Rapid face detection using a multi-mode cascade and Separate Haar Feature

Ning Jiang, Yijun Lu, Shaopeng Tang, Satoshi Goto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

In this paper, firstly, we describe a new feature for fast and accurate face detection. The feature is called Separate Haar Feature. Secondly, we describe a multi-mode detection algorithm to improve the detection rate. There are three key contributions. The first is "Separate Haar Feature", which adds a don't-care area between the rectangles of Haar Feature. We can get some more efficient features by this algorithm. The second is the algorithm for selecting the best width for this don't-care area and the False Alarm Rate for each stage in "Learning". This algorithm for width selecting is proposed to reduce the total number of learning features for reducing the memory used. And we use a smaller false alarm rate for each stage and less number of stages training the detector to improve the hit rate within the same detection time consuming. Finally, we proposed a multi-mode detection algorithm in cascade detection process to improve the detection rate.

Original languageEnglish
Title of host publicationISPACS 2010 - 2010 International Symposium on Intelligent Signal Processing and Communication Systems, Proceedings
DOIs
Publication statusPublished - 2010
Event18th International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2010 - Chengdu
Duration: 2010 Dec 62010 Dec 8

Other

Other18th International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2010
CityChengdu
Period10/12/610/12/8

Fingerprint

Face recognition
learning
Detectors
Data storage equipment

Keywords

  • Boost
  • Cascade
  • Multi-mode detection
  • Separate Haar Feature

ASJC Scopus subject areas

  • Artificial Intelligence
  • Signal Processing
  • Communication

Cite this

Jiang, N., Lu, Y., Tang, S., & Goto, S. (2010). Rapid face detection using a multi-mode cascade and Separate Haar Feature. In ISPACS 2010 - 2010 International Symposium on Intelligent Signal Processing and Communication Systems, Proceedings [5704623] https://doi.org/10.1109/ISPACS.2010.5704623

Rapid face detection using a multi-mode cascade and Separate Haar Feature. / Jiang, Ning; Lu, Yijun; Tang, Shaopeng; Goto, Satoshi.

ISPACS 2010 - 2010 International Symposium on Intelligent Signal Processing and Communication Systems, Proceedings. 2010. 5704623.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Jiang, N, Lu, Y, Tang, S & Goto, S 2010, Rapid face detection using a multi-mode cascade and Separate Haar Feature. in ISPACS 2010 - 2010 International Symposium on Intelligent Signal Processing and Communication Systems, Proceedings., 5704623, 18th International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2010, Chengdu, 10/12/6. https://doi.org/10.1109/ISPACS.2010.5704623
Jiang N, Lu Y, Tang S, Goto S. Rapid face detection using a multi-mode cascade and Separate Haar Feature. In ISPACS 2010 - 2010 International Symposium on Intelligent Signal Processing and Communication Systems, Proceedings. 2010. 5704623 https://doi.org/10.1109/ISPACS.2010.5704623
Jiang, Ning ; Lu, Yijun ; Tang, Shaopeng ; Goto, Satoshi. / Rapid face detection using a multi-mode cascade and Separate Haar Feature. ISPACS 2010 - 2010 International Symposium on Intelligent Signal Processing and Communication Systems, Proceedings. 2010.
@inproceedings{27c6b9199e3246089561fbc2299eb755,
title = "Rapid face detection using a multi-mode cascade and Separate Haar Feature",
abstract = "In this paper, firstly, we describe a new feature for fast and accurate face detection. The feature is called Separate Haar Feature. Secondly, we describe a multi-mode detection algorithm to improve the detection rate. There are three key contributions. The first is {"}Separate Haar Feature{"}, which adds a don't-care area between the rectangles of Haar Feature. We can get some more efficient features by this algorithm. The second is the algorithm for selecting the best width for this don't-care area and the False Alarm Rate for each stage in {"}Learning{"}. This algorithm for width selecting is proposed to reduce the total number of learning features for reducing the memory used. And we use a smaller false alarm rate for each stage and less number of stages training the detector to improve the hit rate within the same detection time consuming. Finally, we proposed a multi-mode detection algorithm in cascade detection process to improve the detection rate.",
keywords = "Boost, Cascade, Multi-mode detection, Separate Haar Feature",
author = "Ning Jiang and Yijun Lu and Shaopeng Tang and Satoshi Goto",
year = "2010",
doi = "10.1109/ISPACS.2010.5704623",
language = "English",
isbn = "9781424473717",
booktitle = "ISPACS 2010 - 2010 International Symposium on Intelligent Signal Processing and Communication Systems, Proceedings",

}

TY - GEN

T1 - Rapid face detection using a multi-mode cascade and Separate Haar Feature

AU - Jiang, Ning

AU - Lu, Yijun

AU - Tang, Shaopeng

AU - Goto, Satoshi

PY - 2010

Y1 - 2010

N2 - In this paper, firstly, we describe a new feature for fast and accurate face detection. The feature is called Separate Haar Feature. Secondly, we describe a multi-mode detection algorithm to improve the detection rate. There are three key contributions. The first is "Separate Haar Feature", which adds a don't-care area between the rectangles of Haar Feature. We can get some more efficient features by this algorithm. The second is the algorithm for selecting the best width for this don't-care area and the False Alarm Rate for each stage in "Learning". This algorithm for width selecting is proposed to reduce the total number of learning features for reducing the memory used. And we use a smaller false alarm rate for each stage and less number of stages training the detector to improve the hit rate within the same detection time consuming. Finally, we proposed a multi-mode detection algorithm in cascade detection process to improve the detection rate.

AB - In this paper, firstly, we describe a new feature for fast and accurate face detection. The feature is called Separate Haar Feature. Secondly, we describe a multi-mode detection algorithm to improve the detection rate. There are three key contributions. The first is "Separate Haar Feature", which adds a don't-care area between the rectangles of Haar Feature. We can get some more efficient features by this algorithm. The second is the algorithm for selecting the best width for this don't-care area and the False Alarm Rate for each stage in "Learning". This algorithm for width selecting is proposed to reduce the total number of learning features for reducing the memory used. And we use a smaller false alarm rate for each stage and less number of stages training the detector to improve the hit rate within the same detection time consuming. Finally, we proposed a multi-mode detection algorithm in cascade detection process to improve the detection rate.

KW - Boost

KW - Cascade

KW - Multi-mode detection

KW - Separate Haar Feature

UR - http://www.scopus.com/inward/record.url?scp=79951736545&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79951736545&partnerID=8YFLogxK

U2 - 10.1109/ISPACS.2010.5704623

DO - 10.1109/ISPACS.2010.5704623

M3 - Conference contribution

SN - 9781424473717

BT - ISPACS 2010 - 2010 International Symposium on Intelligent Signal Processing and Communication Systems, Proceedings

ER -