What question did this study set out to answer?

To develop an accurate and fast multi-view face detection framework capable of handling wide variations in both in-plane and out-of-plane head rotations.

January 1, 2005219 citations

Vector boosting for rotation invariant multi-view face detection

View Full Paper

CHChang Huang HAHaizhou Ai YLYuan Li

Key Points

To develop an accurate and fast multi-view face detection framework capable of handling wide variations in both in-plane and out-of-plane head rotations.
Designed a tree-structured multi-view face detector using a coarse-to-fine strategy to partition the face space into progressively smaller subspaces.
Formulated a vector boosting algorithm to train branching node predictors producing multi-component vector outputs.
Evaluated detection latency and orientation coverage on 320 × 240 video sequences across ±45° in-plane and ±90° out-of-plane rotations, extending to full 360° in-plane coverage via rotated detector instances.
The base detector achieved robust detection across ±45° in-plane and ±90° out-of-plane rotations with a processing latency of approximately 40 ms per frame on 320 × 240 video.
The full 360° rotation-invariant detector maintained high accuracy at real-time speeds of 11 frames per second on 320 × 240 video sequences.

Abstract

In this paper, we propose a novel tree-structured multiview face detector (MVFD), which adopts the coarse-to-fine strategy to divide the entire face space into smaller and smaller subspaces. For this purpose, a newly extended boosting algorithm named vector boosting is developed to train the predictors for the branching nodes of the tree that have multicomponents outputs as vectors. Our MVFD covers a large range of the face space, say, +/-45/spl deg/ rotation in plane (RIP) and +/-90/spl deg/ rotation off plane (ROP), and achieves high accuracy and amazing speed (about 40 ms per frame on a 320 /spl times/ 240 video sequence) compared with previous published works. As a result, by simply rotating the detector 90/spl deg/, 180/spl deg/ and 270/spl deg/, a rotation invariant (360/spl deg/ RIP) MVFD is implemented that achieves real time performance (11 fps on a 320 /spl times/ 240 video sequence) with high accuracy.

Ask AI

Helpful

Bookmark

View Full Paper

Cite This Study

Huang et al. (2005) studied this question.

synapsesocial.com/papers/6a10cac68102eb4b66ee69fd https://doi.org/10.1109/iccv.2005.246

Ask AI

Helpful

Bookmark

View Full Paper

January 1, 2005219 citations

Vector boosting for rotation invariant multi-view face detection

View Full Paper

CHChang Huang HAHaizhou Ai YLYuan Li

Key Points

To develop an accurate and fast multi-view face detection framework capable of handling wide variations in both in-plane and out-of-plane head rotations.
Designed a tree-structured multi-view face detector using a coarse-to-fine strategy to partition the face space into progressively smaller subspaces.
Formulated a vector boosting algorithm to train branching node predictors producing multi-component vector outputs.
Evaluated detection latency and orientation coverage on 320 × 240 video sequences across ±45° in-plane and ±90° out-of-plane rotations, extending to full 360° in-plane coverage via rotated detector instances.
The base detector achieved robust detection across ±45° in-plane and ±90° out-of-plane rotations with a processing latency of approximately 40 ms per frame on 320 × 240 video.
The full 360° rotation-invariant detector maintained high accuracy at real-time speeds of 11 frames per second on 320 × 240 video sequences.

Abstract

Ask AI

Helpful

Bookmark

View Full Paper

Cite This Study

Huang et al. (2005) studied this question.

synapsesocial.com/papers/6a10cac68102eb4b66ee69fd https://doi.org/10.1109/iccv.2005.246

Ask AI

Helpful

Bookmark

View Full Paper