CN104474709A - Game method based on three-dimensional face recognition - Google Patents
Game method based on three-dimensional face recognition Download PDFInfo
- Publication number
- CN104474709A CN104474709A CN201410677869.XA CN201410677869A CN104474709A CN 104474709 A CN104474709 A CN 104474709A CN 201410677869 A CN201410677869 A CN 201410677869A CN 104474709 A CN104474709 A CN 104474709A
- Authority
- CN
- China
- Prior art keywords
- dimensional face
- dimensional
- face images
- carry out
- gaming
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 230000004927 fusion Effects 0.000 claims abstract description 6
- 230000000295 complement effect Effects 0.000 claims abstract description 4
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 abstract 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000003796 beauty Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
Landscapes
- Collating Specific Patterns (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention discloses a game method based on three-dimensional face recognition. The game method based on the three-dimensional face recognition comprises the following steps: S01, obtaining a three-dimensional face image through a three-dimensional scanner; S02, pre-processing the three-dimensional face image, comprising the face cutting and posture correcting, and storing in a database; S03, performing the feature extraction to the pre-processed three-dimensional face image, wherein the depth data and the rigid area are respectively selected as the complementary feature; S04, in the game, using the three-dimensional scanner to take a picture by a player, turning to the step S05 after respectively pre-processing and performing the feature extraction to the obtained three-dimensional face image; S05, performing the feature matching, comprising the depth data matching and the rigid area matching; S06, performing the feature fusion to obtain the to-be-graded three-dimensional face image; and S07, comparing the to-be-graded three-dimensional face image with the image in the step S02, obtaining the comprehensive average similarity and displaying through the characters or voice. The game method is capable of giving the more specific answer to consult by the user.
Description
Technical field
The present invention relates to a kind of method for gaming based on three-dimensional face identification.
Background technology
Whether everybody has a love of beauty, especially women, takes notice of very much oneself appearance and dressing, can the dressing of looking over oneself frequently be satisfied with.General, they can pass through mobile phone photograph, or use mirror to check, Given this, the present inventor provides a kind of method for gaming, marks, provide answer more specifically, for user's reference with the dressing of light mode to people of playing.
Wherein, under being identified in certain constraints based on the two-dimension human face of characteristics of image, more satisfactory recognition effect can be obtained, but process multi-pose, many illumination and multiple expression sample time, its recognition performance can sharply decline.And the recognition of face based on three-dimensional feature grown up has good robustness to illumination and attitude thereupon.
Summary of the invention
For the problems referred to above, the invention provides a kind of method for gaming based on three-dimensional face identification, mark with the dressing of light mode to people of playing, provide answer more specifically, for user's reference.
For realizing above-mentioned technical purpose, reach above-mentioned technique effect, the present invention is achieved through the following technical solutions:
Based on a method for gaming for three-dimensional face identification, it is characterized in that, comprise the steps:
S01: obtain three-dimensional face images by spatial digitizer;
S02: carry out pretreatment to three-dimensional face images, comprises face cutting and attitude updating, and stored in database;
S03: carry out feature extraction to pretreated three-dimensional face images, wherein, chooses depth data and rigid region respectively as complementary characteristic;
S04: when player plays, first uses spatial digitizer to take pictures, enters step S05 after carrying out pretreatment and feature extraction in turn respectively to the three-dimensional face images obtained;
S05: carry out characteristic matching, comprises depth data coupling and rigid region coupling;
S06: carry out Fusion Features and obtain three-dimensional face images to be marked;
S07: compared by the image in three-dimensional face images to be marked and step S02, is drawn comprehensive average similarity and is shown by word or voice.
Preferably, described spatial digitizer is three-dimensional laser scanner, also can be handheld three-dimensional scanner.
Preferably, in step S02, according to face geometrical constraint, determine that the point at face face with greatest z value is prenasale.
In said method, during owing to playing at every turn, the expression of player has difference, so can be reduced the impact of expressing one's feelings and causing three-dimensional face images identification by pretreatment and feature extraction, improves the accuracy identified.In addition, significantly improve discrimination, finally compare and provide the similarity with sample by fusion depth characteristic and facial rigid region, more specifically, wherein, the formation of sample can be selected voluntarily according to the hobby of player in scoring.
The invention has the beneficial effects as follows: mark with the dressing of light mode to people of playing, provide answer more specifically, for user's reference.
