What question did this study set out to answer?

This research aims to improve the efficiency and accuracy of feature localisation in images using boosted regression models.

January 1, 2007

Boosted Regression Active Shape Models

Key Points

This research aims to improve the efficiency and accuracy of feature localisation in images using boosted regression models.
Two types of non-linear boosted feature models were trained using GentleBoost.
A feature detector classifier learns a discrimination function; a boosted regression predictor learns displacement from feature location.
Performance was evaluated on two human face test sets, focusing on search speed and localisation accuracy.
The boosted regression model improves localisation accuracy compared to traditional methods.
Search speed increased by a factor of eight during the local iterative search of the ASM.

Abstract

We present an efficient method of fitting a set of local feature models to an image within the popular Active Shape Model (ASM) framework 3. We compare two different types of non-linear boosted feature models trained using GentleBoost 9. The first type is a conventional feature detector classifier, which learns a discrimination function between the appearance of a feature and the local neighbourhood. The second local model type is a boosted regression predictor which learns the relationship between the local neighbourhood appearance and the displacement from the true feature location. At run-time the second regression model is much more efficient as only the current feature patch needs to be processed. We show that within the local iterative search of the ASM the local feature regression provides improved localisation on two publicly available human face test sets as well as increasing the search speed by a factor of eight. 1

Ask AI

Helpful

Bookmark