facial feature adjustment value, and after obtaining the plastic simulation image, the plastic simulation image may not meet the requirements of the object to be shaped, at this time, a modification instruction may be received, and the features may be modified according to the modification instruction. Fine-tune the data to meet the specific requirements of the object to be reshaped; or, the current simulation of the first target partition does not meet the requirements of the object to be reshaped. You can select a new first target partition for reshaping simulation, so that you can follow the The requirements of the object to be reshaped adjust the simulated reshaping.
在一个实施例中,整形模拟方法还包括以下步骤:In one embodiment, the shaping simulation method further includes the following steps:
接收针对第二目标分区的触发指令,根据触发指令在整形人脸特征数据库中选取多个备选的分区图像,其中,各分区图像的分区类型与第二目标分区的分区类型相同;Receiving a trigger instruction for the second target partition, and selecting multiple candidate partition images in the plastic face feature database according to the trigger instruction, wherein the partition type of each partition image is the same as the partition type of the second target partition;
显示各分区图像,接收第二选取指令,根据第二选取指令在各分区图像中选取目标分区图像;Display each partition image, receive the second selection instruction, and select the target partition image from each partition image according to the second selection instruction;
将目标分区图像融合到原始图像中对应第二目标分区的位置。The target partition image is fused to the position of the second target partition in the original image.
在本实施例中,可以选择并触发第二目标分区,在整形人脸特征数据库中选取与第二目标分区类型相同的多个备选的分区图像,并显示分区图像,供待整形对象进行选择,在待整形对象通过第二选取指令选定目标分区图像后,将目标分区图像融合到原始图像中,以达到待整形对象自主选择整形内容,并展示整形模拟图像的效果。In this embodiment, a second target partition can be selected and triggered, multiple candidate partition images of the same type as the second target partition are selected in the plastic face feature database, and the partition images are displayed for selection of objects to be shaped After the object to be shaped selects the target partition image through the second selection instruction, the target partition image is fused into the original image, so that the object to be shaped can independently select the shaping content and show the effect of shaping the simulated image.
具体的,第二目标分区可以是额头、眼睛、眉毛、鼻子、嘴巴、颏部等部位,例如选取眼睛部位作为第二目标分区,可以在整形人脸特征数据库中选取不同形状的眼睛图像并显示,供待整形对象选择,确定后将选取的新的眼睛图形融合到待整形对象的原始图像中,形成整形模拟图像。Specifically, the second target partition may be a forehead, eyes, eyebrows, nose, mouth, chin, etc. For example, selecting an eye part as the second target partition may select and display eye images of different shapes in the plastic face feature database and display For selection of the object to be shaped, and after the determination, the selected new eye shape is merged into the original image of the object to be shaped to form a shaped simulation image.
在一个实施例中,将目标分区图像融合到原始图像中对应第二目标分区的位置的步骤包括以下步骤:In one embodiment, the step of fusing the target partition image to the position of the second target partition in the original image includes the following steps:
获取第二目标分区的图像大小、位置和颜色数据,根据图像大小、位置和颜色数据对目标分区图像进行调整,将原始图像中对应第二目标分区的部位替换成调整后的图像,并对调整后的图像与原始图像的对接边缘进行模糊处理。Obtain the image size, position and color data of the second target partition, adjust the target partition image according to the image size, position and color data, replace the part of the original image corresponding to the second target partition with the adjusted image, and adjust The butt edge of the original image and the original image are blurred.
在本实施例中,第二目标分区是原始图像的一部分,其具备图像大小、位置、颜色等属性,根据图像大小、位置和颜色等数据对目标分区图像进行调整,可以使目标分区图像与原始图像相协调,另外,对调整后的图像与原始图像的对接边缘进行模糊处理,通过上述处理可以避免最终得到的图像显示突兀,体现良好的模拟效果。In this embodiment, the second target partition is a part of the original image, which has attributes such as image size, position, color, etc. The target partition image is adjusted according to data such as image size, position, and color, so that the target partition image and the original The image is coordinated. In addition, the edge of the interface between the adjusted image and the original image is blurred. The above processing can avoid the abrupt display of the final image and reflect a good simulation effect.
需要说明的是,在进行融合和模糊处理之后,可以得到另一张整形模拟图像,与根据人脸特征调整值对原始图像进行模拟调节得到的整形模拟图像不同;在进行融合和模糊处理后,可以接收修改指令,根据修改指令对得到的图像进行特征数据微调;或者,根据修改指 令重新在各分区中选取第二目标分区。It should be noted that after the fusion and blur processing, another plastic simulation image can be obtained, which is different from the plastic simulation image obtained by adjusting the original image according to the adjustment value of the face feature; after the fusion and blur processing, The modification instruction may be received, and the obtained image may be fine-tuned for the characteristic data according to the modification instruction; or, the second target partition may be selected again from each partition according to the modification instruction.
