Method for automatically generating portrait painting

An automatic generation, portrait painting technology, applied in the generation of 2D images, image data processing, instruments, etc., can solve the problems of slow speed, time-consuming and labor-intensive, and achieve high speed, improved face similarity, and face similarity. high effect

Inactive Publication Date: 2007-09-12
湖北莲花山计算机视觉和信息科学研究院
View PDF0 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The drawbacks of the above method for automatically generating portraits are: 1. Due to the use of a pixel-based sampling method, the speed is very slow; 2. When another style of portrait needs to be output, the method must regenerate the portrait according to another style of training samples. Time-consuming and labor-intensive

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for automatically generating portrait painting
  • Method for automatically generating portrait painting
  • Method for automatically generating portrait painting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] The automatic generation method embodiment 1 of the portrait of the present invention, the software flow process of the automatic generation of the method embodiment of the present invention is as shown in Figure 1, and its method steps are:

[0049] (1), the step of setting up the portrait template library of each part of the face;

[0050] The portrait template library of various parts of the face includes: hair portrait template library, clothes portrait template library, eyebrow portrait template library, eye portrait template library, nose portrait template library, mouth portrait template library, and face profile portrait template library. The relationship diagram between the template libraries of various parts is shown in Figure 7.

[0051] As shown in Figure 2, the storage structure table of each portrait template in the portrait template library includes: coding, the portrait template (form 1) of this part, the coordinates of each feature point of the portrait...

Embodiment 2

[0088] The automatic generation method embodiment 2 of portrait of the present invention, its method is basically the same as embodiment, only step (4) is specifically:

[0089] A, the shape formed by the image feature points of each part after the decomposition is compared with the shape formed by the feature points of the corresponding portrait template parts in the portrait template library respectively, and the matching template is selected;

[0090] B. When the number of matched portrait templates is greater than or equal to 2, step (6) outputs a plurality of combined human face portraits.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a portrait automatic production method, its method step is: (1) builds the step of person face various spots portrait template storehouse; (2) examines various characteristic point coordinates in the input person face picture,and manner face various spots localization step; (3) carries on the step of decomposition according to the person face various spots localization to the input person face picture various spots; (4) separately carries on the contrast between decomposed various spots and respective corresponding portrait template spot in the portrait template storehouse, choose the match template; (5) the matched portrait template will deform to respectively corresponds person face various spots position; (6) outputs the person face portrait. This invention method carries on the contrast with the decomposed each picture characteristic point coordinates and the portrait template storehouse, the choice match template, therefore, this method speedis quick.

Description

technical field [0001] The invention relates to the technical field of computer image processing, in particular to a method for a computer to automatically generate a portrait according to a given face image. Background technique [0002] Portraiture is a very popular form of artistic expression, especially the portrait of a human face can artistically express an individual's facial features. However, drawing portraits is not a natural ability of human beings, and only artists who have undergone long-term hard training can draw very realistic portraits. Therefore, how to make a computer automatically generate a portrait based on a given face image is obviously a very difficult and challenging subject. [0003] The article "Automatic Portrait Generation Algorithm Based on Sample Learning" in the second issue of Volume 26 of "Journal of Computer Science" discloses an automatic portrait generation method. The specific steps of the method are: [0004] (1), using a group of fa...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T11/00
Inventor 朱松纯
Owner 湖北莲花山计算机视觉和信息科学研究院
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap