摘要
手写字符识别是图像识别的一个重要分支,是基于数据挖掘和机器学习技术对数字、字母和文字等的手写体进行识别。当前手写字符识别方法主要集中在对不同深度学习模型的完善和改进上,其中多层极限学习机由于其快于深度信念网络和深度玻尔兹曼机的训练速度以及更高的识别精度引起了学术界和工业界的广泛关注。但是,多层极限学习机的预测表现极易受随机权重的影响,层数越多影响就越明显。文中在深入分析浅层极限学习机训练模式的基础上,提出了一种基于隐含层输出矩阵分解的浅层极限学习机模型,并将其应用于对手写字符的识别。分解极限学习机不需要对手写字符图像进行特征提取,而是通过对大规模隐含层输出矩阵的分解来获得极限学习机的输出层权重。相比深层极限学习机,分解极限学习机降低了基于极限学习机的手写字符识别模型训练的随机性。同时,在MNIST类数据集(即MNIST,EMNIST,KMNIST和K49-MNIST)上的比较结果表明,在相同的训练时间下,分解极限学习机能够获得优于多层极限学习机的识别精度;在相同的识别精度下,分解极限学习机的训练时间明显短于多层极限学习机。实验结果证实了分解极限学习的可行性以及在处理手写字符识别问题上的有效性。
Handwritten character recognition(HCR)is an important branch of image recognition,which recognizes the handwritten characters with the data mining and machine learning technologies.Currently,the HCR methods mainly focus on the improvements of different deep learning models,where the multiple-layer extreme learning machine(ML-ELM)has attracted the wide attention from the academia and industry due to its faster training speed and better recognition performance than deep belief net(DBN)and deep Boltzmann machine(DBM).However,the recognition performance of ML-ELM is severely influenced by the random weights when determining the input weights for each hidden-layer.This paper first proposes a decomposition ELM(DE-ELM)which is a shallow ELM training scheme based on the hidden-layer output matrix decomposition and then applies DE-ELM to deal with HCR problems,i.e.,handwritten digits in MNIST,handwritten digits and English letters in EMNIST,handwritten Japanese characters in KMNIST and K49-MNIST.In comparison with ML-ELM,DE-ELM reduces the randomness of ELM-based HCR model.Meanwhile,DE-ELM can obtain higher recognition accuracy than ML-ELM with the same training time and faster training speed than ML-ELM with the equal recognition accuracy.Experimental results demonstrate the feasibility and effectiveness of the proposed DE-ELM when dealing with HCR problems.
作者
何玉林
李旭
金一
黄哲学
HE Yu-lin;LI Xu;JIN Yi;HUANG Zhe-xue(College of Computer Science&Software Engineering,Shenzhen University,Shenzhen,Guangdong 518060,China;Guangdong Laboratory of Artificial Intelligence and Digital Economy(SZ),Shenzhen,Guangdong 518107,China;Department of Criminal Science and Technology,Criminal Investigation Police University of China,Shenyang 110854,China)
出处
《计算机科学》
CSCD
北大核心
2022年第11期148-155,共8页
Computer Science
基金
国家自然科学基金(61972261)
深圳市基础研究面上项目(JCYJ20210324093609026)。
关键词
手写字符识别
极限学习机
多层极限学习机
深度学习
特征提取
Handwritten character recognition
Extreme learning machine
Multiple layer extreme learning machine
Deep lear-ning
Feature extraction
