Adaboost arithmetic improved robust human ear detection method

A detection method and algorithm technology, applied in computing, computer components, instruments, etc., can solve the problems of false alarm rate not meeting the requirements and high false alarm rate, and achieve the effect of enriching the gray distribution

Inactive Publication Date: 2009-04-01
UNIV OF SCI & TECH BEIJING
View PDF0 Cites 53 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method has greatly improved compared with the model-based method, it only uses the most primitive AdaBoost algorithm, and there are still some shortcomings. For images with simple backgrounds, the f

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
  • Adaboost arithmetic improved robust human ear detection method
  • Adaboost arithmetic improved robust human ear detection method
  • Adaboost arithmetic improved robust human ear detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0262] Embodiment 1: PC-based human ear detection system

[0263] Each operation interface of the human ear detection system of the present invention is as attached respectively Figure 16 , attached Figure 17 And attached Figure 18 shown.

[0264]The human ear detection system constructed by the invention has high-efficiency performance. Ideal test results can be obtained by using the human ear detection system on a PC. The test objects are from the profile face database of the Chinese Academy of Sciences (CAS-PEAL database), the profile face database of Manchester University of Technology (UMIST database) and the human ear of Beijing University of Science and Technology. A total of 434 images with human ears collected in the library (USTB220). The selection principle of the detection library image is: the human ear is not seriously occluded; the size of the human ear image is above 25×30; the complexity of the background image is moderate; the human ear rotated at a ce...

Embodiment 2

[0278] Embodiment 2: DSP-based human ear detection system

[0279] When the research of human ear recognition system is carried out on a PC, its algorithm depends on the specific hardware environment of the PC and the special application software such as Matlab running on it. Therefore, in order to realize the large-scale and extensive application of the human ear recognition system in people's daily life and work, it is necessary to solve many problems such as manufacturing cost, reliability, and power consumption of special equipment. The embedded system itself has the characteristics of portability, low power consumption, strong computing power, reliable operation, and mass production. Therefore, it will be a good choice to combine the human ear recognition technology with the embedded system and develop the human ear recognition system based on the embedded platform.

[0280] By transplanting the program code of the present invention to the DSP platform, an embedded human...

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 robust ear detection method which improves an AdaBoost arithmetic and belongs to the technical field of image mode identifying. The invention is characterized by proposing an ear detection method with excellent performances under a complex underground. The invention proposes four anisomerous Haar-like corner characteristics which are used for describing the grayscale changes on the partial areas of the ears; a policy of subsection selection is adopted for selecting the best sorting threshold of the Haar-like characteristics, thus reducing the sample training time; the weight of a weak sorter is modified for reducing the mistaken detection rate of the sorter; the threshold HW is set and eliminated according to the distribution change of the sample weight in the training, thereby preventing an over-studying phenomenon from being generated and leading the miss-detection rate and the mistaken direction rate of the ear detection to be reduced; besides, the invention also provides a single-ear detection policy for leading both the defection efficiency and the detection effect to be improved. The excellent performances of the robust ear detection method are shown on a PC machine and a DSP.

Description

technical field [0001] The invention relates to a human ear detection system in the technical field of image pattern recognition, in particular to an improved AdaBoost human ear detection method and its hardware implementation. Background technique [0002] With the rapid development of information technology, biometric identification technology has become a new academic research and application hotspot due to its universality, uniqueness, stability and other characteristics. As a unique biological feature of the human body, the human ear not only has the basic properties necessary for biological feature recognition, but also has unique advantages such as rich groove information, gray level distribution, and robustness to postures, making it more and more popular. Come big attention. Since human ear recognition is a relatively new biometric technology, its research is far from the depth and breadth of face recognition. Therefore, as a very important link in the recognition ...

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): G06K9/00G06K9/62
Inventor 穆志纯徐正光敦文杰李文晶张锋
Owner UNIV OF SCI & TECH BEIJING
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