Video image for security system by using chaotic oscillator for segmentation

Abstract EN

There are wide variety of mechanisms available for performing the authentication function.

One of them is by using video film to monitor important places.

In such systems the important task is recognizing human faces which need good segmentation and high feature extraction.

In traditional technique the segmentation can be performed by region growing and shrinking, clustering method, and boundary detection which all take image pixel by pixel and compare each with neighbors to get the similarity.

Chaotic oscillator depends on synchronization concept between points to determine the active points which construct similar region determining the object.

Then RGB color space is used to determine skin color pixel.

Skin color model aids the process of separating the face from the scene due to its skin color.

After isolating the human face image which contains many features (eye, eyebrow, nose, etc...) they identify the person.

Chaotic oscillator is used to extract the important features by removing any point that is not synchronized with its neighbors and gives new image which contains only the main face features and then compare this image with stored image in Database of authorized person and make decision on if (he / she) is an authenticated image or not.