الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 72 |  |  |
| | | from | 72 | | |
Abstract
The humans’ faces hold a lake of information that enables us to identify them. Human brain depends on physical characteristics such as skin color, hair type, and facial features for dividing people into different ethnicity groups. Classification of a human’s ethnicity is important information in various areas, such as biometrics, security, and personal safety.
The importance of human ethnicity classification lies according to context. In some cases, it may be necessary for medical research or treatment, as certain diseases and conditions are more prevalent in specific ethnic groups. In real time applications, it useful in security area. It can also be important for demographic studies and understanding cultural differences. However, it is important to note that ethnicity is a complex, therefore any classification system must be developed with sensitivity and caution.
Within the past few decades, the researchers in the computer vision field developed different algorithms to computerize the distinguish of human ethnicity. At first, reliance on some superficial features may lead to poor discrimination accuracy, as there is often significant overlap between different ethnic groups. With the advent of deep learning, the researchers developed many algorithms, which has contributed to satisfactory ethnicity classification results.
This work presents a model that classifies ethnicity and gender according to 5 ethnicity classes. Moreover, the proposed model classifying males and females for each ethnicity group.