基于BP神经网络手写识别技术的研究.doc

摘要 手写数字识别技术是当今社会研究的热点问题，介于手写数字识别近几年来广泛应用社会的各个领域，越来越多的学者对手写数字识别进行了研究。神经网络由于其具有高度的并行结构和并行处理能力，以及固有的非线性特性和自学习、自组织、自适应能力等，被广泛应用到人工智能、模式识别等领域。本文将BP 神经网络应用到手写数字识别中，并利用Visual C++6.0 进行编程对手写数字识别技术进行了实现，实验结果表明该方法具有较好的效果。 手写数字识别在很多领域具有广泛的应用前景，国内外学者对此做了大量的研究工作，提出了很多预处理和模式识别的算法，大大提高了手写数字的识别精度。但到目前为止，手写数字识别的识别精度还有待提高，核函数核参数选择等问题尚有待解决。 本文基于BP神经网络理论,对手写体字符(包括l0个阿拉伯数字和大小写52个英文字母)识别工作进行了深入的研究。使BP神经网络方法实现模式识别，可处理一些环境信息十分复杂、背景知识不清楚、推理规则不明确的问题，允许样品有较大的缺损、畸变。目前用于文字识别的人工神经网络模型还有： Hopfield神经网络、ART网络、自组织特征映射网络、认知器模型等等。目前，人们还在研究将神经网络方法和传统的识别方法结合起来使用，互相取长补短。 关键词：BP神经网络；数字识别；模式识别；函数；手写数字识别；编程 Abstract Handwritten numeral recognition technology is a hot issue in society today, ranging widely in recent years should be handwritten numeral recognition with all areas of society, and more and more scholar’s handwritten numeral recognition has been studied. Neural network because of its high parallel structures and parallel processing capabilities, and the inherent nonlinear characteristics and self-learning, self-organizing, adaptive ability, are widely used in artificial intelligence, pattern recognition and other fields. This article BP neural network applied to handwritten numeral recognition, and benefit..Using Visual C++6.0 programming in handwritten digits recognition technology to achieve the experimental results show that the method has good effect. Handwritten digit recognition has wide applicative foreground in many domains, and scholars inside and outside have done much research work on it. They have reported many preprocessing algorithms and pattern recognition algorithms, which improves the accuracy of handwritten digit recognition in great measure. But up to now, the recognition accuracy still need to be improved and the problem of selecting kernel functions and kernel parameters still need to be solved. In this paper, on the basis of the theory of Artificial Neural Network,?the recognition for hand-written characters which include ten Arabic numerals and fifty-two English letter, c