Detailed description of the invention
Below in conjunction with specific embodiment, technical solution of the present invention is described in further detail, can better understand the present invention to make those skilled in the art and can be implemented, but illustrated embodiment is not as a limitation of the invention.
Based on a method for gaming for three-dimensional face identification, comprise the steps:
S01: obtain three-dimensional face images by spatial digitizer, wherein, spatial digitizer (3D scanner) is a kind of scientific instrument, be used for detecting and analyze the shape (geometrical construction) of object or environment in real world and appearance data (as the character such as color, surface albedo), three-dimensional laser scanner (three-dimensional laser scanning technique be otherwise known as outdoor scene reproduction technology) can be used to improve accuracy, handheld three-dimensional scanner also can be used to increase flexibility.
S02: the three-dimensional face images using spatial digitizer to obtain, usually also comprises the image such as hair, neck, therefore need to carry out pretreatment to three-dimensional face images, comprises face cutting and attitude updating, and stored in database as sample.
Wherein, sample according to the hobby setting of oneself, also can store multiple three-dimensional face images, and in follow-up scoring process, a selected image is as sample voluntarily.
S03: carry out feature extraction to pretreated three-dimensional face images, wherein, chooses depth data and rigid region respectively as complementary characteristic;
S04: when player plays, first uses spatial digitizer to take pictures, enters step S05 after carrying out pretreatment and feature extraction in turn respectively to the three-dimensional face images obtained;
S05: carry out characteristic matching, comprises depth data coupling and rigid region coupling;
S06: carry out Fusion Features and obtain three-dimensional face images to be marked;
S07: compared by the image in three-dimensional face images to be marked and step S02, is drawn comprehensive average similarity and is shown by word or voice.
Preferably, in step S02, according to face geometrical constraint, determine that the point at face face with greatest z value is prenasale.Preferably, centered by prenasale, R is that radius carries out face cutting.Wherein, R can value for being 90mm, 93 mm, 95 mm or 97mm.
In said method, during owing to playing at every turn, the expression of player has difference, so can be reduced the impact of expressing one's feelings and causing three-dimensional face images identification by pretreatment and feature extraction, improves the accuracy identified.In addition, significantly improve discrimination, finally compare and provide the similarity with sample by fusion depth characteristic and facial rigid region, scoring more specifically.
These are only the preferred embodiments of the present invention; not thereby the scope of the claims of the present invention is limited; every utilize description of the present invention to do equivalent structure or equivalent flow process conversion; or be directly or indirectly used in the technical field that other are relevant, be all in like manner included in scope of patent protection of the present invention.
Claims (6)
1. based on a method for gaming for three-dimensional face identification, it is characterized in that, comprise the steps:
S01: obtain three-dimensional face images by spatial digitizer;
S02: carry out pretreatment to three-dimensional face images, comprises face cutting and attitude updating, and stored in database;
S03: carry out feature extraction to pretreated three-dimensional face images, wherein, chooses depth data and rigid region respectively as complementary characteristic;
S04: when player plays, first uses spatial digitizer to take pictures, enters step S05 after carrying out pretreatment and feature extraction in turn respectively to the three-dimensional face images obtained;
S05: carry out characteristic matching, comprises depth data coupling and rigid region coupling;
S06: carry out Fusion Features and obtain three-dimensional face images to be marked;
S07: compared by the image in three-dimensional face images to be marked and step S02, is drawn comprehensive average similarity and is shown by word or voice.
2. a kind of method for gaming based on three-dimensional face identification according to claim 1, it is characterized in that, described spatial digitizer is three-dimensional laser scanner.
3. a kind of method for gaming based on three-dimensional face identification according to claim 1, is characterized in that, described spatial digitizer is handheld three-dimensional scanner.
4. a kind of method for gaming based on three-dimensional face identification according to claim 1, is characterized in that, in step S02, according to face geometrical constraint, determines that the point at face face with greatest z value is prenasale.
5. a kind of method for gaming based on three-dimensional face identification according to claim 4, is characterized in that, centered by prenasale, R is that radius carries out face cutting.
