The rate is 100% to print digits, more than 98% to the handwritten digits.
对于印刷体数字的识别率达到了100%，对于手写体数字的识别也达到了98%以上。
This paper discusses how to design and develop a system for recognition of handwritten digits.
本文论述并设计实现了一个手写体数字识别系统。
In this paper we give a kind of handwritten digits recognition method based on BP neural network.
本文主要研究BP神经网络在脱机手写体数字识别方面的应用。
Most of the neural network handwritten digits recognition systems adopt a net - work with single structure.
用神经网络识别手写体数字，大多数采用的是单个的神经网络结构。
Fuzzy feature extraction and block design feedforward networks are employed to recognize handwritten digits.
将模糊特征提取技术与区组设计前馈网络相结合用于手写体数字识别。
Finally coarse classification and precise classification are separately carried out in handwritten digits recognition.
最后在对手写数字进行识别时，先进行粗分类再进行细分类。
The result of experiment shows high recognition rate, which indicates that the method can effectively classify handwritten digits and be put into practical use.
实验证明该方法有很高的识别率，能够有效地进行手写数字的分类，可以满足实际应用。
We'll learn the core principles behind neural networks and deep learning by attacking a concrete problem: the problem of teaching a computer to recognize handwritten digits.
我们通过解决一个具体的问题：交计算机识别手写数字，来学习神经网络与深度学习后面的核心理念。
This paper combines the two aspects to recognize handwritten digits by using wavelet transform to extract feature and Adaptive Resonance Theory (ART) Neural Networks for Classification.
本文将二者结合起来，用小波变换抽取特征、用自适应共振art网络作模式分类器来识别手写数字。
This paper combines the two aspects to recognize handwritten digits by using wavelet transform to extract feature and Adaptive Resonance Theory (ART) Neural Networks for Classification.
本文将二者结合起来，用小波变换抽取特征、用自适应共振art网络作模式分类器来识别手写数字。
应用推荐