OCR 是一种文字自动识别技术,能够将图像中的文字输入到计算机中,属于非键盘输入范畴,使用到的图像输入设备主要是扫描仪。本文探讨了印刷体英文 OCR 的实现过程。通过对图像预处理,字符分割,字符识别三个主要模块的分析,使用了便于初学者理解的算法来实现各模块的功能。设计清晰,实现简单,而且具有较快的识别速度和可接受的准确率。%OCR is an automatic text recognition technology,which could input the text in the image into the computer. OCR can be attributed to non -keyboard input areas,using the image input device is mainly scanner.This paper discusses the implementation process of the OCR printed in English.Through the image preprocessing,character segmentation,char-acter recognition analysis of three main modules,the algorithm easy for beginners to understand is used to achieve the func-tion of each module.The design is clear,simple,and has a faster recognition speed and acceptable accuracy.
展开▼