Versatile Recognition Using Haarlike Feature And Cascaded Classifier

• doi: 10.1109/JSEN.2009.2038231
• title: Versatile Recognition Using Haar-Like Feature and Cascaded Classifier
• publisher: IEEE
• isbn:
• issn: 2379-9153
• rank: 3957
• access_type: LOCKED
• content_type: Journals
• 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 ¿-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 ¿W/fps. When the sensor is operated with a duty ratio of 1%, the power consumption is reduced to 28.5 ¿W.
• article_number: 5438924
• pdf_url: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5438924
• html_url: https://ieeexplore.ieee.org/document/5438924/
• abstract_url: https://ieeexplore.ieee.org/document/5438924/
• publication_title: IEEE Sensors Journal
• conference_location:
• conference_dates:
• publication_number: 7361
• is_number: 5437516
• publication_year: 2010
• publication_date: May 2010
• start_page: 942
• end_page: 951
• citing_paper_count: 14
• citing_patent_count: 0
• download_count: 1644
• insert_date: 20100325
• index_terms:
  • ieee_terms:
    • Image recognition
    • Emotion recognition
    • Speech recognition
    • Acceleration
    • Costs
    • Acoustic sensors
    • CMOS technology
    • Energy consumption
    • Signal processing
    • Band pass filters
  • author_terms:
    • Cascaded classifier
    • Haar-like feature
    • sensor networks
    • versatile recognition
  • dynamic_index_terms:
    • Haar-like Features
    • Haar Cascade
    • Cascade Classifier
    • Versatile Recognition
    • Low Cost
    • Computational Cost
    • Power Consumption
    • Temporal Dimension
    • Time Dimension
    • Temporal Properties
    • Integration Of Signals
    • Representative Methods
    • Representation Method
    • Sound Detection
    • Detection Alarm
    • Sound Recognition
    • Sound Categories
    • Sound Classification
    • Face Detection
    • CMOS Technology
    • Intermediate Representation
    • Acceleration Signal
    • Human Activity Recognition
    • Feature Values
    • Characteristic Values
    • Fast Fourier Transform
    • Inverse Fast Fourier Transform
    • Graphics Processing Unit
    • GPUs
    • Emotion Recognition
    • Image Recognition
    • Basic Patterns
    • Recognition Problem
    • Discrete Cosine Transform
    • Feature Pooling
    • Pool Characteristics
    • Speaker Recognition
    • Speaker Identity
    • Voice Activity
    • Speaker Verification
    • Voice Identity
    • Voice Control
    • Relative Accuracy
    • Emotion Categories
    • Emotion Classification
    • Local Wave
    • Temporal Signal
    • Gender Recognition
• authors:
  • Author Name: Jun Nishimura
    Affiliation: Department of Electrical Engineering, Keio University, Yokohama, Japan
    Author URL: https://ieeexplore.ieee.org/author/37407767900
    ID: 37407767900
    Order: 1
    Author Affiliations:
    • Department of Electrical Engineering, Keio University, Yokohama, Japan
  • Author Name: Tadahiro Kuroda
    Affiliation: Department of Electrical Engineering, Keio University, Yokohama, Japan
    Author URL: https://ieeexplore.ieee.org/author/37274599600
    ID: 37274599600
    Order: 2
    Author Affiliations:
    • Department of Electrical Engineering, Keio University, Yokohama, Japan

Image Sensor

• sensor_type: CMOS
• resolution: Not specified
• dynamic_range: Not specified
• pixel_size: Not specified
• dark_current: Not specified

Optical Data

• focal_length: Not specified
• aperture: Not specified
• field_of_view: Not specified
• distortion: Not specified

Performance Metrics

Applications & Benefits

• cell_imaging: Not specified
• benefits: Not specified

Supporting Organizations

• supported_by: Not specified

Manuscript Details

• publication_date: May 2010

Relevancy Score

• score: 1
• missing_fields:
  • pixel size
  • fill factor
  • quantum efficiency
  • dark current
  • signal-to-noise ratio
  • dynamic range
  • power consumption
  • focal length
  • aperture
  • field of view
  • distortion
  • frame rate
  • sensitivity
  • shutter speed
  • noise
  • cell imaging
  • benefits
  • supported by

Processed JSON Filename

request_26669c50-dea8-42d6-9f1f-210b422fa1a4-versatile_recognition_using_haarlike_feature_and_cascaded_classifier.json