An Ultra-Fast, Optimized and Massively-Parallelized Curvelet Transform Algorithm on GP-GPUs
Publish place: 21th Iranian Conference on Electric Engineering
Publish Year: 1392
نوع سند: مقاله کنفرانسی
زبان: English
View: 1,429
This Paper With 6 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
ICEE21_735
تاریخ نمایه سازی: 27 مرداد 1392
Abstract:
The Curvelet transform is among one of the most powerful time-frequency representations of an image. However, since it is not a fast algorithm it cannot be employed in mostreal-time and/or large scale applications. This paper proposes a novel algorithm to speed up the Curvelet transform by bothoptimizing it for repetitive Curvelet usage and by massive parallelization. In this parallel algorithm we have reconfigured the structure of the Curvelet algorithm in a parallel format suitable for implementation on the GP-GPU. Experimental results prove the proposed algorithm to be ultra-fast without loss of accuracy
Keywords:
Authors
Mohammad Motamedi
High speed processing lab., Amirkabir University of Technology
Sima Sobhieh
AIMS lab., Amirkabir University of Technology
S. Ahmad Motamedi
Professor, EED, Amirkabir University of Technology