论文信息 - Gaussian Convolution Analog CMOS Network For 2D Images

Gaussian Convolution Analog CMOS Network For 2D Images

The design of an analog CMOS LSI is presented, that contains a matrix of photoreceptors and a network of posi- tive and negative resistors, capable of performing a 2D Gaussian convolution on a 6Ox6O sampled image in less than 2@is. Details of circuits in a conventional 2/spl mu/m CMOS technology are given, along with simulated performance.

H. Kobayashi | J.L. White | A.A. Abidi

[1] R. L. Stermer,et al. Design And Performance Of Blocked-Impurity-Band Detector Focal Plane Arrays , 1986, Optics & Photonics.

[2] Misha Mahowald,et al. A silicon model of early visual processing , 1993, Neural Networks.

[3] Andrew P. Witkin,et al. Uniqueness of the Gaussian Kernel for Scale-Space Filtering , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4] R. W. Brodersen,et al. Architectures and design techniques for real-time image-processing IC's , 1987 .

[5] S.G. Chamberlain,et al. A novel wide dynamic range silicon photodetector and linear imaging array , 1984, IEEE Journal of Solid-State Circuits.

[6] Carver A. Mead. A Sensitive Electronic Photoreceptor , 1985 .

[7] Alan L. Yuille,et al. A regularized solution to edge detection , 1985, J. Complex..