CN103236075A - Drawing method of SVG (scalable vector graphics) face cartoon - Google Patents

Drawing method of SVG (scalable vector graphics) face cartoon Download PDF

Info

Publication number
CN103236075A
CN103236075A CN 201310172841 CN201310172841A CN103236075A CN 103236075 A CN103236075 A CN 103236075A CN 201310172841 CN201310172841 CN 201310172841 CN 201310172841 A CN201310172841 A CN 201310172841A CN 103236075 A CN103236075 A CN 103236075A
Authority
CN
China
Prior art keywords
face
svg
people
picture
human
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN 201310172841
Other languages
Chinese (zh)
Inventor
彭振云
许奇明
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
WOWMAN INFORMATION SERVICES CO Ltd SUZHOU
Original Assignee
WOWMAN INFORMATION SERVICES CO Ltd SUZHOU
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by WOWMAN INFORMATION SERVICES CO Ltd SUZHOU filed Critical WOWMAN INFORMATION SERVICES CO Ltd SUZHOU
Priority to CN 201310172841 priority Critical patent/CN103236075A/en
Publication of CN103236075A publication Critical patent/CN103236075A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Processing Or Creating Images (AREA)

Abstract

The invention provides a drawing method of an SVG (scalable vector graphics) face cartoon. The method comprises the following steps: preprocessing an input picture and extracting facial features; and drawing SVG vector pictures of five sense organs by taking extracted features as a reference, so as to obtain a cartoon keeping facial features in the picture. All the operations are automatically realized by computer programs, and human intervention is not needed.

Description

A kind of SVG human-face cartoon method for drafting
Technical field
The invention belongs to digital picture, graph processing technique field.
Background technology
Caricature is a kind of art up processing mode of comparison film, is accepted extensively by society, is applicable to the occasion that inconvenience occurs with true man's photo, for example internet head portrait, cartooning's printed matter etc.Present caricature creation mode is completed by hand by the people with drawing technology foundation basically, by the experience accumulation extraction portrait facial characteristics of its long-term creation and with certain drawing style it is embodied in the works of plane.
Pass through the technological accumulation of the image processing field of decades, had mature methods can automatically carry out the face characteristic analysis of photo by software program at present, these tachnical storages provide feasibility for realization of the present invention.
Summary of the invention
The present invention has realized the method for the automatic drawing human-face cartoon of software, and the algorithm by Computer Image Processing carries out the face characteristic analysis to the photo that the user provides, and the method that adopts linear to play up has obtained the vector quantization caricature of SVG form.Concrete implementation step is as described below.
(1) photo initialization: true man's photo that the user is provided adopts the method for level and smooth noise reduction to carry out pre-service, thereby reduces the fluctuation of links such as subsequent treatment algorithm threshold value is chosen, algorithm stability.
(2) the input picture is carried out people's face and detect to judge whether have people's face and face position, people from location in the picture.
(3) by face characteristic detection algorithm location people's face face point, obtain face characteristic information.
(4) adopt the SVG file layout, the face unique point is carried out curve fitting draw and play up color, obtain the caricature result.
Description of drawings
Fig. 1 is process flow diagram of the present invention.
Fig. 2 is example of the invention process, and wherein 1 is input picture, and 2 for people's face detects, and 3 is people's face feature detection, and 4 is drawing result.
Embodiment
This SVG human-face cartoon method for drafting comprises following concrete steps.
Preferably, true man's photo that step (1) provides the user adopts the method for the level and smooth noise reduction of Gauss to carry out pre-service, thereby reduces the fluctuation of links such as subsequent treatment algorithm threshold value is chosen, algorithm stability.
Preferably, step (2) utilizes the people's face detection algorithm based on Haar wavelet character and cascade classifier to detect front face from input picture, cuts out front face image according to the detection position, shown among Fig. 22.
Preferably, step (3) utilizes active shape model (ASM) method to extract the human face characteristic point position for the front face image that obtains in the step (2), shown among Fig. 23.
Preferably, step (4) is carried out 3 rank Bezier curves for the face unique point that obtains in the step (3) and is drawn and play up color and it is handled and preserve with the SVG file layout, thereby obtains the caricature result, shown among Fig. 24.
The above; it only is preferred embodiment of the present invention; be not that the present invention is done any pro forma restriction, any simple modification, equivalent variations and modification that every foundation technical spirit of the present invention is done above embodiment all still belong to the protection domain of technical solution of the present invention.

