Image segmentation using linked mean-shift vectors for SIMD architecture

Hanjoo Cho, Sung In Cho, Young Hwan Kim

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

This paper presents a new mean-shift based segmentation algorithm for single instruction multiple data (SIMD) architecture. A standard mean-shift algorithm has different number of computations for each pixel because the endpoints of each pixel's iteration process are different, thus a standard mean-shift algorithm is hard to be accelerated using SIMD architecture. The proposed algorithm, however, equalizes the number of computations for each pixel by constructing links between pixels using their first mean-shift vectors without iteration process. It makes the proposed algorithm more suitable for the SIMD architecture without a complicated scheduling module. Experimental results using the Berkeley segmentation dataset show the proposed algorithm successfully equalizes the number of computations with reasonable segmentation quality.

Original languageEnglish
Title of host publication2014 IEEE International Conference on Consumer Electronics, ICCE 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages484-485
Number of pages2
ISBN (Print)9781479912919
DOIs
StatePublished - 2014
Event2014 IEEE International Conference on Consumer Electronics, ICCE 2014 - Las Vegas, NV, United States
Duration: 10 Jan 201413 Jan 2014

Publication series

NameDigest of Technical Papers - IEEE International Conference on Consumer Electronics
ISSN (Print)0747-668X

Conference

Conference2014 IEEE International Conference on Consumer Electronics, ICCE 2014
Country/TerritoryUnited States
CityLas Vegas, NV
Period10/01/1413/01/14

Fingerprint

Dive into the research topics of 'Image segmentation using linked mean-shift vectors for SIMD architecture'. Together they form a unique fingerprint.

Cite this