Abstract: Template matching based on Normalized Cross-Correlation（NCC） measure has found application in a broad range of image processing. The ridge of the NCC results can be sharpened for the template matching with image after edge detection through taking full advantage of the image space correlation. To improve the localization accuracy, and to meet the requirements for real-time, space constraints and flexible adaption to different mission phases with different image matching strategies in missile automatic target recognition, combined with the Sobel edge detection, an improved high-speed parallel architecture for real-time implementation of template matching with NCC, using Field Programmable Gate Array（FPGA） is proposed. In this architecture, several novel efficient approaches are proposed to reduce logic resource usage and computation time. A comparative study of the template matching before and after image edge detection has shown that image edge detection can sharpen the ridge of the NCC results. Function and timing simulation and practical experiment for automatic target recognition applied in infrared missile guidance system have shown that this architecture can effectively improve the speed performance of the practical system with little extra computation time. The hardware implementation based on FPGA can reduce the system size.