在一个实施例中,整形模拟方法还包括以下步骤:In one embodiment, the shaping simulation method further includes the following steps:
将处理得到的图像经服务器发送至整形服务端,接收整形服务端返回的修改意见数据,并反馈对修改意见数据的处理信息。Send the processed image to the shaping server through the server, receive the modification opinion data returned by the shaping server, and feed back the processing information on the modification opinion data.
在本实施例中,经过处理得到图像后,可以将其经服务器发送至整形服务端,整形服务端可以获取对图像的修改意见数据并返回;发送端可以针对修改意见数据反馈相应的处理信息,通过此种交互方式可以对图像进行进一步的调整和修改。In this embodiment, after the image is processed, it can be sent to the shaping server through the server, and the shaping server can obtain the modification opinion data for the image and return it; the sending end can feed back the corresponding processing information for the modification opinion data, Through this interactive way, the image can be further adjusted and modified.
需要说明的是,处理得到的图像可以是根据人脸特征调整值进行模拟调节后得到的整形模拟图像,也可以是选取不同分区进行融合处理后的图像。It should be noted that the processed image may be an orthopaedic simulated image obtained by performing simulation adjustment according to the adjustment value of the face feature, or an image obtained by selecting different partitions and performing fusion processing.
具体的,上述处理过程可以应用在用户一侧的咨询终端设备中,整形服务端可以设置在整形医生一侧的接收终端,用户的咨询终端将整形模拟图像发送至整形医生的接收终端,邀请医生对整形模拟图像进行调整并给出修改意见,接收终端返回修改意见数据,交互示意图如图3所示。Specifically, the above processing procedure can be applied to the consulting terminal device on the user side, and the shaping server can be provided on the receiving terminal on the side of the plastic doctor. The consulting terminal of the user sends the plastic simulation image to the receiving terminal of the plastic doctor, inviting the doctor Adjust the plastic simulation image and give the modification opinion, the receiving terminal returns the modification opinion data, and the interactive schematic diagram is shown in Figure 3.
进一步的,还可以直接将待整形对象的原始图像经服务器发送至整形服务端,接收整形服务端返回的修改意见数据,并反馈对修改意见数据的处理信息。Further, the original image of the object to be reshaped can be directly sent to the reshaping server through the server, receive the modification opinion data returned by the reshaping server, and feed back processing information on the modification opinion data.
根据上述整形模拟方法,本发明实施例还提供一种整形模拟系统,以下就本发明的整形模拟系统的实施例进行详细说明。According to the above-mentioned shaping simulation method, an embodiment of the present invention also provides a shaping simulation system. The embodiment of the shaping simulation system of the present invention will be described in detail below.
参见图4所示,为本发明一个实施例的整形模拟系统的结构示意图。该实施例中的整形模拟系统包括:Referring to FIG. 4, it is a schematic structural diagram of a shaping simulation system according to an embodiment of the present invention. The shaping simulation system in this embodiment includes:
图像识别单元210,用于获取待整形对象的原始图像,对原始图像进行人脸识别,获取待整形对象的人脸特征数据;The image recognition unit 210 is used to obtain the original image of the object to be shaped, perform face recognition on the original image, and obtain the facial feature data of the object to be shaped;
图像分析单元220,用于对人脸特征数据与预设的整形人脸特征数据库进行匹配分析,获取人脸特征调整值;The image analysis unit 220 is used to perform matching analysis on the facial feature data and the preset plastic facial feature database to obtain the facial feature adjustment value;
图像调节单元230,根据人脸特征调整值对原始图像进行模拟调节,获得整形模拟图像。The image adjustment unit 230 performs analog adjustment on the original image according to the face feature adjustment value to obtain a plastic analog image.
在本实施例中,图像识别单元210获取待整形对象的原始图像,对原始图像进行人脸识别,得到人脸特征数据;图像分析单元220对人脸特征数据与预设的整形人脸特征数据库进行匹配分析,获取人脸特征调整值;图像调节单元230根据人脸特征调整值对原始图像进行模拟调节,获得整形模拟图像。通过人脸特征数据与整形人脸特征数据库的数据的匹配得到的人脸特征调整值,对原始图像的模拟调节更加符合整形的需要,可以得到相对接近真实且更直观的整形模拟效果,提高整形模拟图像的术前参考作用。In this embodiment, the image recognition unit 210 obtains the original image of the object to be shaped, and performs face recognition on the original image to obtain face feature data; the image analysis unit 220 compares the face feature data with the preset shaped face feature database Perform matching analysis to obtain the face feature adjustment value; the image adjustment unit 230 performs analog adjustment on the original image according to the face feature adjustment value to obtain a plastic analog image. The adjustment value of the face feature obtained by matching the face feature data with the data of the plastic face feature database, the simulation adjustment of the original image is more in line with the needs of plastic surgery, and it can obtain a relatively close to real and more intuitive plastic simulation effect, improve plastic surgery Pre-operative reference function of simulated images.
在一个实施例中,图像识别单元210获取待整形对象的正面图像和多张侧面图像,对正面图像和多张侧面图像进行人脸识别。In one embodiment, the image recognition unit 210 acquires a front image and multiple side images of the object to be shaped, and performs face recognition on the front image and the multiple side images.
