Abstract

We present a nonparametric facial feature localization method using relative directional information between regularly sampled image segments and facial feature points. Instead of using any iterative parameter optimization technique or search algorithm, our method finds the location of facial feature points by using a weighted concentration of the directional vectors originating from the image segments pointing to the expected facial feature positions. Each directional vector is calculated by linear combination of eigendirectional vectors which are obtained by a principal component analysis of training facial segments in feature space of histogram of oriented gradient (HOG). Our method finds facial feature points very fast and accurately, since it utilizes statistical reasoning from all the training data without need to extract local patterns at the estimated positions of facial features, any iterative parameter optimization algorithm, and any search algorithm. In addition, we can reduce the storage size for the trained model by controlling the energy preserving level of HOG pattern space.

Highlights

  • The vision-based face monitoring became one of the convenient human-computer-interaction (HCI) tools since face region detection and tracking algorithms [1,2,3] have been proposed

  • Instead of using any iterative parameter optimization technique or search algorithm, our method finds the location of facial feature points by using a weighted concentration of the directional vectors originating from the image segments pointing to the expected facial feature positions

  • Each directional vector is calculated by linear combination of eigendirectional vectors which are obtained by a principal component analysis of training facial segments in feature space of histogram of oriented gradient (HOG)

Read more

Summary

Introduction

The vision-based face monitoring became one of the convenient human-computer-interaction (HCI) tools since face region detection and tracking algorithms [1,2,3] have been proposed. Likelihood maps for each feature point related to the image segments were calculated by using the classifier trained by boosting strategy This algorithm showed very accurate localization result and fast performance with illumination and scale invariance. For the input face image, they divided face images into canonical segments and found the most similar one from codebook by comparing HOG patterns of input and training segments with approximated nearest neighbor search (ANNS) algorithm [13] They calculated the positions of facial feature points by weighted vector concentration (WVC) algorithm which calculates the crossing points of the relative direction vectors corresponding to the found segments.

Histograms of Oriented Gradients
Compact Codebook
Localizing Facial Features
Experimental Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call