计算机科学 ›› 2022, Vol. 49 ›› Issue (11): 148-155.doi: 10.11896/jsjkx.211200265
何玉林1,2, 李旭1,2, 金一3, 黄哲学1,2
HE Yu-lin1,2, LI Xu1,2, JIN Yi3, HUANG Zhe-xue1,2
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。
中图分类号:
| [1]全国科学技术名词审定委员会术语在线 [EB/OL].[2020-12-20].https://www.termonline.cn/search?k=手写字符识别&r=1608 471572108. [2]MUHAMMAND’ARIFMOHAMAD D N,HASSAN H,HA-RON H.A review on feature extraction and feature selection for handwritten character recognition [J].International Journal of Advanced Computer Science and Applications,2015,6(2):204-212. [3]KUMAR M,JINDAL M K,SHARMA R K.k-nearest neighbor based offline handwritten Gurmukhi character recognition [C]//Proceedings of International Conference on Image Information Processing.IEEE,2011:1-4. [4]SHANTHI N,DURAISWAMY K.A novel SVM-based handwritten Tamil character recognition system [J].Pattern Analysis and Applications,2010,13(2):173-180. [5]PATEL C I,PATEL R,PATEL P.Handwritten character reco-gnition using neural network [J].International Journal of Scientific & Engineering Research,2011,2(5):1-6. [6]SHRIDHAR M,BADRELDIN A.A high-accuracy syntacticrecognition algorithm for handwritten numerals [J].IEEE Transactions on Systems,Man,and Cybernetics,1985,1:152-158. [7]LECUN Y,BOSER B,DENKER J S,et al.Backpropagation applied to handwritten zip code recognition [J].Neural Computation,1989,1(4):541-551. [8]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-basedlearning applied to document recognition [J].Proceedings of the IEEE,1998,86(11):2278-2324. [9]HINTON G E,OSINDERO S,TEH Y W.A fast learning algorithm for deep belief nets [J].Neural Computation,2006,18(7):1527-1554. [10]SALAKHUTDINOV R,LAROCHELLE H.Efficient learningof deep Boltzmann machines [C]//In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics.2010:693-700. [11]HUANG G B,ZHU Q Y,SIEW C K.Extreme learning ma-chine:theory and applications [J].Neurocomputing,2006,70(1/2/3):489-501. [12]HUANG G B,ZHOU H,DING X,et al.Extreme learning machine for regression and multiclass classification [J].IEEE Transactions on Systems,Man,and Cybernetics,Part B(Cybernetics),2011,42(2):513-529. [13]HUANG G B,CHEN L,SIEW C K.Universal approximationusing incremental constructive feedforward networks with random hidden nodes [J].IEEE Transactions on Neural Networks,2006,17(4):879-892. [14]HUANG G B,DING X,ZHOU H.Optimization method based extreme learning machine for classification [J].Neurocompu-ting,2010,74(1/2/3):155-163. [15]LEKAMALAGE C K,LIU T,YANG Y,et al.Extreme learning machine for clustering [C]//Proceedings of ELM-2014.Sprin-ger,2015:435-444. [16]HUANG G,SONG S,GUPTA J N,et al.Semi-supervised and unsupervised extreme learning machines [J].IEEE Transactions on Cybernetics,2014,44(12):2405-2417. [17]PAN J,WANG X,CHENG Y,et al.Reinforcement learningbased on extreme learning machine [C]//Proceedings of International Conference on Intelligent Computing.Springer,2012:80-86. [18]CAO F,LIU B,PARK D S.Image classification based on effective extreme learning machine [J/OL].Neurocomputing.2013,102:90-97.https://doi.org/10.1016/j.neucom.2012.02.042. [19]SCHMIDT W F,KRAAIJVELD M A,DUIN R P.Feed forwardneural networks with random weights [C]//Proceedings of In- ternational Conference on Pattern Recognition.IEEE,1992:1-4. [20]IGELNIK B,PAO Y H.Stochastic choice of basis functions inadaptive function approximation and the functional-link net [J].IEEE transactions on Neural Networks,1995,6(6):1320-1329. [21]HUANG G,HUANG G B,SONG S,et al.Trends in extreme learning machines:A