Human face detection aims to detect the presence and subsequently the position of face or faces in an image is an important task in automated facial image analysis. Humans are able to detect and identify faces in a scene with little or no effort. Our brain analyses, performs segmentation , classifies, recognizes and interprets a huge amount of data captured by the sensory organs like eyes (visual information) and ears (auditory information ) when looking at a scene. These tasks are performed by our brain within a fraction of time with very negligible error. However, many reported methods assume that the faces in an image or an image sequence have been identified and localized.
[...] Based on the compact distribution of human skin color in YCbCr color space and characteristics of eyes and mouth color to segment, the proposed methods deals with the detection of face regions in an image. It consists of two image-processing steps. The first method is to separate skin regions from non-skin-regions and then to locate the frontal of the human face within the skin regions. A chroma chart shows likelihoods of skin colors which is used to generate a gray scale image from the original color image. [...]
[...] Face detection is achieved using Euler's method and some developed heuristics. Then a template matching is performed using template face. Cross–correlation is determined between the skin region and template face images. The luminance component is itself is used together with the template matching to determine if the skin region represents a frontal human face or not. This project presents a face detection technique mainly based on skin color model, skin segmentation, heuristic approaches and template matching method. This document is divided into several pages, each one describing a part of the process to do face detection 2. [...]
[...] However, the increase in segmented region will gradually decrease (as percentage of skin regions detected approaches but will increase sharply when the threshold value is considerably too small that other non-skin regions get included. The threshold value at which the minimum increase in region size is observed while stepping down the threshold value will be the optimal threshold. The threshold value is decremented from 0.60 to 0.05 in steps of 0.1 Next step is to determine which regions can possibly determine a frontal human face for which there is a need to know the number of skin regions in the image. [...]
[...] A frontal face detection techniques based on skin color model which is developed an implemented using face images with different poses, face variations, occlusions and illumination conditions. The entire face detection algorithm is implemented using MATLAB tool on a P4 machine with 2.4 GHz. Current implementation is limited to the detection of frontal human faces. The distance between the objects and camera should be within the range of 10ft. Intersection of two face regions is not detected. A possible extension would be to expand the template matching process to include sided-view faces as well. [...]
[...] 263- S.Sports and R.Rabenstein,” A Real-Time Face Tracker for Color Video”, IEEE International Conference on Acoustics, speech & Signal Processing, Utah, USA, May 2001. K. C. Yow, R. Cipolla,, Feature- based human face detection”, Image and Vision Computing, vol no pp. 713- Dale Brisinda, “Face Detection from constituent Features and Energy Minimizing Spring-Facial Templates”, Thesis Department of Computer science, University of Calgary Saman Cooray and Novel O'Connor, facial feature extraction and principal component analysis for face detection in color Images”, ICIAR 2004, [...]
APA Style reference
For your bibliographyOnline reading
with our online readerContent validated
by our reading committee