Method and device for generating image sample

An image sample and sample technology, applied in the field of image processing, can solve the problems of inability to meet the needs of the application, limited quantity, and few types of face image samples, and achieve the effect of meeting the application needs, good quality, and expanding the image sample library.

Inactive Publication Date: 2011-06-22
VIMICRO CORP
View PDF2 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the above-mentioned prior art methods for obtaining new face image samples are relatively simple, and the types of new

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 and device for generating image sample
  • Method and device for generating image sample
  • Method and device for generating image sample

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Embodiments of the present invention provide a method and device for generating image samples, which are used to obtain better quality and more representative image samples, thereby expanding the image sample library, improving the training accuracy of classifiers based on image samples, and meeting more requirements. Multiple application requirements.

[0023] The embodiment of the present invention is described by taking a human face image sample as an example. Of course, for image samples of other objects, the technical solutions provided in the embodiments of the present invention are also applicable.

[0024] The embodiments of the present invention generate new face image samples based on the AAM model, and use the AAM model to generate a variety of new face image samples from limited face image samples, which can obtain good quality and representative face images. Face image samples, and can generate infinitely many new face image samples, thereby expanding the ...

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 discloses a method and device for generating image sample for obtaining the image sample featured with better quality and excellent representativeness for expanding an image sample base, improving the training precision of a classifier of the image sample and satisfying the application demand. The invention provides a method for generating image sample, comprising the following steps of: classifying the collected image samples according to the predetermined type to obtain different types of image sample sets; performing AAM (Active Appearance Model) training to the image sample of each image sample set to obtain a plurality of AAM models; and generating new image sample by each AAM model.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image sample generation method and device. Background technique [0002] In technical applications involving face image processing, such as face detection, face recognition, etc., the acquisition and processing of face image sample images is a key issue. [0003] The existing technology generally collects a large number of face image samples for training. The more samples, the more extensible the trained classifier is. However, the collection of a large number of face image samples is time-consuming and laborious, and the collected samples are also uneven. Especially for some special applications, such as real-time recognition of a single person, face image samples are limited. [0004] In order to obtain more new face image samples based on existing face image samples, some methods have been proposed in the prior art, such as: using mirror transformation te...

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): G06K9/62
Inventor 谢东海
Owner VIMICRO CORP
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