CASIA OpenIR  > 毕业生  > 硕士学位论文
Thesis Advisor裘聿皇
Degree Grantor中国科学院自动化研究所
Place of Conferral中国科学院自动化研究所
Degree Discipline控制理论与控制工程
Keyword遗传算法 复数编码 (0 1 *)-矩阵 印刷体字符识别 手写体 数字识别 Genetic Algorithms Complex-valued Encodings (0 1 *)-matrix Printed Character Recognition Handwritten Numeral Recognition
Abstract本文首先简要分析了遗传算法的理论知识,并在此基础上提出了一种基于 复数编码的遗传算法。第一次把复数编码的思想应用到遗传算法中去,用复数 编码来表达双倍体,并具体规定了遗传操作。每一个复数对应于双倍体的一对 等位基因。目标函数自变量的大小由其对应的复数的模决定,符号则由相应复 数的幅角决定。与传统的实数编码的遗传算法相比,该算法大大地扩展了表达 空间的维数,仿真结果证明了本算法的有效。此外,本算法的提出对解决复数 权神经网络的训练过程中可能出现的局部极值问题提供了可行的解决方案。 字符识别是遗传算法的一个非常重要的应用领域。本文充分考虑到遗传算 法的优良全局搜索性能,将遗传算法分别应用于印刷体字符识别和手写体数字 识别中去。在印刷体字符识别中,为了减少印刷体字符识别的计算复杂性,提 高识别率,针对印刷体字型相对稳定的特点,给出了一种全新有效的快速算法。 该方法通过合理的阈值将模板向量转化为(0,1,*)-向量,并充分考虑到代 表样本与模板之间相关性的不同因素的不同重要性,赋以相应的权系数,最后, 用遗传算法来确定阈值和权系数。而在手写体数字识别中,我们利用具有五个 独立子网的三层BP网作为分类器。将遗传算法与神经网络的BP反传算法结合 起来,先用遗传算法为神经网络确定一个具有全局意义的初始权分布,再使用 BP反传算法搜索全局最优解。这样既克服了BP算法的局部收敛性,又能充分 利用该算法的良好的局部搜索能力。
Other AbstractIn this dissertation, we make a brief analysis of Genetic Algorithms (Gas) in its theory basis. Afterward Complex-valued Encodings are first applied to Genetic Algorithms. We use one complex number to denote each diploidy and define the genetic operators accordingly as well. Each pair of alleles corresponds one complex number. The independent variables of the objective function are determined by the modules and angles of their corresponding complex numbers. Compared with the conventional Genetic Algorithms based on real-valued encodings or binary encodings, our algorithm expands the dimensions for denoting greatly. The computer simulation results prove its efficiency. Furthermore, the algorithm can be used to ensure global optimization during the training of artificial neural networks using complex numbers. Character recognition is a very important field GAs are applied to. Fully considering that genetic algorithms have excellent global sampling abilities, we apply them to printed character recognition and handwritten numeral recognition. In the case of printed character recognition, in order to simplify the computing complexity of printed character recognition and improve recognition rate as well, we proposed a new effective algorithm. Using two reasonable threshold values, the algorithm transformed real template vectors into (0,1,*)-ones. Meanwhile, adequately considering the different weightiness of the four different factors denoting the pertinence between template and unknown sample as we described, we allocated them corresponding weight coefficients. Finally we used Genetic Algorithm to decide all these threshold values and weight coefficients. In case of handwritten numeral recognition, we apply a simple multilayer cluster neural network with five independent subnetworks as the classifier. GAs are combined with backpropagation algorithm effectively. The initial weights of the neural network are decided by GAs, and then we use backpropagation algorithm to continue the search until the global maxima are found at last. By doing so, we can avoid the problem of finding local minima in training the neural network with backpropagation algorithm while taking advantage of its effective local search.
Other Identifier584
Document Type学位论文
Recommended Citation
GB/T 7714
郑朝晖. 遗传算法及其在字符识别中的应用[D]. 中国科学院自动化研究所. 中国科学院自动化研究所,2000.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[郑朝晖]'s Articles
Baidu academic
Similar articles in Baidu academic
[郑朝晖]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[郑朝晖]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.