基于 SoC FPGA 的文字分割系统设计

摘要

In order to solve the problems of power consumption,portability,real-time and volume limitation of image acquisition and processing system based on PC,the text segmentation system based on SoC FPGA in-built hard-core ARM is designed.By co-design of hardware and software based on SoC FPGA hardware platform and embedded Linux development,the system realizes the image ac-quisition of the CMOS sensor,storage of SDRAM,data communication of two-port RAM and VGA display.In the meanwhile,ARM-based HPS controls dual-port RAM to read or write image data and the image preprocessing and watershed algorithm are implemented.Experimental results show that this system has the high accuracy of text segmentation and the real-time processing average speed of one image is 0.87 s,which is 0.84 and 4.52 times faster than that of PC-based MATLAB environment and SOPC system based on NIOS II respectively.This system has the advantages of flexibility,high speed and good portability and there is the real-time image acquisition and processing system.%针对于传统 PC 机实现的图像采集与处理系统在功耗、移植性、实时性和体积上的局限性问题,本设计实现了基于FPGA 和 ARM 硬核处理器整合的 SoC FPGA 的图像文字分割系统。基于 SoC FPGA 的硬件平台和移植的嵌入式Linux 开发环境的软硬协同设计方法,实现了 CMOS 传感器的图像采集、SDRAM 存储、双口 RAM 数据通信和 VGA 显示输出。同时,基于 ARM 的硬核处理系统(HPS)控制双口 RAM 读写图像数据,在 HPS 中实现图像的预处理和分水岭算法。实验结果表明：本系统具有较准确的文字分割效果,一幅图像实时文字分割的平均速度为0.87 s,比基于 PC 机的matlab 环境和 NIOS II 的 SOPC 系统上实现速度分别提高了0．84倍和4．52倍。本系统具有设计灵活,速度快、可移植性强的优点,对实时图像采集与处理系统的研究提供参考意义。