在一个实施例中,图像识别单元210获取待整形对象的脸部区域特征点,根据脸部区域特征点对脸部进行分区,获取各分区的特征数据以及脸部的轮廓数据;其中,各分区包括眼部、鼻部、嘴部、面部和颏部,特征数据包括当前分区的位置数据以及当前分区和其他分区之间的相对位置数据。In one embodiment, the image recognition unit 210 acquires the facial region feature points of the object to be shaped, partitions the face according to the facial region feature points, and acquires the feature data of each partition and the contour data of the face; wherein, each partition Including the eyes, nose, mouth, face and chin, the feature data includes the position data of the current partition and the relative position data between the current partition and other partitions.
在一个实施例中,图像分析单元220根据人脸特征数据在整形人脸特征数据库中搜索匹配数据,其中,匹配数据与人脸特征数据的相似度大于或等于预设值;In one embodiment, the image analysis unit 220 searches for matching data in the plastic face feature database according to the face feature data, where the similarity of the match data and the face feature data is greater than or equal to a preset value;
图像分析单元220获取人脸特征数据与匹配数据的比值,根据比值获取人脸特征调整值,其中,人脸特征调整值在比值和数值1之间。The image analysis unit 220 acquires the ratio of the facial feature data to the matching data, and acquires the facial feature adjustment value according to the ratio, where the facial feature adjustment value is between the ratio and the value 1.
在一个实施例中,图像分析单元220接收第一选取指令,根据第一选取指令在各分区中选取第一目标分区;根据除第一目标分区以外的其他分区的特征数据,在整形人脸特征数据库选取子数据库,对第一目标分区的特征数据与子数据库进行匹配分析;其中,子数据库中的人脸特征数据与第一目标分区以外的其他分区的特征数据相匹配。In one embodiment, the image analysis unit 220 receives the first selection instruction and selects the first target partition among the partitions according to the first selection instruction; according to the feature data of the partitions other than the first target partition, the face features are reshaped The database selects a sub-database, and performs matching analysis on the feature data of the first target partition and the sub-database; wherein, the face feature data in the sub-database matches the feature data of the partitions other than the first target partition.
在一个实施例中,如图5所示,整形模拟系统还包括图像修改单元240,用于接收修改指令,根据修改指令对整形模拟图像进行特征数据微调;或者,根据修改指令重新在各分区中选取第一目标分区。In one embodiment, as shown in FIG. 5, the shaping simulation system further includes an image modification unit 240 for receiving a modification instruction, and fine-tuning the characteristic data of the shaping simulation image according to the modification instruction; or, according to the modification instruction, in each partition Select the first target partition.
在一个实施例中,如图6所示,整形模拟系统还包括图像组合单元250,用于接收针对第二目标分区的触发指令,根据触发指令在整形人脸特征数据库中选取多个备选的分区图像,其中,各分区图像的分区类型与第二目标分区的分区类型相同;In one embodiment, as shown in FIG. 6, the shaping simulation system further includes an image combining unit 250 for receiving a trigger instruction for the second target partition, and selecting a plurality of candidate candidates in the shaping facial feature database according to the trigger instruction Partition images, where the partition type of each partition image is the same as the partition type of the second target partition;
图像组合单元250还用于显示各分区图像,接收第二选取指令,根据第二选取指令在各分区图像中选取目标分区图像;The image combining unit 250 is further used to display each partition image, receive a second selection instruction, and select a target partition image from each partition image according to the second selection instruction;
图像组合单元250还用于将目标分区图像融合到原始图像中对应第二目标分区的位置。The image combining unit 250 is also used to fuse the target partition image to the position of the original image corresponding to the second target partition.
在一个实施例中,图像组合单元250获取第二目标分区的图像大小、位置和颜色数据,根据图像大小、位置和颜色数据对目标分区图像进行调整,将原始图像中对应第二目标分区的部位替换成调整后的图像,并对调整后的图像与原始图像的对接边缘进行模糊处理。In one embodiment, the image combining unit 250 acquires the image size, position and color data of the second target partition, adjusts the target partition image according to the image size, position and color data, and compares the part of the original image corresponding to the second target partition Replace with the adjusted image, and blur the edge of the interface between the adjusted image and the original image.
在一个实施例中,如图7所示,整形模拟系统还包括数据交互单元270,用于将整形模拟图像经服务器发送至整形服务端,接收整形服务端返回的修改意见数据,并反馈对修改意见数据的处理信息。In one embodiment, as shown in FIG. 7, the shaping simulation system further includes a data interaction unit 270 for sending the shaping simulation image to the shaping server via the server, receiving the modification opinion data returned by the shaping server, and feeding back the modification Processing information of opinion data.
本发明的整形模拟系统与本发明的整形模拟方法相对应,在上述整形模拟方法的实施例中阐述的技术特征及其有益效果均适用于整形模拟系统的实施例中。The shaping simulation system of the present invention corresponds to the shaping simulation method of the present invention, and the technical features and beneficial effects described in the above embodiments of the shaping simulation method are applicable to the embodiments of the shaping simulation system.
