基于TensorFlow的手写体数字识别  

Digital Recognition of Handwritten Numerals based on Tensorflow

作　　者：高春庚[1] 孙建国[1] Gao Chungeng;Sun Jianguo(Department of Information Engineering,Jiyuan Vocational and Technical College,Jiyuan 459000,China)

机构地区：[1]济源职业技术学院信息工程系,河南济源459000

出　　处：《洛阳师范学院学报》2022年第2期39-41,共3页Journal of Luoyang Normal University

摘　　要：手写体数字识别技术是模式识别领域研究的热点,而人工神经网络是人工智能领域的研究热点.本文将二者结合并利用TensorFlow技术,提出了一种基于TensorFlow的手写体数字识别技术.结果表明:该技术方法简单,识别率高,有一定的实用性.Technology of handwritten numeral recognition is a hotspot in field of researches on pattern recognition,while artificial neural network is in artificial intelligence.Combining the two and using Tensorflow technology,a technology of digital recognition of handwritten numerals based on Tensorflow is proposed.The results show that this technology is easy to use,efficient in recognition rate,reasonably practical.

关 键 词：TensorFlow 神经网络 手写体数字识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]