6. a kind of method for gaming based on three-dimensional face identification according to claim 5, is characterized in that, described R is one in 90mm, 93 mm, 95 mm, 97mm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410677869.XA CN104474709A (en) | 2014-11-24 | 2014-11-24 | Game method based on three-dimensional face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410677869.XA CN104474709A (en) | 2014-11-24 | 2014-11-24 | Game method based on three-dimensional face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104474709A true CN104474709A (en) | 2015-04-01 |
Family
ID=52749395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410677869.XA Pending CN104474709A (en) | 2014-11-24 | 2014-11-24 | Game method based on three-dimensional face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104474709A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018209569A1 (en) * | 2017-05-16 | 2018-11-22 | 深圳市三维人工智能科技有限公司 | 3d scanning model cutting device and method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101315661A (en) * | 2008-07-18 | 2008-12-03 | 东南大学 | A Fast 3D Face Recognition Method with Reduced Effect of Expression |
| CN101398886A (en) * | 2008-03-17 | 2009-04-01 | 杭州大清智能技术开发有限公司 | Rapid three-dimensional face identification method based on bi-eye passiveness stereo vision |
| CN101986328A (en) * | 2010-12-06 | 2011-03-16 | 东南大学 | Local descriptor-based three-dimensional face recognition method |
| CN102592136A (en) * | 2011-12-21 | 2012-07-18 | 东南大学 | Three-dimensional human face recognition method based on intermediate frequency information in geometry image |
| CN104112115A (en) * | 2014-05-14 | 2014-10-22 | 南京国安光电科技有限公司 | Three-dimensional face detection and identification technology |
-
2014
- 2014-11-24 CN CN201410677869.XA patent/CN104474709A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398886A (en) * | 2008-03-17 | 2009-04-01 | 杭州大清智能技术开发有限公司 | Rapid three-dimensional face identification method based on bi-eye passiveness stereo vision |
| CN101315661A (en) * | 2008-07-18 | 2008-12-03 | 东南大学 | A Fast 3D Face Recognition Method with Reduced Effect of Expression |
| CN101986328A (en) * | 2010-12-06 | 2011-03-16 | 东南大学 | Local descriptor-based three-dimensional face recognition method |
| CN102592136A (en) * | 2011-12-21 | 2012-07-18 | 东南大学 | Three-dimensional human face recognition method based on intermediate frequency information in geometry image |
| CN104112115A (en) * | 2014-05-14 | 2014-10-22 | 南京国安光电科技有限公司 | Three-dimensional face detection and identification technology |
Non-Patent Citations (1)
| Title |
|---|
| 朱冰莲等: "针对表情变化的三维人脸识别系统研究", 《仪器仪表学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018209569A1 (en) * | 2017-05-16 | 2018-11-22 | 深圳市三维人工智能科技有限公司 | 3d scanning model cutting device and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695471B (en) | Avatar generation method, apparatus, device and storage medium | |
| CN106803057B (en) | Image information processing method and device | |
| CN101847268B (en) | Cartoon human face image generation method and device based on human face images | |
| US9552467B2 (en) | Information processing device and information processing method | |
| US20230103125A1 (en) | 3d upper garment tracking | |
| US12198664B2 (en) | Interactive fashion with music AR | |
| CN111243101B (en) | Method, system and device for increasing AR environment immersion degree of user based on artificial intelligence | |
| US9415313B2 (en) | Information processing device and information processing method | |
| US9921052B2 (en) | Information processing device and information processing method | |
| CN114303120A (en) | virtual keyboard | |
| US20140342818A1 (en) | Attributing User Action Based On Biometric Identity | |
| CN110363867A (en) | Virtual dress up system, method, equipment and medium | |
| CN105405157B (en) | Portrait generation device, Portrait generation method | |
| CN108159700B (en) | Method, device, storage medium, processor and terminal for generating verification code | |
| CN111640200B (en) | AR scene special effect generation method and device | |
| US20150125048A1 (en) | Information processing device and information processing method | |
| CN106161939A (en) | A kind of method, photo taking and terminal | |
| CN110210449A (en) | A kind of face identification system and method for virtual reality friend-making | |
| CN106127828A (en) | A processing method, device and mobile terminal for augmented reality | |
| CN108629248A (en) | A kind of method and apparatus for realizing augmented reality | |
| CN110045817A (en) | Using the interactive camera chain of virtual reality technology | |
| CN109509141A (en) | Image processing method, head portrait setting method and device | |
| CN105354869A (en) | Method and system for representing real head features of user on virtual head portrait | |
| CN105224936A (en) | A kind of iris feature information extracting method and device | |
| CN107808372B (en) | Image crossing processing method and device, computing equipment and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150401 |
|
| RJ01 | Rejection of invention patent application after publication |