一种可读存储介质,其上存储有可执行程序,可执行程序被处理器执行时实现上述的整形模拟方法的步骤。A readable storage medium has stored thereon an executable program, and when the executable program is executed by a processor, the steps of the above-mentioned shaping simulation method are realized.
上述可读存储介质,通过其存储的可执行程序,可以实现通过人脸特征数据与整形人 脸特征数据库的数据的匹配得到人脸特征调整值,对原始图像的模拟调节更加符合整形的需要,可以得到相对接近真实且更直观的整形模拟效果,提高整形模拟图像的术前参考作用。The above-mentioned readable storage medium, through the executable program stored in it, can achieve the adjustment value of the facial features by matching the facial feature data with the data of the plastic facial feature database, and the analog adjustment of the original image is more in line with the needs of plastic surgery. A relatively close to real and more intuitive plastic simulation effect can be obtained, and the preoperative reference function of the plastic simulation image can be improved.
一种整形模拟设备,包括存储器和处理器,存储器存储有可执行程序,处理器执行可执行程序时实现上述的整形模拟方法的步骤。A shaping simulation device includes a memory and a processor. The memory stores an executable program. When the processor executes the executable program, the steps of the shaping simulation method described above are implemented.
上述整形模拟设备,通过在处理器上运行可执行程序,可以实现通过人脸特征数据与整形人脸特征数据库的数据的匹配得到人脸特征调整值,对原始图像的模拟调节更加符合整形的需要,可以得到相对接近真实且更直观的整形模拟效果,提高整形模拟图像的术前参考作用。The above-mentioned shaping simulation device can achieve the adjustment value of the face feature by matching the face feature data with the data of the shaping face feature database by running the executable program on the processor, and the simulation adjustment of the original image is more in line with the needs of shaping , You can get relatively close to the real and more intuitive plastic simulation effect, improve the pre-operative reference role of plastic simulation images.
上述整形模拟设备,通过在处理器上运行可执行程序,通过人脸特征数据与整形人脸特征数据库的数据的匹配得到人脸特征调整值,对原始图像的模拟调节更加符合整形的需要,可以得到相对接近真实且更直观的整形模拟效果,提高整形模拟图像的术前参考作用。The above-mentioned shaping simulation device, by running an executable program on the processor, obtains the face feature adjustment value by matching the face feature data with the data of the shaping face feature database, and the simulation adjustment of the original image is more in line with the needs of shaping. Obtain a relatively close to real and more intuitive plastic simulation effect, and improve the preoperative reference function of plastic simulation images.
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程,是可以通过计算机程序来指令相关的硬件来完成,程序可存储于一非易失性的计算机可读取存储介质中,如实施例中,该程序可存储于计算机系统的存储介质中,并被该计算机系统中的至少一个处理器执行,以实现包括如上述整形模拟方法的实施例的流程。其中,存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)或随机存储记忆体(Random Access Memory,RAM)等。A person of ordinary skill in the art may understand that all or part of the processes in the method of the foregoing embodiments may be completed by instructing relevant hardware through a computer program, and the program may be stored in a non-volatile computer-readable storage medium. As in the embodiment, the program may be stored in a storage medium of the computer system and executed by at least one processor in the computer system to implement the process including the embodiment of the above-described shaping simulation method. Among them, the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM) or a random access memory (Random Access Memory, RAM), etc.
在一个实施例中,整形模拟设备还包括整形服务端设备。In one embodiment, the shaping simulation device further includes a shaping server device.
在一个实施例中,整形模拟方法可以应用在移动设备中,移动设备可以是个人计算机、笔记本电脑、掌上电脑、智能手机、平板电脑、便携式可穿戴设备等。In one embodiment, the shaping simulation method can be applied to a mobile device, which can be a personal computer, a notebook computer, a palmtop computer, a smartphone, a tablet computer, a portable wearable device, and the like.
