GLORIA

GEOMAR Library Ocean Research Information Access

Your email was sent successfully. Check your inbox.

An error occurred while sending the email. Please try again.

Proceed reservation?

Export
Filter
  • Wang, Yang  (3)
  • Comparative Studies. Non-European Languages/Literatures  (3)
Material
Person/Organisation
Language
Years
FID
Subjects(RVK)
  • Comparative Studies. Non-European Languages/Literatures  (3)
RVK
  • 1
    Online Resource
    Online Resource
    Acoustical Society of America (ASA) ; 2012
    In:  The Journal of the Acoustical Society of America Vol. 131, No. 4_Supplement ( 2012-04-01), p. 3447-3447
    In: The Journal of the Acoustical Society of America, Acoustical Society of America (ASA), Vol. 131, No. 4_Supplement ( 2012-04-01), p. 3447-3447
    Abstract: Ultrasonic human face recognition systems transmit ultrasonic Continuously Transmitted Frequency Modulated (CTFM) signal, extract facial geometry characteristic information from the received echo signals, and process the information for face recognition. Compared to vision-based approaches, ultrasonic human face recognition systems reduce the influence of illumination and avoid privacy leak. The existing approaches showed the feasibility of ultrasonic face recognition and achieved acceptable recognition accuracy. However, the aging problem, which equals to performance degradation caused by facial geometry change with time going on, is not considered in the previous researches. In this paper, robustness of the ultrasonic face recognition method to age variation is analysed. A database is built, in which each subject's face information was acquired at intervals of months during the last two years. Based on the database, various recognition experiments are conducted using the different pattern recognition algorithms. Aiming at the experimental results, the analysis to age factor that influences face recognition performance is implemented. The feature extraction methods and the pattern recognition algorithms are developed to increase the recognition rate.
    Type of Medium: Online Resource
    ISSN: 0001-4966 , 1520-8524
    RVK:
    Language: English
    Publisher: Acoustical Society of America (ASA)
    Publication Date: 2012
    detail.hit.zdb_id: 1461063-2
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 2
    Online Resource
    Online Resource
    Acoustical Society of America (ASA) ; 2012
    In:  The Journal of the Acoustical Society of America Vol. 131, No. 4_Supplement ( 2012-04-01), p. 3423-3423
    In: The Journal of the Acoustical Society of America, Acoustical Society of America (ASA), Vol. 131, No. 4_Supplement ( 2012-04-01), p. 3423-3423
    Abstract: Continuously Transmitted Frequency Modulated (CTFM) sonar transmits wideband acoustic signal, demodulates the echo signal, and calculates the target distance by acquiring the frequency of the demodulation output signal. Still objects can be accurately detected using CTFM sonar. However, moving target brings Doppler shift to the echo signal frequency, which makes the output signal frequency of CTFM sonar deviate from the accurate distance of the target. In this paper, a novel airborne sonar sensing approach is proposed. Using a modified transmitted signal, single moving target that appears in a static environment can be detected. Compared to traditional CTFM sonar, a single tone is added to the transmitted signal. The existence and radial velocity of a moving target can be calculated based on the single tone Doppler shift of the echo. Furthermore, the simultaneous kinematic information of the target can be extracted by the system algorithm. An experimental system is developed, and the result of experiments verified the feasibility of the approach.
    Type of Medium: Online Resource
    ISSN: 0001-4966 , 1520-8524
    RVK:
    Language: English
    Publisher: Acoustical Society of America (ASA)
    Publication Date: 2012
    detail.hit.zdb_id: 1461063-2
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
  • 3
    Online Resource
    Online Resource
    Acoustical Society of America (ASA) ; 2012
    In:  The Journal of the Acoustical Society of America Vol. 131, No. 4_Supplement ( 2012-04-01), p. 3447-3447
    In: The Journal of the Acoustical Society of America, Acoustical Society of America (ASA), Vol. 131, No. 4_Supplement ( 2012-04-01), p. 3447-3447
    Abstract: Unlike vision-based approaches, ultrasonic sensing systems have the ability to obtain the object distance and echo energy information. With the development of airborne ultrasonic detection, ultrasonic face recognition has been discussed. However, the existing ultrasonic face recognition systems store the echo waveform data and make processing and analysis afterwards. Seperated acquisition and analysis procedures make these systems non-realtime. In this paper, a realtime ultrasonic face recognition system is proposed. The system has the following functions: signal generation, transmitting, receiving, amplification, demodulation, spectral analysis, and feature extraction. A continuous wideband ultrasonic signal is transmitted, then the geometrical information can be extracted from the echo signal, and suitable pattern recognition methods are used to recognize human face. The system can implement realtime face recognition with ultrasonic sensing, and a considerable recognition rate is achieved.
    Type of Medium: Online Resource
    ISSN: 0001-4966 , 1520-8524
    RVK:
    Language: English
    Publisher: Acoustical Society of America (ASA)
    Publication Date: 2012
    detail.hit.zdb_id: 1461063-2
    Location Call Number Limitation Availability
    BibTip Others were also interested in ...
Close ⊗
This website uses cookies and the analysis tool Matomo. More information can be found here...