Skip to content
Free planNo credit card requiredStart writing

article · 2002

Analog VLSI arrays for morphological image processing

T.G. Morris, Stephen P. DeWeerth

Cited by 16Abstract and details only

Abstract

A two-dimensional analog VLSI array that performs basic morphological image processing operations is presented. The system uses a smart pixel approach that facilitates the parallel computation of continuous real-time outputs. Photodetectors within the array of smart pixels also allow for parallel optical inputs. The processing is performed by current-mode circuitry implemented with CMOS technology. The signal values are encoded as analog current values. The processing array uses local communication to perform the morphological operation known as dilation, and outputs the difference between the original input image and the dilation image to detect edges. The system was fabricated using a standard 2.0 /spl mu/m digital CMOS process. Example output data of the fabricated circuitry are presented.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Cite this paper

APA 7

Morris, T., & DeWeerth, S. P. (2002). Analog VLSI arrays for morphological image processing. https://doi.org/10.1109/asap.1994.331809

MLA 9

Morris, T.G., and Stephen P. DeWeerth. “Analog VLSI arrays for morphological image processing.” 2002, pp. 132–42, https://doi.org/10.1109/asap.1994.331809.

Chicago

Morris, T.G., and Stephen P. DeWeerth. 2002. “Analog VLSI arrays for morphological image processing.” https://doi.org/10.1109/asap.1994.331809.

Harvard

Morris, T. and DeWeerth, S.P. (2002) ‘Analog VLSI arrays for morphological image processing’. Available at: https://doi.org/10.1109/asap.1994.331809.

BibTeX
@article{morris2002analog,
  title = {{Analog VLSI arrays for morphological image processing}},
  author = {Morris, T.G. and DeWeerth, Stephen P.},
  pages = {132--142},
  year = {2002},
  doi = {10.1109/asap.1994.331809}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.