This paper presents a novel method for facial feature extraction from video. Face recognition from video has been extensively studied in recent years. Intuitively, video provides more information than a single image. When a face is partially occluded, handling the occluded part of the face is an especially challenging task. The present research work proposes the method to recognize a face from video based on face patches. First, face patches are cropped from the video frame by frame [4]. Then, face patches are to be matched to an overall face model and stitched together. By accumulating the patches, a reconstructed face is to be built which is used in recognition. Then testing has to be done in two parts. In the first part, a still face database is to be used by randomly occluding parts of the face and using the remaining face patches in recognition. In the second part, the image is to be tested on video sequences. Related Work Automated face recognition is a relatively new concept. Developed in the 1960’s[1], the first semi-automated system for face recognition required the administrator to locate features(such as eyes, ears, nose, and mouth) on the photographs before it calculated distances and ratios to a common reference point, which were then compared to a reference data[2].
[1]
Teuvo Kohonen,et al.
An introduction to neural computing
,
1988,
Neural Networks.
[2]
Igor Aleksander,et al.
Introduction to Neural Computing
,
1990
.
[3]
L. D. Harmon,et al.
Identification of human faces
,
1971
.
[4]
Bayya Yegnanarayana,et al.
Face Detection, Recognition in an Image Sequence Using Eigenedginess
,
2002,
ICVGIP.
[5]
Takeo Kanade,et al.
Multiple Face Recognition from Omnidirectional Video
,
2005
.
[6]
Jake K. Aggarwal,et al.
Patch-based face recognition from video
,
2009,
2009 16th IEEE International Conference on Image Processing (ICIP).