"This paper presents highly optimized implementation of image registration method that is invariant to rotation scale and translation. Image registration method using FFT works with comparable accuracy as similar methods proposed in the literature, but practical applications seldom use this technique because of high computational requirement. However, this method is highly parallelizable and offloading it to the commodity graphics cards increases its performance drastically. We are proposing the parallel implementation of FFT based registration method on CUDA and OpenCL. Performance analysis of this implementation suggests that the parallel version can be used for real time image registration even for image size up to 2k x 2k. We have achieved significant speed up of up to 345x on NVIDIA GTX 580 using CUDA and up to 116x on AMD HD 6950 using OpenCL. Comparison of our implementation with other GPU based registration method reveals that our implementation performs better compared to other implementations." . "9"^^ . "RIV/49777513:23520/12:43921647" . . . . . . . "23520" . "P(GBP103/12/G084)" . "Object Recognition; OpenCL; CUDA; Image Registration; GPU"@en . . . "10.1007/978-3-642-31295-3_27" . "Wasnik, Ratul" . . "2012-06-25+02:00"^^ . "GPU Accelerated Real Time Rotation, Scale and Translation Invariant Image Registration Method"@en . "978-3-642-31294-6" . "GPU Accelerated Real Time Rotation, Scale and Translation Invariant Image Registration Method" . "Sah, Sudhakar" . . "138334" . . . "GPU Accelerated Real Time Rotation, Scale and Translation Invariant Image Registration Method" . . "0302-9743" . . . "Van\u011Bk, Jan" . "http://www.springerlink.com/content/985306314uq284g1/fulltext.pdf" . "[A4647406FA50]" . "4"^^ . "Portugalsko" . "Berlin Heidelberg" . "Lecture Notes in Computer Science" . . "RIV/49777513:23520/12:43921647!RIV14-GA0-23520___" . . "This paper presents highly optimized implementation of image registration method that is invariant to rotation scale and translation. Image registration method using FFT works with comparable accuracy as similar methods proposed in the literature, but practical applications seldom use this technique because of high computational requirement. However, this method is highly parallelizable and offloading it to the commodity graphics cards increases its performance drastically. We are proposing the parallel implementation of FFT based registration method on CUDA and OpenCL. Performance analysis of this implementation suggests that the parallel version can be used for real time image registration even for image size up to 2k x 2k. We have achieved significant speed up of up to 345x on NVIDIA GTX 580 using CUDA and up to 116x on AMD HD 6950 using OpenCL. Comparison of our implementation with other GPU based registration method reveals that our implementation performs better compared to other implementations."@en . "GPU Accelerated Real Time Rotation, Scale and Translation Invariant Image Registration Method"@en . . "Springer-Verlag" . "1"^^ . . "Roh, YoungJun" .