Human face cartoon generation method based on feature point localization

A technology of feature point positioning and cartoon drawing, which is applied in the fields of image processing and computer vision, can solve the problems of face image similarity difference and complex learning process, and achieve high similarity and good cartoon effect

Inactive Publication Date: 2013-12-18
UNIV OF ELECTRONIC SCI & TECH OF CHINA
View PDF3 Cites 41 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These methods can effectively generate cartoon faces with a certain artistic style, but the learning process is extremely c

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
  • Human face cartoon generation method based on feature point localization
  • Human face cartoon generation method based on feature point localization
  • Human face cartoon generation method based on feature point localization

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0039] From training to detection to realize face cartoon generation, the steps are as follows figure 1 Shown:

[0040] Step 1. Positioning of facial feature points. First, preprocess the images in the face training library (face image library) and cartoon training library (cartoon image library), including alignment and normalizing all images to 250*300. Based on the AAM algorithm, the active appearance model, it is applied to face cartoonization. The feature points of the face image database and cartoon image database are manually calibrated, and the AAM model is used to train them to obtain the face image and The average face of the cartoon image, and the change process from the average face of the face image (photo) to the real face is obtained from the model. At the same time, through this model, the position information of the corresponding feature points can be obtained for the input test image, and the coordinate information of these feature points can be saved. The num...

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 provides a human face cartoon generation method based on feature point localization. The method comprises the steps that the feature points of an input image are obtained, the feature points comprise symbolic face contour points; eyes, eyebrows and a nose in the input image are subjected to overlapping partitioning respectively; optimum matching blocks are searched for all blocks in a human face image block base, a cartoon block in a cartoon image block base corresponding to each optimum matching block is a found cartoon matching block; the cartoon matching blocks are combined to form whole organ blocks, organs are placed to the corresponding positions of the input image according to the positions of the feature points; a face contour and a mouth are placed to the corresponding positions of the input image according to the positions of the feature points; hair is placed to the corresponding position of the input image; coloring is carried out on a cartooned image, and a final human face cartoon is generated. According to the generation method, the feature points are used for partitioning the input image, and accordingly the optimum matching blocks are found to be combined to form the whole organs, and a human face similar to a real human face can be well formed quickly.

Description

technical field [0001] The invention belongs to image processing and computer vision technology, in particular to a method for generating a cartoon based on a single front face image. Background technique [0002] At present, the methods of face cartoonization mainly include methods based on templates, methods based on image processing, and methods based on sample learning. [0003] The template-based method mainly finds the difference between the test face and the "average face" through observation and statistics, and exaggerates the difference through artificially specified exaggeration deformation parameters. Since the template-based method is mainly aimed at the exaggerated deformation of the specified features, although it has strong interactivity, the change form is fixed and lacks artistic sense and aesthetic feeling. [0004] The method based on image processing is to process the pixels of the image itself, and the processed image can automatically generate a cartoo...

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
IPC IPC(8): G06T7/00
Inventor 李宏亮许静黄超黄敏吴庆波罗冰谢昱瑞
Owner UNIV OF ELECTRONIC SCI & TECH OF CHINA
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