FPGA based accelerated 3D affine transform for real-time image processing applications

• In the proposed algorithm, simultaneously 4 pixel/voxel locations can be transformed to compute AT of the entire image.
• The proposed architecture requires only relevant frames instead of all the frames simultaneously.
• The faster implementation of the affine transform is useful during image registration of the 3D bio-medical images.

Affine Transform (AT) is widely used in high-speed image processing systems. This transform plays an important role in various high-speed image processing applications. AT, an important process during the intensity-based image registration, is applied iteratively during the registration. This is also used for the analysis of the interior of an organ and to get a better view of the organs from various angles in 3D coordinate system. Hence, for real-time medical image registration and visualization of the acquired volumetric images, acceleration of AT is very much sought for. In this paper, a parallel and pipelined architecture of the proposed AT algorithm has been presented. This will accelerate the transform process and reduce the processing time of medical image registration. The architecture is mapped in Field-Programmable Gate Array (FPGA) for prototyping and verification. The results show that the computational complexity of the proposed parallel algorithm is almost 4 times better than that of the conventional algorithm.

Figure optionsDownload as PowerPoint slide