Versatile recognition using haar-like feature and cascaded classifier

Jun Nishimura, Tadahiro Kuroda

Research output: Contribution to journalArticle

13 Citations (Scopus)

Abstract

This paper describes a world first versatile recognition algorithm suitable for processing images, sound and acceleration signals simultaneously with extremely low calculation cost while maintaining high recognition rates. There are three main contributions. The first is the introduction of a versatile recognition using Haar-like feature for images, sound and acceleration signals. The novel 1-D Haar-like features are proposed as very rough band pass filters for signals in temporal dimension. The second is a content-aware classifier which is based on the cascaded classifier and positive estimation. The cascaded classifier with positive estimation is introduced to allow a sensor node to computes finely only when the inputs are target-like and difficult to recognize, and stop computing when inputs obtain enough confidence. The third is a method of intermediate signal representation called Integral Signals and Δ-Integral Signals for calculation cost reduction in Haar-like feature based recognition. In this paper, the proposed recognition is experimented for a variety of sound recognition applications such as speech/non-speech, gender, speaker, emotion, and environmental sounds recognition. The preliminary results on human activity recognition and face detection are also given to show the versatility. The proposed algorithm yields sound recognition performance comparable to the conventional state-of-art method called MFCC while 96%99% efficient in terms of the total amount of add and multiply operations. The proposed algorithm is evaluated with a versatile recognition processor implemented in 90-nm CMOS technology. For speech/nonspeech classification on 8-kHz 8-bit sound, the power consumption per frame rate is 0.28 μW/fps. When the sensor is operated with a duty ratio of 1%, the power consumption is reduced to 28.5 μW.

Original languageEnglish
Article number5438924
Pages (from-to)942-951
Number of pages10
JournalIEEE Sensors Journal
Volume10
Issue number5
DOIs
Publication statusPublished - 2010

Fingerprint

classifiers
Classifiers
Acoustic waves
acoustics
Electric power utilization
Face recognition
Cost reduction
Bandpass filters
Sensor nodes
emotions
Image processing
cost reduction
sensors
versatility
bandpass filters
Sensors
image processing
central processing units
confidence
CMOS

Keywords

  • Cascaded classifier
  • Haar-like feature
  • Sensor networks
  • Versatile recognition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Instrumentation

Cite this

Versatile recognition using haar-like feature and cascaded classifier. / Nishimura, Jun; Kuroda, Tadahiro.

In: IEEE Sensors Journal, Vol. 10, No. 5, 5438924, 2010, p. 942-951.

Research output: Contribution to journalArticle

@article{12905c8dbfb44e06a2a0c90e249aba2e,
title = "Versatile recognition using haar-like feature and cascaded classifier",
abstract = "This paper describes a world first versatile recognition algorithm suitable for processing images, sound and acceleration signals simultaneously with extremely low calculation cost while maintaining high recognition rates. There are three main contributions. The first is the introduction of a versatile recognition using Haar-like feature for images, sound and acceleration signals. The novel 1-D Haar-like features are proposed as very rough band pass filters for signals in temporal dimension. The second is a content-aware classifier which is based on the cascaded classifier and positive estimation. The cascaded classifier with positive estimation is introduced to allow a sensor node to computes finely only when the inputs are target-like and difficult to recognize, and stop computing when inputs obtain enough confidence. The third is a method of intermediate signal representation called Integral Signals and Δ-Integral Signals for calculation cost reduction in Haar-like feature based recognition. In this paper, the proposed recognition is experimented for a variety of sound recognition applications such as speech/non-speech, gender, speaker, emotion, and environmental sounds recognition. The preliminary results on human activity recognition and face detection are also given to show the versatility. The proposed algorithm yields sound recognition performance comparable to the conventional state-of-art method called MFCC while 96{\%}99{\%} efficient in terms of the total amount of add and multiply operations. The proposed algorithm is evaluated with a versatile recognition processor implemented in 90-nm CMOS technology. For speech/nonspeech classification on 8-kHz 8-bit sound, the power consumption per frame rate is 0.28 μW/fps. When the sensor is operated with a duty ratio of 1{\%}, the power consumption is reduced to 28.5 μW.",
keywords = "Cascaded classifier, Haar-like feature, Sensor networks, Versatile recognition",
author = "Jun Nishimura and Tadahiro Kuroda",
year = "2010",
doi = "10.1109/JSEN.2009.2038231",
language = "English",
volume = "10",
pages = "942--951",
journal = "IEEE Sensors Journal",
issn = "1530-437X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

