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

Race recognition method and system based on face and wavelet packet analysis

A technology of wavelet packet analysis and recognition method, which is applied in character and pattern recognition, instruments, computer components, etc., and can solve problems such as inability to adapt to dynamic detection, extremely high classifier requirements, and difficult implementation

Active Publication Date: 2019-05-10
霍尔果斯奇妙软件科技有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, Document 1 requires that the face position is correct, so it can only be used to detect specific pictures, and cannot adapt to dynamic detection; while the feature points extracted in Document 2 are too detailed, the requirements for the classifier are extremely high, and it is difficult to implement

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
  • Race recognition method and system based on face and wavelet packet analysis
  • Race recognition method and system based on face and wavelet packet analysis
  • Race recognition method and system based on face and wavelet packet analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] Below in conjunction with accompanying drawing and embodiment the present invention will be further described:

[0062] In order to clearly illustrate the technical features of this solution, the present invention will be described in detail below through specific implementation modes and in conjunction with the accompanying drawings. The following disclosure provides many different embodiments or examples for implementing different structures of the present invention. To simplify the disclosure of the present invention, components and arrangements of specific examples are described below. Furthermore, the present invention may repeat reference numerals and / or letters in different instances. This repetition is for the purpose of simplicity and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. It should be noted that components illustrated in the figures are not necessarily drawn to scale. Description...

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 race recognition method and system based on face and wavelet packet analysis, and the method comprises the steps: selecting a training sample set comprising different race faces, and carrying out the wavelet packet decomposition of a face image, and obtaining a corresponding decomposition coefficient; screening the decomposition coefficient of the wavelet packet, and selecting a feature subspace of a face race by using an LDB method to obtain an optimal base after wavelet packet transformation; respectively projecting the training sample set images to face race feature subspaces, respectively calculating to obtain feature vector sets of the training sample set images, and training by utilizing an SVM classifier to obtain a training model; and identifying and classifying the to-be-tested image by using the training model to obtain a classification result which is the species to which the test face belongs. According to the method, the race characteristics of the human face are extracted through wavelet packet transformation, the race characteristics are classified through the SVM classifier, the human face race recognition is achieved, the good race recognition effect is achieved, and auxiliary information is provided for personnel identity confirmation.

Description

technical field [0001] The invention relates to a race identification method and system based on human face and wavelet packet analysis, belonging to the technical field of artificial intelligence. Background technique [0002] With the development of the internationalization of the global market, cross-regional exchanges and activities of people of different skin colors are becoming more and more common, and related service industries are also paying more and more attention to differentiated and customized services. The service industry, such as restaurants, faces customers of different races and needs to provide services according to different living and eating habits. Therefore, identifying customer groups of different races plays an important role and significance in improving service quality and providing precise customized services . In addition, accurate racial classification can not only effectively obtain the face characteristics in face data, but also obtain more ...

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): G06K9/00G06K9/62
Inventor 郑飞许芝光
Owner 霍尔果斯奇妙软件科技有限公司