Claims (4)

1. a SVG human-face cartoon method for drafting is characterized in that automatically the photo of input being changed by program, obtains people's face picture of caricature style.
2. a kind of SVG human-face cartoon method for drafting according to claim 1 is characterized in that adopting the method for Digital Image Processing, the input photo is carried out graphical analysis obtain face characteristic information, and step is as follows:
(1) use level and smooth noise-reduction method that the input photo is carried out pretreatment operation, to guarantee the signal to noise ratio (S/N ratio) of subsequent algorithm input signal;
(2) the input picture is carried out the Haar wavelet analysis, carry out people's face and detect to judge whether have people's face and face position, people from location in the picture;
(3) by ASM algorithm location people's face face point, obtain face characteristic information.
3. a kind of SVG human-face cartoon method for drafting according to claim 1 is characterized in that each face feature is carried out linear to be played up, and sketches the contours of the caricature sketch and draws color.
4. a kind of SVG human-face cartoon method for drafting according to claim 1 is characterized in that the caricature style people face picture of its output is the polar plot of SVG form, is convenient to the combination of later stage head and other key elements during integral manufacturing.
CN 201310172841 2013-05-13 2013-05-13 Drawing method of SVG (scalable vector graphics) face cartoon Pending CN103236075A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 201310172841 CN103236075A (en) 2013-05-13 2013-05-13 Drawing method of SVG (scalable vector graphics) face cartoon

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 201310172841 CN103236075A (en) 2013-05-13 2013-05-13 Drawing method of SVG (scalable vector graphics) face cartoon

Publications (1)

Publication Number Publication Date
CN103236075A true CN103236075A (en) 2013-08-07

Family

ID=48884114

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201310172841 Pending CN103236075A (en) 2013-05-13 2013-05-13 Drawing method of SVG (scalable vector graphics) face cartoon

Country Status (1)

Country Link
CN (1) CN103236075A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104157001A (en) * 2014-08-08 2014-11-19 中科创达软件股份有限公司 Method and device for drawing head caricature
CN104616329A (en) * 2015-02-10 2015-05-13 广州视源电子科技股份有限公司 Picture generation method and device

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104157001A (en) * 2014-08-08 2014-11-19 中科创达软件股份有限公司 Method and device for drawing head caricature
CN104616329A (en) * 2015-02-10 2015-05-13 广州视源电子科技股份有限公司 Picture generation method and device

Similar Documents

Publication Publication Date Title
WO2018177237A1 (en) Image processing method and device, and storage medium
CN101477696B (en) Human character cartoon image generating method and apparatus
EP3096263A1 (en) Human body orientation recognition method and system based on two-lens camera
CN111767920B (en) Method and device for extracting region of interest, electronic equipment and storage medium
CN111243050A (en) Portrait simple stroke generation method and system and drawing robot
CN104915952B (en) Local protrusion object extraction method based on multiway tree in a kind of depth image
Zhang et al. Segmentation for finger vein image based on PDEs denoising
CN103236075A (en) Drawing method of SVG (scalable vector graphics) face cartoon
Wang et al. Relief stylization from 3D models using featured lines
CN113628144B (en) Portrait restoration method and device, electronic equipment and storage medium
CN202855297U (en) Background music control device based on expression
CN113392820B (en) Dynamic gesture recognition method and device, electronic equipment and readable storage medium
Angelina Uy et al. Revisiting point cloud classification: A new benchmark dataset and classification model on real-world data
CN102013107A (en) Selective image stylizing method based on nonlinear filtering
JP2009271657A5 (en)
Hwang et al. A Study on Adaptive Skin Extraction using a Gradient Map and Saturation Features
Li et al. Eyeglasses try-on based on improved poisson equations
Rui et al. Improved color image segmentation algorithm based on GrabCut
CN115695948B (en) Video cover setting method, device, equipment and storage medium
Liu et al. Line drawing via saliency map and ETF
Xie Image Processing Analysis and Research Based on 3D Animation Design
MENG et al. Salient Region Extraction Algorithm for Multi-target
Shen et al. Depth-aware video abstraction
Zhang et al. Automatic face caricatures synthesis and exaggeration
Zhang et al. Generating algorithm of portrait cartoon based on face image

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20130807

WD01 Invention patent application deemed withdrawn after publication