Presentation 1997/1/24
Real-time Morphology Processing using Highly-parallel 2D Cellular Automata CAM^2
Takeshi IKENAGA, Takeshi OGURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Mathematical morphology has many applications for image processing. However there are no compact, practical computers. This paper proposes a morphology processing method based on a highly-parallel 2D cellular automata called CAM^2 that can attain pixel-order parallelism on a single PC board. New data transfer method enables morphology processing with large and complex structuring elements (SEs). Evaluation results show that CAM^2 can perform more than a thousand dilation operations for various SEs at video rates. And it can perform multiple object tracking through a combination of morphology and other CA-based algorithm. CAM^2 is a promising platform for processing morphology.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) cellular automata / CAM / highly-parallel / real-time image processing / morphology
Paper # PRMU96-143
Date of Issue

Conference Information
Committee PRMU
Conference Date 1997/1/24(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Real-time Morphology Processing using Highly-parallel 2D Cellular Automata CAM^2
Sub Title (in English)
Keyword(1) cellular automata
Keyword(2) CAM
Keyword(3) highly-parallel
Keyword(4) real-time image processing
Keyword(5) morphology
1st Author's Name Takeshi IKENAGA
1st Author's Affiliation NTT System Electronics Laboratories()
2nd Author's Name Takeshi OGURA
2nd Author's Affiliation NTT System Electronics Laboratories
Date 1997/1/24
Paper # PRMU96-143
Volume (vol) vol.96
Number (no) 492
Page pp.pp.-
#Pages 8
Date of Issue