Object-Based Analog VLSI Vision Circuits
Abstract
We describe two successfully working, analog VLSI vision circuits that move beyond pixel-based early vision algorithms. One circuit, implementing the dynamic wires model, provides for dedicated lines of communication among groups of pixels that share a common property. The chip uses the dynamic wires model to compute the arclength of visual contours. Another circuit labels all points inside a given contour with one voltage and all other with another volt(cid:173) age. Its behavior is very robust, since small breaks in contours are automatically sealed, providing for Figure-Ground segregation in a noisy environment. Both chips are implemented using networks of resistors and switches and represent a step towards object level processing since a single voltage value encodes the property of an ensemble of pixels.
Cite
Text
Koch et al. "Object-Based Analog VLSI Vision Circuits." Neural Information Processing Systems, 1992.Markdown
[Koch et al. "Object-Based Analog VLSI Vision Circuits." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/koch1992neurips-objectbased/)BibTeX
@inproceedings{koch1992neurips-objectbased,
title = {{Object-Based Analog VLSI Vision Circuits}},
author = {Koch, Christof and Mathur, Binnal and Liu, Shih-Chii and Harris, John G. and Luo, Jin and Sivilotti, Massimo},
booktitle = {Neural Information Processing Systems},
year = {1992},
pages = {828-835},
url = {https://mlanthology.org/neurips/1992/koch1992neurips-objectbased/}
}