Time effectiveness optimization of cross correlation methods for ocr systems with the use of graphics processing units

• Autorzy: Wieloch K. , Stokfiszewski K.
• Języki publikacji: EN

Abstrakty

EN

In this paper authors propose a time optimization of fast normalized cross corrlation methods for image processing and optical character recognition with the use of parallel computing techniques realized on graphics processing units (GPU). It is shown that suitable modification of the wellknown formulas and their parallel implementation on graphics processing units may substantially accelerate computing time without any change of the quality of results. The performed research include comparative analysis of time efficiency of the developed methods with respect to their standard sequential implementations.

Słowa kluczowe

EN

correlation methods; GPU; image processing; character recognition; parallel computing

PL

metody korelacji; GPU; przetwarzanie obrazu; rozpoznawanie znaków; obliczenia równoległe

• Wydawca: Wydawnictwo Politechniki Łódzkiej
• Czasopismo: Journal of Applied Computer Science
• Rocznik: 2015
• Tom: Vol. 23, nr 2
• Strony: 79--100
• Opis fizyczny: Bibliogr. 16 poz.

Twórcy

autor

Wieloch K.

• Lodz University of Technology, Institute of Information Technology, Wólczańska 215, 90-924 Łódź, Poland

autor

Stokfiszewski K.

• Lodz University of Technology, Institute of Information Technology, Wólczańska 215, 90-924 Łódź, Poland

Bibliografia

• [1] Sanders J., Kandrod E. (2012) CUDA w przykładach. Wprowadzenie do ogólnego programowania procesorów GPU. Helion, Gliwice.
• [2] [2015-01-12] NVIDIA graphics cards comparison http://www.nvidia.pl/object/geforce-desktop-graphics-cards-pl
• [3] Szymczyk T. (2008) Metoda dopasowania wzorców w rozpoznawaniu obrazów - ograniczenia, problemy i modyfikacje metody http://journals.bg.agh.edu.pl/AUTOMATYKA/2008-02/Auto23.pdf
• [4] Szabatin J. (2015) Podstawy teorii sygnałów. WKŁ, Warszawa.
• [5] [2016-01-06] Levis J. P. Fast Normalized Cross-Correlation http://scribblethink.org/Work/nvisionInterface/nip.html
• [6] [2016-01-08] CUDA Programming Guide http://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html
• [7] [2016-01-06] How Good Can It Get? Analysing and Improving OCR Accuracy in Large Scale Historic Newspaper Digitisation Programs http://www.dlib.org/dlib/march09/holley/03holley.html
• [8] [2016-01-06] Optical Character Recognition http://www.explainthatstuff.com/how-ocr-works.html
• [9] McClanahan C. (2010) Artykuł: Ewolucja układów graficznych. http://mcclanahoochie.com/blog/wp-content/uploads/2011/03/ gpu-hist-paper.pdf
• [10] [2016-01-06] Blaise B. (2014) Introduction to Parallel Computing https://computing.llnl.gov/tutorials/parallel_comp
• [11] [2016-01-06] Czym są obliczenia na GPU? http://www.nvidia.pl/object/gpu-computing-pl.html
• [12] [2015-01-12] What is OCR? http://www.dataid.com/aboutocr.htm
• [13] [2016-01-06] Form processing - CMS Software http://www.cmssoft.co.uk/pages/form_processing.html
• [14] [2016-01-08] OpenCL https://developer.nvidia.com/opencl
• [15] [2016-01-08] CUDA GPUs architecture https://developer.nvidia.com/cuda-gpus
• [16] [2016-01-06] Obliczenia równoległe CUDA http://www.nvidia.pl/object/cuda-parallel-computing-pl.html