基于卷积神经网络的手写体数字识别系统

A System of Convolutional Neural Networks Based Handwritten Number Recognition

摘要: 近年来, 卷积神经网络在图像的分类识别领域取得成功, 并逐渐在许多嵌入式终端设备上得到应用.在Linux环境下采用QT开发框架, 设计实现了一个基于卷积神经网络的手写体数字识别系统.该系统可以很方便的跨平台移植于各类嵌入式设备上.测试结果表明, 该系统对手写体识别具有良好的识别效果.

Abstract: In recent years, Convolutional Neural Network (CNN) has been successfully used in the field of image classification and recognition. In this paper, based on the QT development framework, we designed and implemented a handwritten numeral recognition system based on CNN in Linux environment. The proposed system can be easily transplanted on various embedded devices. The test results show that the system has good recognition effect.