Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for multi-angle face detection

A technology of face detection and person angle, applied in the field of person target query and search, which can solve problems such as inability to fully adapt

Inactive Publication Date: 2015-07-15
陈遇春
View PDF3 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, so far, any method has its specific application conditions and limitations, and cannot be fully adapted to various situations.

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 multi-angle face detection
  • Method for multi-angle face detection
  • Method for multi-angle face detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described below in conjunction with the accompanying drawings.

[0040] refer to figure 1 , an implementation process of this method. A multi-angle face detection method, the method first adopts the feature detection method of the maximum stable extremum region to the input image to detect the image, obtains the maximum stable extremum region of the image, and normalizes the obtained region, Get the rectangular image of the candidate face to be detected, and then use the LBP algorithm to extract the LBP feature of the image to be detected, and use the neural network RBF function as the face pose classifier according to the LBP feature, and divide the image into left and right faces according to the pose of the face. , positive, and right subcategories, and then calculate the images of each posture subcategory through the continuous Adaboost algorithm, calculate the face features under the three posture subcategories, and finally fu...

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 method for multi-angle face detection. The method comprises the following steps: detecting input images using a maximally stable extremal region feature detection method to obtain maximum stable extremum regions of the images, normalizing the obtained regions to obtain rectangular to-be-detected images of candidate faces, and then using an LBP algorithm to extract LBP characteristics of the to-be-detected images, according to the LBP characteristics, using a neural network RBF function as a face pose classifier to divide the images into three subclasses of left, front, and right according to face poses, calculating the images of each pose subclass through a continuous Adaboost algorithm to obtain facial features under the three pose subclasses, and finally, combining calculating results under the three pose subclasses to detect the face in the image.

Description

technical field [0001] The invention belongs to the technical field of character target query and search, and in particular relates to a multi-angle face detection method. Background technique [0002] The current research methods for face detection of a single image are divided into four categories: [0003] (1) Knowledge-based method. These prior-knowledge-based methods encode knowledge of what constitutes a typical human face. Usually, the prior knowledge contains the interrelationships among these facial features. Such methods are mainly used for face localization. A difficulty of this approach is how to convert face knowledge into well-defined guidelines. If the criteria are too detailed, some faces will be missed because they do not pass all the criteria. If the guidelines are too rough, many positive mistakes will be made. In addition, this method is difficult to extend to detect faces in different poses, because it is difficult to enumerate all possible situati...

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 Patents(China)
IPC IPC(8): G06K9/62
Inventor 李灿
Owner 陈遇春