整形模拟方法的流程简图如图8所示。具体的,用户可以通过手机、平板电脑、摄像头等电子设备扫描或拍摄面部,上传三张不同面的人脸图像(正面,侧面(45度)两张),建立3D原始图像模型。然后对用户的原始图像模型进行人脸识别,将脸部各部位进行分区,分割成额头、眼部(单眼,包括眼睛、眉毛)、鼻部(鼻头、鼻翼)、颏部、面部(两面颊)等分区(部位分区是通过用户手动设置点位来进行选取),通脸型数据计算算法,分析出使用人的脸部特征,及预先设定的标准值进行对比,得出脸部分析报告,用户可以根据分析报告中的建议进行自动整形模拟,完成后得出整形建议报告,用户可保存通过模拟形成的图像及报告,作为一定的整形参考。同时用户也可以对单个脸部部位进行分析和更换成整形人脸数据库里的各类部位图像,从而得到整形模拟图像,可以在分析后得到调整数据对用户的人脸图像进行调整,得到整形模拟图像,也可以更换部位图像,用户可以自主选择部位,从整形人脸数据库里选取相同类型的部位图像供用户选择,在用户确定需要的部位图像后,将选定的部位图像融合到用户的脸部图像中,将对接位置进行模拟处理,得到另一种整形模拟图像,如对整形模拟的效果不满意,用户可以用微调功能来进行对单个部位的图像处理,或者重新 选择部位进行整形模拟,最后经过重新计算并混合系统设计的标准值对原始图像进行相应的整形模拟处理,得到最终的整形模拟图像,用户可以将此模拟效果图像通过在线咨询服务模块(即数据交互模块)发给在线整形医生进行点对点的咨询,在线整形医生可以在此模拟图像的基础上再进行微调或是重新对每个部位进行匹配,从而得到最佳整形模拟图像;让整形医生在线提供整形建议,并可修改客户的模拟数据,从而得到两方都觉得好的整形模拟图像,然后用户可以保存模拟图像,还可以进行3D模拟图像打印,图像会保存在医生的整形服务端的数据库里,待下次用户线下找医生面诊时,医生可以调出数据作为面诊依据,减少双方沟通的时间;也可以通过分享功能,通过微信、QQ等即时通讯软件分享给朋友,相对于传统整形模拟技术,只能通过简单的进行模糊图像处理,不能融合医美容专业技术,减少了用户的操作时间,提高了整形模拟的效率和专业性,特别是应用在医疗美容术后客户面诊环节,可以更直观的让用户提前得到术后的效果模拟图像。The flow chart of the shaping simulation method is shown in Figure 8. Specifically, the user can scan or photograph the face through electronic devices such as mobile phones, tablets, cameras, and upload three face images (front and side (45 degrees) two) to establish a 3D original image model. Then perform face recognition on the user's original image model, partition each part of the face into forehead, eye (single eye, including eyes, eyebrows), nose (nose, nose wings), chin, face (both cheeks) ) And other partitions (parts are selected by the user manually setting points), through the face data calculation algorithm, the user's facial features are analyzed, and the preset standard values are compared to obtain a facial analysis report, The user can perform automatic shaping simulation according to the suggestions in the analysis report, and the shaping recommendation report is obtained after completion. The user can save the image and report formed by the simulation as a certain shaping reference. At the same time, users can also analyze individual face parts and replace them with images of various parts in the plastic face database to obtain plastic simulation images. After the analysis, adjustment data can be obtained to adjust the user's face images to obtain plastic simulation. The image can also be replaced with a part image. The user can select a part independently and select the same type of part image from the plastic face database for the user to choose. After the user determines the required part image, the selected part image is fused to the user's face In the part of the image, the docking position is simulated to obtain another shape simulation image. If the effect of the shape simulation is not satisfactory, the user can use the fine-tuning function to process the image of a single part, or reselect the part to perform the shape simulation. Finally, after recalculating and mixing the standard values of the system design, the original image is subjected to corresponding shaping simulation processing to obtain the final shaped simulation image. The user can send this simulation effect image to the online shaping through the online consulting service module (ie, data interaction module) Doctors conduct point-to-point consultations. Online plastic surgeons can fine-tune or rematch each part based on this simulated image to obtain the best plastic simulation image; let the plastic surgeon provide plastic suggestions online and modify customers Simulation data of both sides, so that you can get a plastic simulation image that both parties think is good. Then the user can save the simulation image and print the 3D simulation image. The image will be saved in the database of the doctor’s plastic surgery server. During the doctor's face consultation, the doctor can call up the data as a basis for the face consultation to reduce the communication time between the two parties; it can also be shared with friends through instant messaging software such as WeChat and QQ through the sharing function. Compared with the traditional plastic simulation technology, it can only be achieved through simple Blurred image processing cannot be integrated with medical and cosmetic professional technology, which reduces the user's operation time and improves the efficiency and professionalism of plastic simulation, especially when applied to the customer's face-to-face consultation after medical cosmetic surgery, which can make the user more intuitive in advance Obtain post-operative effect simulation images.
以上所述实施例的各技术特征可以进行任意的组合,为使描述简洁,未对上述实施例中的各个技术特征所有可能的组合都进行描述,然而,只要这些技术特征的组合不存在矛盾,都应当认为是本说明书记载的范围。The technical features of the above-mentioned embodiments can be arbitrarily combined. To simplify the description, all possible combinations of the technical features in the above-mentioned embodiments are not described. However, as long as there is no contradiction in the combination of these technical features, All should be considered within the scope of this description.
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成。所述的程序可以存储于一计算机可读取存储介质中。该程序在执行时,包括上述方法所述的步骤。所述的存储介质,包括:ROM/RAM、磁碟、光盘等。A person of ordinary skill in the art may understand that all or part of the steps in the method of the foregoing embodiments may be implemented by a program instructing relevant hardware. The program can be stored in a computer-readable storage medium. When this program is executed, it includes the steps described in the above method. The storage medium includes: ROM/RAM, magnetic disk, optical disk, etc.
