Publication Details

AxMED: Formal Analysis and Automated Design of Approximate Median Filters using BDDs

MRáZEK Vojtěch and VAšíčEK Zdeněk. AxMED: Formal Analysis and Automated Design of Approximate Median Filters using BDDs. In: 2025 IEEE International Symposium on Circuits and Systems (ISCAS). London: Institute of Electrical and Electronics Engineers, 2025, pp. 1-5. ISBN 979-8-3503-5683-0.
Czech title
AxMED: Formální analýza a automatizovaný návrh přibližných mediánových filtrů pomocí BDD
Type
conference paper
Language
english
Authors
Keywords

approximate computing, median filters, design automation

Abstract

The increasing demand for energy-efficient solutions has led to the emergence of an approximate computing paradigm that enables power-efficient implementations in various application areas such as image and data processing. The median filter, widely used in image processing and computer vision, is of immense importance in these domains. We propose a systematic design methodology for the design of power-efficient median networks suitable for on-chip or FPGA-based implementations. A search-based design method is used to obtain approximate medians that show the desired trade-offs between accuracy, power consumption and area on chip. A new metric tailored to this problem is proposed to quantify the accuracy of approximate medians. Instead of the simple error rate, our method analyses the rank error. A significant improvement in implementation cost is achieved. For example, compared to the well-optimized high-throughput implementation of the exact 9-input median, a 30% reduction in area and a 36% reduction in power consumption was achieved by introducing an error by one position (i.e., allowing the 4th or 6th lowest input to be returned instead of the median).

Published
2025
Pages
1-5
Proceedings
2025 IEEE International Symposium on Circuits and Systems (ISCAS)
Conference
2025 IEEE International Symposium on Circuits and Systems, London, GB
ISBN
979-8-3503-5683-0
Publisher
Institute of Electrical and Electronics Engineers
Place
London, GB
DOI
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB13350,
   author = "Vojt\v{e}ch Mr\'{a}zek and Zden\v{e}k Va\v{s}\'{i}\v{c}ek",
   title = "AxMED: Formal Analysis and Automated Design of Approximate Median Filters using BDDs",
   pages = "1--5",
   booktitle = "2025 IEEE International Symposium on Circuits and Systems (ISCAS)",
   year = 2025,
   location = "London, GB",
   publisher = "Institute of Electrical and Electronics Engineers",
   ISBN = "979-8-3503-5683-0",
   doi = "10.1109/ISCAS56072.2025.11043775",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/13350"
}
Back to top