教師著作

Permanent URI for this collectionhttp://rportal.lib.ntnu.edu.tw/handle/20.500.12235/31266

Browse

Author: search.filters.author.Yeh, Zong-MuSubject: search.filters.subject.Fuzzy logic classification

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Contrast compensation for back-lit and front-lit color face images via fuzzy logic classification and image illumination analysis
    (2008-07-12) Tsai, Chun-Ming; Yeh, Zong-Mu; Wang, Yuan-Fang
    Conventional contrast enhancement methods have two shortcomings. First, most of them do not produce satisfactory enhancement results for face images with back-lit or front-lit. Second, most of them need transformation functions and parameters which are specified manually. Thus, this paper proposes an automatic and parameter-free contrast compensation algorithm for color face images. This method includes: RGB color space is transformed to YIQ color space. Fuzzy logic is used to classify the color images into back-lit, normal-lit, and front-lit categories. Image illumination analysis is used to analyze the image distribution. The input image is compensated by piecewise linear based compensation method. Finally, the compensation image is transformed back to RGB color space. This novel compensation method is automatic and parameter-free. Our experiments included back-lit and front-lit images. Experiment results show that the performance of the proposed method is better than other available methods in visual perception measurements.
  • No Thumbnail Available
    Item
    Contrast Compensation for Back-lit and Front-lit Color Face Image via Fuzzy Logic Classification and Image Illumination Analysis
    (Institute of Electrical and Electronics Engineers (IEEE), 2008-07-12) Tsai, Chun-Ming; Yeh, Zong-Mu; Wang, Yuan-Fang
    Conventional contrast enhancement methods have two shortcomings. First, most of them do not produce satisfactory enhancement results for face images with back-lit or front-lit. Second, most of them need transformation functions and parameters which are specified manually. Thus, this paper proposes an automatic and parameter-free contrast compensation algorithm for color face images. This method includes: RGB color space is transformed to YIQ color space. Fuzzy logic is used to classify the color images into back-lit, normal-lit, and front-lit categories. Image illumination analysis is used to analyze the image distribution. The input image is compensated by piecewise linear based compensation method. Finally, the compensation image is transformed back to RGB color space. This novel compensation method is automatic and parameter-free. Our experiments included back-lit and front-lit images. Experiment results show that the performance of the proposed method is better than other available methods in visual perception measurements.
  • No Thumbnail Available
    Item
    Contrast compensation by fuzzy classification and image illumination analysis for back-lit and front-lit color face images.
    (Institute of Electrical and Electronics Engineers (IEEE), 2010-08-01) Tsai, Chun-Ming; Yeh, Zong-Mu
    Conventional contrast enhancement methods have two shortcomings. First, most of them do not produce satisfactory enhancement results for face images with back-lit or front-lit. Second, most of them need transformation functions and parameters which are specified manually. Thus, this paper proposes an automatic and parameter-free contrast compensation algorithm for skin detection in color face images. This method includes following steps: First, RGB color space is transformed to YIQ color space. Second, fuzzy logic is used to classify the color images into three categories: back-lit, normal-lit, and front-lit. Third, image illumination analysis is used to analyze the image distribution. Fourth, the input image is compensated by piecewise linear based enhancement method. Finally, the compensation image is transformed back to RGB color space. Our experiments included various color and gray face images. Experiment results show that the performance of the proposed compensation method is better than other available methods in skin detection and visual perception measurements.