• Title/Summary/Keyword: normalized facial region extraction

Search Result 4, Processing Time 0.027 seconds

Normalized Region Extraction of Facial Features by Using Hue-Based Attention Operator (색상기반 주목연산자를 이용한 정규화된 얼굴요소영역 추출)

  • 정의정;김종화;전준형;최흥문
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.29 no.6C
    • /
    • pp.815-823
    • /
    • 2004
  • A hue-based attention operator and a combinational integral projection function(CIPF) are proposed to extract the normalized regions of face and facial features robustly against illumination variation. The face candidate regions are efficiently detected by using skin color filter, and the eyes are located accurately nil robustly against illumination variation by applying the proposed hue- and symmetry-based attention operator to the face candidate regions. And the faces are confirmed by verifying the eyes with the color-based eye variance filter. The proposed CIPF, which combines the weighted hue and intensity, is applied to detect the accurate vertical locations of the eyebrows and the mouth under illumination variations and the existence of mustache. The global face and its local feature regions are exactly located and normalized based on these accurate geometrical information. Experimental results on the AR face database[8] show that the proposed eye detection method yields better detection rate by about 39.3% than the conventional gray GST-based method. As a result, the normalized facial features can be extracted robustly and consistently based on the exact eye location under illumination variations.

Realtime Face Recognition by Analysis of Feature Information (특징정보 분석을 통한 실시간 얼굴인식)

  • Chung, Jae-Mo;Bae, Hyun;Kim, Sung-Shin
    • Proceedings of the Korean Institute of Intelligent Systems Conference
    • /
    • 2001.12a
    • /
    • pp.299-302
    • /
    • 2001
  • The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region of face candidate. The feature information in the region of the face candidate is used to detect the face region. In the recognition step, as a tested, the 120 images of 10 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression. Input variables of the neural networks are the geometrical feature information and the feature information that comes from the eigenface spaces. The simulation results of$.$10 persons show that the proposed method yields high recognition rates.

  • PDF

Realtime Face Recognition by Analysis of Feature Information (특징정보 분석을 통한 실시간 얼굴인식)

  • Chung, Jae-Mo;Bae, Hyun;Kim, Sung-Shin
    • Journal of the Korean Institute of Intelligent Systems
    • /
    • v.11 no.9
    • /
    • pp.822-826
    • /
    • 2001
  • The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region of face candidate. The feature information in the region of the face candidate is used to detect the face region. In the recognition step, as a tested, the 120 images of 10 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression. Input variables of the neural networks are the geometrical feature information and the feature information that comes from the eigenface spaces. The simulation results of 10 persons show that the proposed method yields high recognition rates.

  • PDF

Face Recognition Using Feature Information and Neural Network

  • Chung, Jae-Mo;Bae, Hyeon;Kim, Sung-Shin
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 2001.10a
    • /
    • pp.55.2-55
    • /
    • 2001
  • The statistical analysis of the feature extraction and the neural networks are proposed to recognize a human face. In the preprocessing step, the normalized skin color map with Gaussian functions is employed to extract the region efface candidate. The feature information in the region of face candidate is used to detect a face region. In the recognition step, as a tested, the 360 images of 30 persons are trained by the backpropagation algorithm. The images of each person are obtained from the various direction, pose, and facial expression, Input variables of the neural networks are the feature information that comes from the eigenface spaces. The simulation results of 30 persons show that the proposed method yields high recognition rates.

  • PDF