FEATURE EXTRACTION USING ICA AND HOG METHOD FOR FACE RECOGNITION SYSTEM
Face recognition is one of the relevant image analysis aplications in the field of computer vision considering that currently access to camera technology is easy to obtain and its application in the field of biometrics and supervision. One of the main factor that determine the accuracy of the face r...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/30973 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Face recognition is one of the relevant image analysis aplications in the field of computer vision considering that currently access to camera technology is easy to obtain and its application in the field of biometrics and supervision. One of the main factor that determine the accuracy of the face recognition process is the feature representation of the image and the classification method used. At present, many method can be used to represent features of an image. Independent Component Analysis (ICA) technique that can be used to represent features of an image. But in terms of speed, ICA requires a long time. In this study will be used Histogram of Oriented Gradient (HOG) to help accelerate ICA. The result of this study indicate that the implementation of HOG can increase the feature extraction time required by an ICA. |
|---|