Please use this identifier to cite or link to this item: http://localhost:8081/xmlui/handle/123456789/9788
Title: FACE DETECTION USING COLOR SEGMENTATION
Authors: Kumar, Maheshwarla Praveen
Keywords: ELECTRONICS AND COMPUTER ENGINEERING;ELECTRONICS AND COMPUTER ENGINEERING;ELECTRONICS AND COMPUTER ENGINEERING;ELECTRONICS AND COMPUTER ENGINEERING
Issue Date: 2003
Abstract: Images containing faces are essential to intelligent vision-based human computer interaction. To build fully automated systems that analyze the information contained in face images, robust and efficient face detection algorithms are required. Given a single image, the goal of face detection is to identify all image regions that contain a face regardless of its position, orientation, and lighting conditions. Color image segmentation algorithm is used for the face detection. Color image segmentation is a process of extracting from the image domain one or more connected regions satisfying uniformity (homogeneity) criterion, which is based on features. Color segmentation is effective process to separate skin from its background. Color in the linear format is transformed to other color space in order to provide a wide distinguish between skin and nonskin components. Further the image is post processed to acquire the face region in the image. Color of skin is a property that could easily differentiate clothing, hair etc so the face regions present is easily identified and could ,segmented from the non skin regions. The skin regions belong to certain range of values in the color space that is used for the identification of skin regions in the pixel. The skin regions obtained are operated by the morphological operators that makes the clear identification of how far the face region is present and made it possible for the location of face
URI: http://hdl.handle.net/123456789/9788
Other Identifiers: M.Tech
Research Supervisor/ Guide: Anand, R. S.
metadata.dc.type: M.Tech Dessertation
Appears in Collections:MASTERS' DISSERTATIONS (E & C)

Files in This Item:
File Description SizeFormat 
ECDG11255.pdf3.36 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.