TY - JOUR

T1 - Versatile recognition using haar-like feature and cascaded classifier

AU - Nishimura, Jun

AU - Kuroda, Tadahiro

PY - 2010

Y1 - 2010

N2 - This paper describes a world first versatile recognition algorithm suitable for processing images, sound and acceleration signals simultaneously with extremely low calculation cost while maintaining high recognition rates. There are three main contributions. The first is the introduction of a versatile recognition using Haar-like feature for images, sound and acceleration signals. The novel 1-D Haar-like features are proposed as very rough band pass filters for signals in temporal dimension. The second is a content-aware classifier which is based on the cascaded classifier and positive estimation. The cascaded classifier with positive estimation is introduced to allow a sensor node to computes finely only when the inputs are target-like and difficult to recognize, and stop computing when inputs obtain enough confidence. The third is a method of intermediate signal representation called Integral Signals and Δ-Integral Signals for calculation cost reduction in Haar-like feature based recognition. In this paper, the proposed recognition is experimented for a variety of sound recognition applications such as speech/non-speech, gender, speaker, emotion, and environmental sounds recognition. The preliminary results on human activity recognition and face detection are also given to show the versatility. The proposed algorithm yields sound recognition performance comparable to the conventional state-of-art method called MFCC while 96%99% efficient in terms of the total amount of add and multiply operations. The proposed algorithm is evaluated with a versatile recognition processor implemented in 90-nm CMOS technology. For speech/nonspeech classification on 8-kHz 8-bit sound, the power consumption per frame rate is 0.28 μW/fps. When the sensor is operated with a duty ratio of 1%, the power consumption is reduced to 28.5 μW.

AB - This paper describes a world first versatile recognition algorithm suitable for processing images, sound and acceleration signals simultaneously with extremely low calculation cost while maintaining high recognition rates. There are three main contributions. The first is the introduction of a versatile recognition using Haar-like feature for images, sound and acceleration signals. The novel 1-D Haar-like features are proposed as very rough band pass filters for signals in temporal dimension. The second is a content-aware classifier which is based on the cascaded classifier and positive estimation. The cascaded classifier with positive estimation is introduced to allow a sensor node to computes finely only when the inputs are target-like and difficult to recognize, and stop computing when inputs obtain enough confidence. The third is a method of intermediate signal representation called Integral Signals and Δ-Integral Signals for calculation cost reduction in Haar-like feature based recognition. In this paper, the proposed recognition is experimented for a variety of sound recognition applications such as speech/non-speech, gender, speaker, emotion, and environmental sounds recognition. The preliminary results on human activity recognition and face detection are also given to show the versatility. The proposed algorithm yields sound recognition performance comparable to the conventional state-of-art method called MFCC while 96%99% efficient in terms of the total amount of add and multiply operations. The proposed algorithm is evaluated with a versatile recognition processor implemented in 90-nm CMOS technology. For speech/nonspeech classification on 8-kHz 8-bit sound, the power consumption per frame rate is 0.28 μW/fps. When the sensor is operated with a duty ratio of 1%, the power consumption is reduced to 28.5 μW.

KW - Cascaded classifier

KW - Haar-like feature

KW - Sensor networks

KW - Versatile recognition

UR - http://www.scopus.com/inward/record.url?scp=77950310788&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950310788&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2009.2038231

DO - 10.1109/JSEN.2009.2038231

M3 - Article

AN - SCOPUS:77950310788

VL - 10

SP - 942

EP - 951

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

SN - 1530-437X

IS - 5

M1 - 5438924

ER -