#TITLE_ALTERNATIVE#
<p align="justify">Human ability in recoginitiion faces is an really extraordinary. With this ability, human can recognize thousands of faces learned throughout lifetime and identify familiar faces at a glance even after years of separation. This skill is quite robust despite large c...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/11078 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | <p align="justify">Human ability in recoginitiion faces is an really extraordinary. With this ability, human can recognize thousands of faces learned throughout lifetime and identify familiar faces at a glance even after years of separation. This skill is quite robust despite large changes in visual stimulus due to viewing conditions, expression, aging, and distractions such as glasses or changes in hairstyle or facial hair. As a consequence the visual processing of human faces has fascinated philosophers and scientists for centuries.<p align="justify"><p>The ability to recognize faces which is implemented in a system can give many benefits in life nowadays. Many aplication of such system range from searching criminal, criminality, access system, until human interactin with computers.<p align="justify"><p>In this paper, a system of human face recognition, called face recognition, is designed. Face recognition is a branch of biometric, that is a science that use physical characteristic of human to recognize and to identify someone. Recognition method used in the system is eigenface method. Eigenface method is classified in appearance-based method. It means that the inputs is human faces as a whole and it doesn't consider geometric nor spatial relationship among face elements such as nose, eyes, chin and mouth. Eigenface method works by comparing face image in low dimension, much more lower than the real dimension of the image. The reduction of dimension is conducted by implementing principal component analysis technique on the face images.<p align="justify"><p>To know the performance of this system, a test will be conducted to the system. The inputs used in the test are 135 face images from Yale Face Database and 9 non-face images. Based on the test, the performance of the system is 85,42% in recognition image inputs. <br />
|
|---|