摘要
针对指纹图像核心区域方向变化剧烈及用软件实现图像增强速度慢的缺点,提出了一种适应于硬件并行处理的基于改进的Gabor滤波的指纹图像增强算法,并用硬件描述语言在可编程逻辑门阵列(FPGA)上实现,同时介绍了系统的工作过程及总体结构。实验结果表明,改进的Gabor滤波能使图像的断裂处得到很好的连接,指纹图像信息明显增强,并且在速度方面利用硬件实现远远高于软件。实验表明,FPGA在图像处理方面满足实时性的要求,适用于图像增强的系统。
The orientation in core region of fingerprint image changed acutely. The speed is very slow when using software to realize image enhancement algorithm. In view of these shortcomings, an algorithm of fingerprint image enhancement is presented based on the improved Gabor filter which is adapted to parallel processing on hardware, and the Gabor filter on FPGA is realized using hardware description language. The work process of system and overall structure are presented. The experimental result indicates that the improved Gabor filter can make the broken point of fingerprint image connected commendably and the information of fingerprint image is enhanced greatly. In the aspect of speed, it is more quickly using FPGA to realize the algorithm than using software. The experiment proves that FPGA can meet the request of real time and is fit for the system of image process.
出处
《计算机工程与设计》
CSCD
北大核心
2008年第18期4743-4745,共3页
Computer Engineering and Design
