基于卷积神经网络的图像信息识别系统设计  

Design of Image Information Recognition System Based on Convolutional Neural Network

作　　者：胡俊梅 HU Junmei(Xi’an Traffic Engineering Institute,Xi’an Shaanxi 710300,China)

机构地区：[1]西安交通工程学院,陕西西安710300

出　　处：《信息与电脑》2022年第13期178-180,共3页Information & Computer

摘　　要：针对传统图像信息识别系统在图像信息识别应用中误识率较高的现状,提出了基于卷积神经网络的图像信息识别系统的设计。在系统硬件方面,对中心交换机和加速器进行选型与设计;在系统软件方面,对图像数据进行灰度转换、灰度拉伸、滤波处理,并利用卷积神经网络技术对图像特征进行深度挖掘,以识别图像信息。测试实验结果表明,设计的系统误识率低于传统图像信息识别系统,具有较好的可行性与可靠性。Aiming at the high error rate of traditional image information recognition system in the application of image information recognition,a design of image information recognition system based on convolutional neural network is proposed.In terms of system hardware,the central switch and accelerator are selected and designed;in terms of system software,grayscale conversion,grayscale stretching and filtering are performed on image data,and convolutional neural network technology is used to deeply mine image features,identify.The image information is obtained to realize the system design.According to the test results,the error recognition rate of this design system is lower than the traditional image information recognition system,which has better feasibility and reliability.

关 键 词：卷积神经网络(CNN) 图像信息 中心交换机 加速器 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]