Ear Identification System Based on Hybrid Techniques

Alaa Sulaiman Al-Waisy

In this paper, an efficient ear identification system is presented for human recognition based on Curvelet Transform and Fractal Dimension (FD). In the proposed system, the ear images are cropped manually from the side head images. After that curvelet Transform and FD are used as a hybrid features extraction technique. The proposed system aims to reduce the dimensionality that reduce the required computational power and memory size so that, the mean and standard deviation (STD) are computed from the learning and testing samples and used as input to classification phase to recognize different ears. The proposed system have been tested and compared with other systems using two different databases the first one is a constructed ear database named as Ear_Images database, which is consist of 200 images. The second database is the USTB database. The experimental results show that the achieved recognition rates by the proposed system are up to 92.7% and 93.4, respectively.

Select Volume / Issues:

• Volume 3 Issue 5, Sept. 2012

Year:

2012

Type of Publication:

Article

Keywords:

Biometrics; Ear Recognition; Ear Identification; Curvelet Transform; Fractal Dimension

Journal:

IJECCE

Volume:

3

Number:

5

Pages:

1244-1247

Month:

Sept.