Oscillator Networks for Image Segmentation and Their Circuits Using Pulse Modulation Method
暂无分享,去创建一个
This paper proposes a modi ed model of the oscillator network, LEGION, suitable for VLSI implementation. The model performs gray-level real image segmentation using nonlinear analog dynamics. Because of the limited calculation precision in VLSI implementation, it is important to estimate the calculation precision required for proper operations in the modi ed model. By using numerical simulation, the necessary precision is estimated to be 5 bits. A new circuit technique using pulse-width/pulse-phase modulation (PWM/PPM) methods is proposed for implementing nonlinear dynamics. A nonlinear oscillator circuit, which is the most important part of LEGION, is proposed by using this technique. The basic operation of this circuit is con rmed by circuit simulation.
[1] Atsushi Iwata,et al. Nonlinear function generators and chaotic signal generators using a pulse-width modulation method , 1997 .
[2] DeLiang Wang,et al. Locally excitatory globally inhibitory oscillator networks , 1995, IEEE Transactions on Neural Networks.
[3] Makoto Nagata,et al. A concept of analog-digital merged circuit architecture for future VLSI's , 1996 .
[4] DeLiang Wang,et al. Image Segmentation Based on Oscillatory Correlation , 1997, Neural Computation.