以上所述实施例仅表达了本发明的几种实施方式,其描述较为具体和详细,但并不能因此而理解为对发明专利范围的限制。应当指出的是,对于本领域的普通技术人员来说,在不脱离本发明构思的前提下,还可以做出若干变形和改进,这些都属于本发明的保护范围。因此,本发明专利的保护范围应以所附权利要求为准。The above examples only express several implementations of the present invention, and their descriptions are more specific and detailed, but they should not be construed as limiting the patent scope of the invention. It should be noted that, for a person of ordinary skill in the art, without departing from the concept of the present invention, a number of modifications and improvements can also be made, which all fall within the protection scope of the present invention. Therefore, the protection scope of the invention patent shall be subject to the appended claims.
Claims (12)
- 一种整形模拟方法,其特征在于,包括以下步骤:A shaping simulation method is characterized by the following steps:获取待整形对象的原始图像,对所述原始图像进行人脸识别,获取所述待整形对象的人脸特征数据;Acquiring the original image of the object to be shaped, performing face recognition on the original image, and acquiring the facial feature data of the object to be shaped;对所述人脸特征数据与预设的整形人脸特征数据库进行匹配分析,获取人脸特征调整值;Perform matching analysis on the face feature data and a preset plastic face feature database to obtain face feature adjustment values;根据所述人脸特征调整值对所述原始图像进行模拟调节,获得整形模拟图像。The original image is simulated and adjusted according to the face feature adjustment value to obtain a plastic analog image.
- 根据权利要求1所述的整形模拟方法,其特征在于,所述获取待整形对象的原始图像,对所述原始图像进行人脸识别的步骤包括以下步骤:The shaping simulation method according to claim 1, wherein the step of acquiring the original image of the object to be shaped and performing face recognition on the original image includes the following steps:获取待整形对象的正面图像和多张侧面图像,对所述正面图像和所述多张侧面图像进行人脸识别。Obtain a front image and multiple side images of the object to be shaped, and perform face recognition on the front image and the multiple side images.
- 根据权利要求1所述的整形模拟方法,其特征在于,所述获取所述待整形对象的人脸特征数据的步骤包括以下步骤:The shaping simulation method according to claim 1, wherein the step of acquiring face feature data of the object to be shaped includes the following steps:获取所述待整形对象的脸部区域特征点,根据所述脸部区域特征点对脸部进行分区,获取各分区的特征数据以及脸部的轮廓数据;其中,各所述分区包括眼部、鼻部、嘴部、面部和颏部,所述特征数据包括当前分区的位置数据以及当前分区和其他分区之间的相对位置数据。Obtain the feature points of the face area of the object to be reshaped, partition the face according to the feature points of the face area, and obtain the feature data of each zone and the contour data of the face; wherein, each of the zones includes the eye, For the nose, mouth, face and chin, the characteristic data includes position data of the current partition and relative position data between the current partition and other partitions.
- 根据权利要求1所述的整形模拟方法,其特征在于,所述对所述人脸特征数据与预设的整形人脸特征数据库进行匹配分析的步骤包括以下步骤:The shaping simulation method according to claim 1, wherein the step of matching and analyzing the face feature data with a preset shaping face feature database includes the following steps:根据所述人脸特征数据在所述整形人脸特征数据库中搜索匹配数据,其中,所述匹配数据与所述人脸特征数据的相似度大于或等于预设值;Searching matching data in the plastic face feature database according to the face feature data, wherein the similarity between the match data and the face feature data is greater than or equal to a preset value;所述获取人脸特征调整值的步骤还包括以下步骤:The step of obtaining the adjustment value of the facial features further includes the following steps:获取所述人脸特征数据与所述匹配数据的比值,根据所述比值获取所述人脸特征调整值,其中,所述人脸特征调整值在所述比值和数值1之间。Obtain a ratio of the face feature data to the matching data, and obtain the face feature adjustment value according to the ratio, where the face feature adjustment value is between the ratio and the value 1.
- 根据权利要求3所述的整形模拟方法,其特征在于,所述对所述人脸特征数据与预设的整形人脸特征数据库进行匹配分析的步骤包括以下步骤:The shaping simulation method according to claim 3, wherein the step of matching and analyzing the face feature data with a preset shaping face feature database includes the following steps:接收第一选取指令,根据所述第一选取指令在各分区中选取第一目标分区;Receiving a first selection instruction, and selecting a first target partition among the partitions according to the first selection instruction;根据除所述第一目标分区以外的其他分区的特征数据,在所述整形人脸特征数据库选取子数据库,其中,所述子数据库中的人脸特征数据与所述第一目标分区以外的其他分区的特征数据相匹配;According to the feature data of other partitions than the first target partition, select a sub-database in the plastic face feature database, wherein the face feature data in the sub-database and other than the first target partition Match the feature data of the partition;对所述第一目标分区的特征数据与所述子数据库进行匹配分析。Perform matching analysis on the feature data of the first target partition and the sub-database.
