Academic Journals Database
Disseminating quality controlled scientific knowledge

FACIAL FEATURES DETECTION

ADD TO MY LIST
 
Author(s): Surbhi | Vishal Arora

Journal: International Journal of Chemical Sciences and Research
ISSN 2249-0329

Volume: 02;
Issue: 01;
Start page: 19;
Date: 2012;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Affine transformation | Thresholding | floodfill algorithm | bezier curve

ABSTRACT
Computer has been widely deployed to our daily lives, but human computer interaction still lacks intuition. Researchers intend to resolve these shortcomings by augmenting traditional systems with human like interaction mechanism. Dedicated hardware often infers the emotional state from human body measures. These have been a considerable amount of research done into the detection and implicit communication channels, including the study of facial feature extraction. [5] The original ASM method developed by Cootes et al. highly relies on the initialization and the representation of the local structure of the facial features in the image. We use color information to improve the ASM approach for facial feature extraction. Image is converted into 256 X 256 pixel mask using affine transformation’s Translation and Rotation Any skin color if found in the image is caught and turned black. A larger area of connected region (skin color) is found that is probable to become a face. The image is converted into a 2 color image (binary image), white representing the normal skin part, black defines the dark edges found on the face image. Using the binary images, we know the edges of facial feature (eyes, lips) now. These are used to extract out only the facial area. Based on the facial image block, eyes and lips are detected in the image. Using Flood Fill technique, each among the three features – left eye, right eye, lips, a shape define by some coordinates is derived out.
Save time & money - Smart Internet Solutions     

Tango Rapperswil
Tango Rapperswil