Human Ear Recognition System
No Thumbnail Available
Date
2013
Journal Title
Journal ISSN
Volume Title
Publisher
Uva Wellassa University of Sri Lanka
Abstract
Biometric features are widely used today for identification purposes. The most interesting
human anatomical parts for biometrics systems are finger prints, the irises, face and ear. These
parts contain a large volume of unique features that allow identifying humans. Among them the
ear has a large amount of unique features (Bhanuet al., 2008). The shape and appearance of an
ear are fixed while other biometric features are changed with age (Singh et al., 2013). There are
no developed systems for identifying a human by using the ear.
This System can be used for criminal investigation purposes. Police Departments, Custom
Departments and other government agencies can use this system as a tool for person
identification.
Methodology
The system will accept an image which contains the ear of a person and register the image and
store its color information taken from 25 regions. When it searches information of a person by
his/her ear, it will compare the values with stored database values using Euclidean distance and
output the corresponding personal information.
The Human Ear Recognition System is an Image based recognition system consisting of three
main modules as shown in Figure 1.
The Widget module contains Graphical User Interfaces of the system. The process component
supports preprocessing of the ear image before registering the ear in the system. It performs
image rotation, cropping and edge detection. Registration component supports the registration
of personal information with a preprocessed image of the ear. The search component supports
searching a particular person from the system by using his/her ear image.
The Service module contains functionalities to detect the edges of the ear, rescale the ear image
and compare the particular ear with the ear database. The average color values of pixels within
predefined 25 areas are taken in to account (Figure 2). The comparison is based on Euclidean
Distance.
The Database module supports the Widget module and the Service module to access the
database. The Database includes records of personal information, a photograph of particular
person and an ear image of the person. These data can be accessed only through the Database
module.
Result and Discussion
The system is able to recognize a person by ear, independent of the angle of the ear. However
problems were occurred due to various lighting conditions, which affects the detection the edges
of the ear. Therefore, there should be standards to take an ear image that will not change from
time to time. So the ear image that is going to be recognized should be taken by following the
same standards as registered images were taken.
The collections of ears used in this research were provided by IIT Delhi Ear Database. They
were taken under identical conditions. The accuracy level of system for those images is 90%.
Description
Keywords
Computer Science, Science and Technology, Technology, System, Recognition System