Real-time binary shape matching system based on FPGA

In this paper, we propose a simple binary shape matching algorithm and its hardware implementation. A shape matching algorithm is a method to measure the similarity of objects in an image. This technology is generally used in image retrieval, inspection, and object detection. The proposed method uses a transformation matrix that handles translation, rotation, and scaling. With a combined transformation matrix, we can easily obtain the transformed image and compare with this transform image and pattern image. After examination of the basic algorithm, we consider the hardware perspective. We analyze the difference between the software and hardware implementations and present revision factors for hardware implementation. Finally, we propose a dedicated hardware binary matching system. It is implemented on a field programmable gate array (FPGA) using the VHSIC hardware description language (VHD). The implementation is evaluated using experimental result and a device utilization summary.