Empirical analysis of cascade deformable models for multi-view face detection

J. Orozco; B. Martinez; M. Pantic

Empirical analysis of cascade deformable models for multi-view face detection

J. Orozco, B. Martinez, M. Pantic

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

93 Downloads (Pure)

Abstract

In this paper, we present a face detector based on Cascade Deformable Part Models (CDPM) [1]. Our model is learnt from partially labelled images using Latent Support Vector Machines (LSVM). Recently Zhu et al. [2] proposed a Tree StructureModel for multi-view face detection trained with facial landmark labels, which resulted on a complex and suboptimal system for face detection. Instead, we adopt CDPMs enhanced with a data-mining procedure to enrich models during the LSVM training. Furthermore, a post-optimization procedure is derived to improve the performance of the CDPMs. Experimental results show that the proposed model can deal with highly expressive and partially occluded faces while outperforming the state-of-the-art face detectors by a large margin on challenging benchmarks such as the FDDB [3] and the AFLW [4] databases.

Original language	English
Title of host publication	Proceedings of the IEEE International Conference on Image Processing, ICIP 2013
Publisher	IEEE Computer Society
Number of pages	5
Publication status	Published - Sep 2013
Event	IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, Australia Duration: 15 Sep 2013 → 18 Sep 2013

Conference

Conference	IEEE International Conference on Image Processing, ICIP 2013
Abbreviated title	ICIP
Country	Australia
City	Melbourne
Period	15/09/13 → 18/09/13

Keywords

HMI-HF: Human Factors
FDDB database
AFLW database
Multi-view face detection
Cascade deformable models

Access to Document

Orozco2015empirical
open
Final published version, 694 KB

Fingerprint Dive into the research topics of 'Empirical analysis of cascade deformable models for multi-view face detection'. Together they form a unique fingerprint.

Cite this

@inproceedings{e6c7906a2e28400a9540ca65b36505e9,

title = "Empirical analysis of cascade deformable models for multi-view face detection",

abstract = "In this paper, we present a face detector based on Cascade Deformable Part Models (CDPM) [1]. Our model is learnt from partially labelled images using Latent Support Vector Machines (LSVM). Recently Zhu et al. [2] proposed a Tree StructureModel for multi-view face detection trained with facial landmark labels, which resulted on a complex and suboptimal system for face detection. Instead, we adopt CDPMs enhanced with a data-mining procedure to enrich models during the LSVM training. Furthermore, a post-optimization procedure is derived to improve the performance of the CDPMs. Experimental results show that the proposed model can deal with highly expressive and partially occluded faces while outperforming the state-of-the-art face detectors by a large margin on challenging benchmarks such as the FDDB [3] and the AFLW [4] databases.",

keywords = "HMI-HF: Human Factors, FDDB database, AFLW database, Multi-view face detection, Cascade deformable models",

author = "J. Orozco and B. Martinez and M. Pantic",

year = "2013",

month = sep,

language = "English",

booktitle = "Proceedings of the IEEE International Conference on Image Processing, ICIP 2013",

publisher = "IEEE Computer Society",

address = "United States",

note = "IEEE International Conference on Image Processing, ICIP 2013, ICIP ; Conference date: 15-09-2013 Through 18-09-2013",

}

TY - GEN

T1 - Empirical analysis of cascade deformable models for multi-view face detection

AU - Orozco, J.

AU - Martinez, B.

AU - Pantic, M.

PY - 2013/9

Y1 - 2013/9

N2 - In this paper, we present a face detector based on Cascade Deformable Part Models (CDPM) [1]. Our model is learnt from partially labelled images using Latent Support Vector Machines (LSVM). Recently Zhu et al. [2] proposed a Tree StructureModel for multi-view face detection trained with facial landmark labels, which resulted on a complex and suboptimal system for face detection. Instead, we adopt CDPMs enhanced with a data-mining procedure to enrich models during the LSVM training. Furthermore, a post-optimization procedure is derived to improve the performance of the CDPMs. Experimental results show that the proposed model can deal with highly expressive and partially occluded faces while outperforming the state-of-the-art face detectors by a large margin on challenging benchmarks such as the FDDB [3] and the AFLW [4] databases.

AB - In this paper, we present a face detector based on Cascade Deformable Part Models (CDPM) [1]. Our model is learnt from partially labelled images using Latent Support Vector Machines (LSVM). Recently Zhu et al. [2] proposed a Tree StructureModel for multi-view face detection trained with facial landmark labels, which resulted on a complex and suboptimal system for face detection. Instead, we adopt CDPMs enhanced with a data-mining procedure to enrich models during the LSVM training. Furthermore, a post-optimization procedure is derived to improve the performance of the CDPMs. Experimental results show that the proposed model can deal with highly expressive and partially occluded faces while outperforming the state-of-the-art face detectors by a large margin on challenging benchmarks such as the FDDB [3] and the AFLW [4] databases.

KW - HMI-HF: Human Factors

KW - FDDB database

KW - AFLW database

KW - Multi-view face detection

KW - Cascade deformable models

M3 - Conference contribution

BT - Proceedings of the IEEE International Conference on Image Processing, ICIP 2013

PB - IEEE Computer Society

T2 - IEEE International Conference on Image Processing, ICIP 2013

Y2 - 15 September 2013 through 18 September 2013

ER -