review [J].Neural Networks,2015,61(1):32-48. [22]DING S,ZHAO H,ZHANG Y,et al.Extreme learning ma-chine:algorithm,theory and applications [J].Artificial Intelligence Review,2015,44(1):103-115. [23]CAO W,WANG X,MING Z,et al.A review on neural networks with random weights [J/OL].Neurocomputing,2018,275:278-287.https://doi.org/10.1016/j.neucom.2017.08.040. [24]KASUN L L,ZHOU H,HUANG G B,et al.Representational learning with extreme learning machine for big data [J].IEEE Intelligent Systems,2013,28(6):31-34. [25]DING S,ZHANG N,XU X,et al.Deep extreme learning ma-chine and its application in EEG classification [J/OL].Mathematical Problems in Engineering,2015,2015(129021).https://www.hindawi.com/journals/mpe/2015/129021. [26]TANG J X,DENG C,HUANG G B.Extreme learning machine for multilayer perceptron [J].IEEE Transactions on Neural Networks and Learning Systems,2015,27(4):809-821. [27]KUSSUL E,BAIDYK T.Improved method of handwritten digit recognition tested on MNIST database [J].Image and Vision Computing,2004,22(12):971-981. [28]COHEN G,AFSHAR S,TAPSON J,et al.EMNIST:Extending MNIST to handwritten letters [C]//Proceedings of Interna-tional Joint Conference on Neural Networks.IEEE,2017:2921-2926. [29]CLANUWAT T,BOBER-IRIZAR M,KITAMOTO A,et al.Deep learning for classical Japanese literature [J].arXiv:1812.01718,2018. [30]ZHAO Z T,ZHENG X D.Feature Incremental Extreme Lear-ning Machine[J].Computer Science,2019,46(11A):112-116. [31]XU R,LIANG X,MA R F,et al.Adaptive Orthogonal Search for Network Structure Learning of ELM[J].Chinese Journal of Computer,2021,44(9):1888-1906. [32]HE Y L,LIU J N,WANG X Z,et al.Optimal bandwidth selection for re-substitution entropy estimation [J].Applied Mathematics and Computation,2012,219(8):3425-3260. |
| [1] | 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204 |
| [2] | 饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277 |
| [3] | 汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108 |
| [4] | 孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061 |
| [5] | 王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099 |
| [6] | 郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077 |
| [7] | 姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046 |
| [8] | 张源, 康乐, 宫朝辉, 张志鸿. 基于Bi-LSTM的期货市场关联交易行为检测方法 Related Transaction Behavior Detection in Futures Market Based on Bi-LSTM 计算机科学, 2022, 49(7): 31-39. https://doi.org/10.11896/jsjkx.210400304 |
| [9] | 胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092 |
| [10] | 曾志贤, 曹建军, 翁年凤, 蒋国权, 徐滨. 基于注意力机制的细粒度语义关联视频-文本跨模态实体分辨 Fine-grained Semantic Association Video-Text Cross-modal Entity Resolution Based on Attention Mechanism 计算机科学, 2022, 49(7): 106-112. https://doi.org/10.11896/jsjkx.210500224 |
| [11] | 程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157 |
| [12] | 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木. 中文预训练模型研究进展 Advances in Chinese Pre-training Models 计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018 |
| [13] | 周慧, 施皓晨, 屠要峰, 黄圣君. 基于主动采样的深度鲁棒神经网络学习 Robust Deep Neural Network Learning Based on Active Sampling 计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044 |
| [14] | 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫. 小样本雷达辐射源识别的深度学习方法综述 Survey of Deep Learning for Radar Emitter Identification Based on Small Sample 计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138 |
| [15] | 刘伟业, 鲁慧民, 李玉鹏, 马宁. 指静脉识别技术研究综述 Survey on Finger Vein Recognition Research 计算机科学, 2022, 49(6A): 1-11. https://doi.org/10.11896/jsjkx.210400056 |
|
||
首页