Shape from Focus Using Multilayer Feedforward Neural Networks
スポンサーリンク
概要
- 論文の詳細を見る
The conventional shape from focus(SFF) methods have inaccuracies because of piecewise constant approximation of the focused image surface(FIS). We propose a more accurate scheme for SFF based on representation of three-dimensional FIS in terms of neural network weights. The neural networks are trained to learn the shape of the FIS that maximizes the focus measure.
- 社団法人電子情報通信学会の論文
- 2000-04-25
著者
-
Choi T‐s
Kwangju Inst. Sci. And Technol. Gwangju Kor
-
Choi Tae-sun
Department Of Mechatronics Kjist
-
ASIF Muhammad
The authors are with the Department of Mechatronics, Kwangju Institute of Science and Technology
-
CHOI Tae-Sun
The authors are with the Department of Mechatronics, Kwangju Institute of Science and Technology
-
Choi Tae-sun
The Authors Are With The Department Of Mechatronics Kwangju Institute Of Science And Technology
-
Asif M
Kwangju Inst. Sci. And Technol. Gwangju Kor
関連論文
- Shape from Focus Using Multilayer Feedforward Neural Networks
- Histogram Based Chain Codes for Shape Description
- Fast Motion Estimation Techniques with Adaptive Variable Search Range (Special Section of Papers Selected from ITC-CSCC '98)
- Histogram Based Chain Codes for Shape Description(Multimedia Systems)
- Depth from Defocus Using Wavelet Transform
- A New Approach to 3-D Profilometry for the White Light Interferometric (WLI)
- Depth from Defocus Using Wavelet Transform (Image Processing, Image Pattern Recognition)
- Motion Estimation Based on Chain Code and Dynamic Programming(Fundamental Theories)
- Sampling Low Significance Bits Image to Reduce Quantized Bit Rate(Image Processing and Video Processing)
- List Based Zerotree Wavelet Image Coding with Two Symbols
- List Based Zerotree Wavelet Image Coding with Two Symbols (Image Processing, Image Pattern Recognition)