Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Real-Time Face Recognition Based on Optical Flow and Histogram Equalization


Affiliations
1 Department of Electronics and Communication Engineering, RMK Engineering College, India
     

   Subscribe/Renew Journal


Face recognition is one of the intensive areas of research in computer vision and pattern recognition but many of which are focused on recognition of faces under varying facial expressions and pose variation. A constrained optical flow algorithm discussed in this paper, recognizes facial images involving various expressions based on motion vector computation. In this paper, an optical flow computation algorithm which computes the frames of varying facial gestures, and integrating with synthesized image in a probabilistic environment has been proposed. Also Histogram Equalization technique has been used to overcome the effect of illuminations while capturing the input data using camera devices. It also enhances the contrast of the image for better processing. The experimental results confirm that the proposed face recognition system is more robust and recognizes the facial images under varying expressions and pose variations more accurately.

Keywords

Optical Flow Algorithm, Skin Color Segmentation, Histogram Equalization, Feature Extraction, Pattern Matching.
Subscription Login to verify subscription
User
Notifications
Font Size

Abstract Views: 222

PDF Views: 2




  • Real-Time Face Recognition Based on Optical Flow and Histogram Equalization

Abstract Views: 222  |  PDF Views: 2

Authors

D. Sathish Kumar
Department of Electronics and Communication Engineering, RMK Engineering College, India
S. Joshua Kumaresan
Department of Electronics and Communication Engineering, RMK Engineering College, India

Abstract


Face recognition is one of the intensive areas of research in computer vision and pattern recognition but many of which are focused on recognition of faces under varying facial expressions and pose variation. A constrained optical flow algorithm discussed in this paper, recognizes facial images involving various expressions based on motion vector computation. In this paper, an optical flow computation algorithm which computes the frames of varying facial gestures, and integrating with synthesized image in a probabilistic environment has been proposed. Also Histogram Equalization technique has been used to overcome the effect of illuminations while capturing the input data using camera devices. It also enhances the contrast of the image for better processing. The experimental results confirm that the proposed face recognition system is more robust and recognizes the facial images under varying expressions and pose variations more accurately.

Keywords


Optical Flow Algorithm, Skin Color Segmentation, Histogram Equalization, Feature Extraction, Pattern Matching.