- 根据权利要求5所述的整形模拟方法,其特征在于,还包括以下步骤:The shaping simulation method according to claim 5, further comprising the following steps:接收修改指令,根据所述修改指令对所述整形模拟图像进行特征数据微调;Receiving a modification instruction, and fine-tuning feature data of the plastic analog image according to the modification instruction;或者,根据所述修改指令重新在各分区中选取第一目标分区。Or, select the first target partition among the partitions again according to the modification instruction.
- 根据权利要求3所述的整形模拟方法,其特征在于,还包括以下步骤:The shaping simulation method according to claim 3, further comprising the following steps:接收针对第二目标分区的触发指令,根据所述触发指令在所述整形人脸特征数据库中选取多个备选的分区图像,其中,各所述分区图像的分区类型与所述第二目标分区的分区类型相同;Receiving a trigger instruction for a second target partition, and selecting a plurality of candidate partition images in the plastic face feature database according to the trigger instruction, wherein the partition type of each partition image and the second target partition The partition type is the same;显示各所述分区图像,接收第二选取指令,根据所述第二选取指令在各所述分区图像中选取目标分区图像;Displaying each of the partition images, receiving a second selection instruction, and selecting a target partition image from each of the partition images according to the second selection instruction;将所述目标分区图像融合到所述原始图像中对应所述第二目标分区的位置。Fuse the target partition image to a position corresponding to the second target partition in the original image.
- 根据权利要求7所述的整形模拟方法,其特征在于,所述将所述目标分区图像融合到所述原始图像中对应所述第二目标分区的位置的步骤包括以下步骤:The shaping simulation method according to claim 7, wherein the step of fusing the target partition image to the position corresponding to the second target partition in the original image includes the following steps:获取所述第二目标分区的图像大小、位置和颜色数据,根据所述图像大小、位置和颜色数据对所述目标分区图像进行调整,将所述原始图像中对应所述第二目标分区的部位替换成所述调整后的图像,并对所述调整后的图像与所述原始图像的对接边缘进行模糊处理。Obtain the image size, position and color data of the second target partition, adjust the target partition image according to the image size, position and color data, and place the original image corresponding to the second target partition Replace with the adjusted image, and blur the edge of the interface between the adjusted image and the original image.
- 根据权利要求1至8中任意一项所述的整形模拟方法,其特征在于,还包括以下步骤:The shaping simulation method according to any one of claims 1 to 8, further comprising the following steps:将处理得到的图像经服务器发送至整形服务端,接收所述整形服务端返回的修改意见数据,并反馈对所述修改意见数据的处理信息。Send the processed image to the shaping server via the server, receive the modification opinion data returned by the shaping server, and feed back processing information on the modification opinion data.
- 一种整形模拟系统,其特征在于,包括:A shaping simulation system, which is characterized by including:图像识别单元,用于获取待整形对象的原始图像,对所述原始图像进行人脸识别,获取所述待整形对象的人脸特征数据;An image recognition unit, configured to obtain an original image of the object to be shaped, perform face recognition on the original image, and obtain facial feature data of the object to be shaped;图像分析单元,用于对所述人脸特征数据与预设的整形人脸特征数据库进行匹配分析,获取人脸特征调整值;An image analysis unit, configured to perform matching analysis on the face feature data and a preset plastic face feature database to obtain face feature adjustment values;图像调节单元,根据所述人脸特征调整值对所述原始图像进行模拟调节,获得整形模拟图像。The image adjustment unit performs analog adjustment on the original image according to the face feature adjustment value to obtain a plastic analog image.
- 一种可读存储介质,其上存储有可执行程序,其特征在于,所述可执行程序被处理器执行时实现权利要求1至7中任一项所述的整形模拟方法的步骤。A readable storage medium on which an executable program is stored, characterized in that when the executable program is executed by a processor, the steps of the shaping simulation method according to any one of claims 1 to 7 are realized.
