Fast bilateral filter for multichannel images via soft-assignment coding

Kenjiro Sugimoto, Norishige Fukushima, Seiichiro Kamata

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

This paper presents an acceleration method of the bilateral filter (BF) for multi-channel images. In most existing acceleration methods, the BF is approximated by an appropriate combination of convolutions. A major purpose under this framework is to achieve sufficient approximate accuracy by as few convolutions as possible. However, state-of-the-art methods for multi-channel images still requires hundreds of (e.g., 256) convolutions to achieve sufficient accuracy. The proposed method reduces the number of convolutions without a loss in accuracy via soft-assignment coding. This approach enables us to take two major advantages that two state-of-the-art methods (scalar quantization with linear interpolation and vector quantization) have individually provided. Experiments show that the proposed method can produce sufficiently-accurate resulting images by using 64-80 convolutions only.

Original languageEnglish
Title of host publication2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9789881476821
DOIs
Publication statusPublished - 2017 Jan 17
Event2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016 - Jeju, Korea, Republic of
Duration: 2016 Dec 132016 Dec 16

Other

Other2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016
CountryKorea, Republic of
CityJeju
Period16/12/1316/12/16

Fingerprint

Convolution
Vector quantization
Interpolation
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems
  • Signal Processing

Cite this

Sugimoto, K., Fukushima, N., & Kamata, S. (2017). Fast bilateral filter for multichannel images via soft-assignment coding. In 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016 [7820813] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APSIPA.2016.7820813

Fast bilateral filter for multichannel images via soft-assignment coding. / Sugimoto, Kenjiro; Fukushima, Norishige; Kamata, Seiichiro.

2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016. Institute of Electrical and Electronics Engineers Inc., 2017. 7820813.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sugimoto, K, Fukushima, N & Kamata, S 2017, Fast bilateral filter for multichannel images via soft-assignment coding. in 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016., 7820813, Institute of Electrical and Electronics Engineers Inc., 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016, Jeju, Korea, Republic of, 16/12/13. https://doi.org/10.1109/APSIPA.2016.7820813
Sugimoto K, Fukushima N, Kamata S. Fast bilateral filter for multichannel images via soft-assignment coding. In 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016. Institute of Electrical and Electronics Engineers Inc. 2017. 7820813 https://doi.org/10.1109/APSIPA.2016.7820813
Sugimoto, Kenjiro ; Fukushima, Norishige ; Kamata, Seiichiro. / Fast bilateral filter for multichannel images via soft-assignment coding. 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{3984b0320b604130b53d70b7e04c56c4,
title = "Fast bilateral filter for multichannel images via soft-assignment coding",
abstract = "This paper presents an acceleration method of the bilateral filter (BF) for multi-channel images. In most existing acceleration methods, the BF is approximated by an appropriate combination of convolutions. A major purpose under this framework is to achieve sufficient approximate accuracy by as few convolutions as possible. However, state-of-the-art methods for multi-channel images still requires hundreds of (e.g., 256) convolutions to achieve sufficient accuracy. The proposed method reduces the number of convolutions without a loss in accuracy via soft-assignment coding. This approach enables us to take two major advantages that two state-of-the-art methods (scalar quantization with linear interpolation and vector quantization) have individually provided. Experiments show that the proposed method can produce sufficiently-accurate resulting images by using 64-80 convolutions only.",
author = "Kenjiro Sugimoto and Norishige Fukushima and Seiichiro Kamata",
year = "2017",
month = "1",
day = "17",
doi = "10.1109/APSIPA.2016.7820813",
language = "English",
booktitle = "2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Fast bilateral filter for multichannel images via soft-assignment coding

AU - Sugimoto, Kenjiro

AU - Fukushima, Norishige

AU - Kamata, Seiichiro

PY - 2017/1/17

Y1 - 2017/1/17

N2 - This paper presents an acceleration method of the bilateral filter (BF) for multi-channel images. In most existing acceleration methods, the BF is approximated by an appropriate combination of convolutions. A major purpose under this framework is to achieve sufficient approximate accuracy by as few convolutions as possible. However, state-of-the-art methods for multi-channel images still requires hundreds of (e.g., 256) convolutions to achieve sufficient accuracy. The proposed method reduces the number of convolutions without a loss in accuracy via soft-assignment coding. This approach enables us to take two major advantages that two state-of-the-art methods (scalar quantization with linear interpolation and vector quantization) have individually provided. Experiments show that the proposed method can produce sufficiently-accurate resulting images by using 64-80 convolutions only.

AB - This paper presents an acceleration method of the bilateral filter (BF) for multi-channel images. In most existing acceleration methods, the BF is approximated by an appropriate combination of convolutions. A major purpose under this framework is to achieve sufficient approximate accuracy by as few convolutions as possible. However, state-of-the-art methods for multi-channel images still requires hundreds of (e.g., 256) convolutions to achieve sufficient accuracy. The proposed method reduces the number of convolutions without a loss in accuracy via soft-assignment coding. This approach enables us to take two major advantages that two state-of-the-art methods (scalar quantization with linear interpolation and vector quantization) have individually provided. Experiments show that the proposed method can produce sufficiently-accurate resulting images by using 64-80 convolutions only.

UR - http://www.scopus.com/inward/record.url?scp=85013813045&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013813045&partnerID=8YFLogxK

U2 - 10.1109/APSIPA.2016.7820813

DO - 10.1109/APSIPA.2016.7820813

M3 - Conference contribution

AN - SCOPUS:85013813045

BT - 2016 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -