Presentation 2012-05-29
An Acceleration of a Graph Cut Segmentation with FPGA
Daichi KOBORI, Tsutomu MARUYAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose an FPGA implementation of the max-flow problem for the image segmentation by the graph cuts. The graph cuts is an effective method for the image segmentation, and can be solved efficiently as the max-flow problem. In our implementation, the push-relabel method and the gap relabeling are used in order to achieve high performance on FPGA. The performance gain compared with a software library on CPU is about 3-5.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) graph cut / segmentation / max-flow / FPGA
Paper # RECONF2012-1
Date of Issue

Conference Information
Committee AI
Conference Date 2012/5/22(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 Artificial Intelligence and Knowledge-Based Processing (AI)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Acceleration of a Graph Cut Segmentation with FPGA
Sub Title (in English)
Keyword(1) graph cut
Keyword(2) segmentation
Keyword(3) max-flow
Keyword(4) FPGA
1st Author's Name Daichi KOBORI
1st Author's Affiliation Systems and Information Engineering, University of Tsukuba()
2nd Author's Name Tsutomu MARUYAMA
2nd Author's Affiliation Systems and Information Engineering, University of Tsukuba
Date 2012-05-29
Paper # RECONF2012-1
Volume (vol) vol.112
Number (no) 70
Page pp.pp.-
#Pages 6
Date of Issue