January 1, 2014

Active Shape Models with SIFT Descriptors and MARS

Key Points

Key points are not available for this paper at this time.

Abstract

We present a technique for locating landmarks in images of human faces. We replace the 1D gradient profiles of the classical Active Shape Model (ASM) (Cootes and Taylor, 1993) with a simplified form of SIFT descriptors (Lowe, 2004), and use Multivariate Adaptive Regression Splines (MARS) (Friedman, 1991) for descriptor matching. This modified ASM is fast and performs well against existing techniques for automatic face landmarking on frontal faces.

Perguntar à IA

Bookmark

Cite This Study

A Wed, study studied this question.

synapsesocial.com/papers/6a1b285c4c407ac708e580bb https://doi.org/https://doi.org/10.5220/0004680003800387

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Multiview Active Shape Models with SIFT Descriptors for the 300-W Face Landmark Challenge2013 · 25 citations
2An extended set of Haar-like features for rapid object detection2003 · 2,962 citations
3Random Forests2001 · 126,387 citations
4Facial biometrics for 2D barcodes2012 · 13 citations
5Multivariate Adaptive Regression Splines1991 · 8,084 citations

Perguntar à IA

Bookmark