Published on Jan 09, 2023
Biometrics is the science of identifying or verifying the identity of a person based on physiological or behavioral characteristics. Biometrics identification methods have proved to be very efficient, more natural and easy for users than traditional methods of human identification. In today’s world security plays a very important role in organizations and particularly computer systems .
To make systems more reliable and secure, several biometric techniques that exploit physiological and behavioral traits and characteristics of people have been developed for verification and identification of the individuals. Biometric authentication systems are essentially pattern recognition systems, the physiological characteristics being fingerprint, face, hand geometry, DNA and iris recognition.
The main aim of the project is to develop a biometric authentication system using the ear. The process will involve several steps from acquisition of the image to the point where a positive identification can be made using the system. The image was acquired using a digital camera. The photo is then processed, stored and used for the identification process. For every individual, there are some distinct features that can be used for identification. The portion or segment that contains these unique features is known as the Region of Interest. After the raw data is obtained, the Region of Interest (ROI) which is the area containing the ear image is chosen.
Feature extraction filters the uniqueness data out of the raw data and combines them into the biometric feature The method applied for this is Edge detection. For “easy” images from the database error-free recognition was obtained. When all the external conditions such as lighting are effectively controlled and remain constant, all the system produces a perfect performance with accurate results all the time.
In proposing the ear as the basis for a new class of biometrics, there is the need to show that it is viable (i.e., Universal, unique, Permanent, Collectable). In the same way that no one can prove that fingerprints are unique, there is no absolute way to show that each human has a unique pair of ears. Instead, an assertion that this is probable can be made based on supporting evidence from two experiments conducted by Alfred Iannarelli (Appendix 2). It is obvious that the structure of the ear does not change radically over time. Medical literature reports that ear growth after the first four months of birth is proportional. It turns out that even though ear growth is proportional, gravity can cause the ear to undergo stretching in the vertical direction.
The effect of this stretching is most pronounced in the lobe of the ear, and measurements show that the change is non-linear. The rate of stretching is approximately five times greater than normal during the period from four months to the age of eight, after which it is constant until around 70 when it again increases. Since every individual has ears, it is rational to conclude that the ear is universal. The ear is also collectable using various means. The ear has several unique key points that can be used for identification. The major problem in ear identification systems is discovering an automated method to extract those specific key points.
DThe use of the ear has certain advantages. These include:
It is passive. Unlike the fingerprint and iris, it can be easily captured from a distance without a fully cooperative subject.
Unlike the face, the ear is a relatively stable structure that does not change much with the age and facial expressions. The shape does not change due to emotion as the face does, and the ear is relatively constant over most of a person’s life.
The ear’s smaller size and more uniform color are desirable traits for pattern recognition. The uniform distribution of color means that almost all information is conserved when converting the original image into gray scales.
Basically there are two types of application scenarios:
Identification (also known as recognition)
Authentication (also known as verification) Identification (“one-to-many matching”) implies matching a biometric sample against all records in a database of templates.
The individual presents a biometric sample and the system tries to identify the individual from a database of stored biometric samples. This process intends to answer the question “Who is he?” Biometric verification requires comparing an enrolled biometric sample (biometric template) against a newly presented one. It is a “one-to-one matching” process. In authentication the comparison is done only with data, which is known to be valid for the approved person, e.g. the fingerprint or hand shape is included in an identification card. The card will be entered first to the system. After that the system verifies that the new biometric is valid with the one which was in the identification card. Ear biometrics can be used as a supplementary source of evidence in identification and recognition systems.
This project was aimed at developing a biometric authentication system based on human ear images. An invariant geometrical method was used in order to extract features needed for classification. After the feature extraction, authentication is performed based on simple comparison between a new input image and an already existing one.
The human ear is a perfect source of data for passive person authentication in many applications. In a growing need for security in various public places, ear biometrics seem to be a good solution, since ears are visible and its images can be easily taken, even without the knowledge of the examined person. Then the robust feature extraction method can be used to determine personality of some individuals, for instance terrorists at the airports and stations.
Access control to various buildings and crowd surveillance are among other possible applications. Ear biometrics can be also used to enhance effectiveness of other well-known biometrics, by its implementation in multimodal systems. Since most of the methods have some drawbacks, recently, the idea of building multimodal (hybrid) biometrics systems is gaining lot of attention. Due to its advantages, ear biometrics seems to be a good choice to support well known methods like voice, hand or face identification.
The hardware and software requirements for the development phase of our project are:
OPERATING SYSTEM: Windows XP or Windows Vista
DEVELOPMENT KIT : MATLAB
Image Acquisition Device: CCTV or Digital Camera
Processor : Pentium IV or higher
Hard Disk : 40GB or more
RAM : 256MB or more