- 一种整形模拟设备,包括存储器和处理器,所述存储器存储有可执行程序,其特征在于,所述处理器执行所述可执行程序时实现权利要求1至7中任一项所述的整形模拟方法的步骤。A shaping simulation device includes a memory and a processor, and the memory stores an executable program, wherein the processor implements the shaping according to any one of claims 1 to 7 when the processor executes the executable program The steps of the simulation method.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811581506.0 | 2018-12-24 | ||
CN201811581506.0A CN111353931B (en) | 2018-12-24 | 2018-12-24 | Shaping simulation method, system, readable storage medium and apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020135286A1 true WO2020135286A1 (en) | 2020-07-02 |
Family
ID=71126289
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2019/127251 WO2020135286A1 (en) | 2018-12-24 | 2019-12-22 | Shaping simulation method and system, readable storage medium and device |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111353931B (en) |
WO (1) | WO2020135286A1 (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114494601B (en) * | 2022-02-09 | 2024-03-08 | 南京医科大学附属口腔医院 | Three-dimensional face retrieval orthodontic correction and curative effect simulation system based on face image |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8265351B2 (en) * | 2006-05-05 | 2012-09-11 | Parham Aarabi | Method, system and computer program product for automatic and semi-automatic modification of digital images of faces |
CN107122727A (en) * | 2017-04-20 | 2017-09-01 | 北京旷视科技有限公司 | Method, apparatus and system for face's shaping |
CN107123160A (en) * | 2017-05-02 | 2017-09-01 | 成都通甲优博科技有限责任公司 | Simulation lift face system, method and mobile terminal based on three-dimensional image |
CN108447017A (en) * | 2018-05-31 | 2018-08-24 | Oppo广东移动通信有限公司 | Face virtual face-lifting method and device |
CN108765273A (en) * | 2018-05-31 | 2018-11-06 | Oppo广东移动通信有限公司 | The virtual lift face method and apparatus that face is taken pictures |
CN109189967A (en) * | 2018-08-24 | 2019-01-11 | 微云(武汉)科技有限公司 | A kind of lift face proposal recommending method, device and storage medium based on recognition of face |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
FR2728982A1 (en) * | 1994-12-29 | 1996-07-05 | Jean Marc Robin | AUTOMATIC RECOGNITION OF FACE CHARACTERISTICS AND SIMULATION OF AN AESTHETIC IMAGE OF A REAL OBJECTIVE (FACE) |
CN106652015B (en) * | 2015-10-30 | 2020-10-30 | 深圳超多维光电子有限公司 | Virtual character head portrait generation method and device |
CN105938627B (en) * | 2016-04-12 | 2020-03-31 | 湖南拓视觉信息技术有限公司 | Processing method and system for virtual shaping of human face |
-
2018
- 2018-12-24 CN CN201811581506.0A patent/CN111353931B/en active Active
-
2019
- 2019-12-22 WO PCT/CN2019/127251 patent/WO2020135286A1/en active Application Filing
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8265351B2 (en) * | 2006-05-05 | 2012-09-11 | Parham Aarabi | Method, system and computer program product for automatic and semi-automatic modification of digital images of faces |
CN107122727A (en) * | 2017-04-20 | 2017-09-01 | 北京旷视科技有限公司 | Method, apparatus and system for face's shaping |
CN107123160A (en) * | 2017-05-02 | 2017-09-01 | 成都通甲优博科技有限责任公司 | Simulation lift face system, method and mobile terminal based on three-dimensional image |
CN108447017A (en) * | 2018-05-31 | 2018-08-24 | Oppo广东移动通信有限公司 | Face virtual face-lifting method and device |
CN108765273A (en) * | 2018-05-31 | 2018-11-06 | Oppo广东移动通信有限公司 | The virtual lift face method and apparatus that face is taken pictures |
CN109189967A (en) * | 2018-08-24 | 2019-01-11 | 微云(武汉)科技有限公司 | A kind of lift face proposal recommending method, device and storage medium based on recognition of face |
Also Published As
Publication number | Publication date |
---|---|
CN111353931A (en) | 2020-06-30 |
CN111353931B (en) | 2023-10-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10979624B2 (en) | Methods and devices for establishing photographing template database and providing photographing recommendation information | |
US9367756B2 (en) | Selection of representative images | |
CN109310196B (en) | Makeup assisting device and makeup assisting method | |
WO2020228384A1 (en) | Virtual head portrait generation method and device, and storage medium | |
WO2020019904A1 (en) | Image processing method and apparatus, and computer device and storage medium | |
US20120007859A1 (en) | Method and apparatus for generating face animation in computer system | |
JP2009064423A (en) | Makeup simulation system, makeup simulation device, makeup simulation method, and makeup simulation program | |
US11461384B2 (en) | Facial images retrieval system | |
CN110866139A (en) | Cosmetic treatment method, device and equipment | |
WO2023010796A1 (en) | Image processing method and related apparatus | |
WO2020135286A1 (en) | Shaping simulation method and system, readable storage medium and device | |
KR102594093B1 (en) | Dermatologic treatment recommendation system using deep learning model and method thereof | |
Barroso et al. | Periocular recognition: how much facial expressions affect performance? | |
CN112995520B (en) | Method and system for quickly shooting certificate photo and readable storage medium | |
WO2020135287A1 (en) | Plastic surgery simulation information processing method, plastic surgery simulation terminal and plastic surgery service terminal | |
KR102330833B1 (en) | cosmetic curation service method | |
KR101507410B1 (en) | Live make-up photograpy method and apparatus of mobile terminal | |
JP2014149841A (en) | Make-up counseling method | |
CN114333018A (en) | Shaping information recommendation method and device and electronic equipment | |
KR101382172B1 (en) | System for classifying hierarchical facial feature and method therefor | |
CN111370100A (en) | Face-lifting recommendation method and system based on cloud server | |
CN111444979A (en) | Face-lifting scheme recommendation method, cloud device and storage medium | |
CN113902790B (en) | Beauty guidance method, device, electronic equipment and computer readable storage medium | |
TW202122040A (en) | Method for analyzing and estimating face muscle status | |
CN113076779A (en) | Shaping simulation matching method, shaping simulation matching system, readable storage medium and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19904968 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19904968 Country of ref document: EP Kind code of ref document: A1 |