We propose an appearance based model for face recognition in news videos using an enormously large databank of still
images. This is a step towards building an elaborate face-query system using multimodal audio-visual data. We use the
fact that faces of the same person appear similar than of different people. We preprocess the videos, apply feature
extraction, feature matching and a unique parallel line matching algorithm to develop a simple yet a powerful face
recognition system. We tested our approach on real world data and the results show good performance both for high
resolution still images and low resolution news videos without involving any training or tasks like face rectification,
warping etc. It can be incorporated as part of a larger multimodal news video analysis system with problems of time
alignment between text and faces. Our results show that this simple approach also works well where video modality is
the only source of information.
Due to a large increase in the video surveillance data recently in an effort to maintain high security at public
places, we need more robust systems to analyze this data and make tasks like face recognition a realistic possibility
in challenging environments. In this paper we explore a watch-list scenario where we use an appearance based
model to classify query faces from low resolution videos into either a watch-list or a non-watch-list face. We
then use our simple yet a powerful face recognition system to recognize the faces classified as watch-list faces.
Where the watch-list includes those people that we are interested in recognizing. Our system uses simple feature
machine algorithms from our previous work to match video faces against still images. To test our approach, we
match video faces against a large database of still images obtained from a previous work in the field from Yahoo
News over a period of time. We do this matching in an efficient manner to come up with a faster and nearly
real-time system. This system can be incorporated into a larger surveillance system equipped with advanced
algorithms involving anomalous event detection and activity recognition. This is a step towards more secure and
robust surveillance systems and efficient video data analysis.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.