计算机技术与发展2016，Vol.26Issue(7)：19-23,29,6.DOI:10.3969/j.issn.1673-629X.2016.07.005
手写数字深度特征学习与识别
Deep Learning and Recognition of Handwritten Numeral Features
摘要
Abstract
Network structure design,feature extraction and fusion in deep learning are key problems in data mining and pattern recognition theory and industry application. The design of deep learning network's structure and the problem of feature fusion is explored,taking handwritten numeral recognition and authoritative database MNIST,with 70 thousands of handwritten image,as the experiment platform, which guarantees the practicability,representation and reference of the research results. The solution step has been given. Firstly,the unsu-pervised deep learning network is designed,learning unsupervised high-level semantic features,extraction of depth features,and explora-tion of higher cognitive characteristics of features. Secondly,unsupervised features of handwritten database are extracted,including HOG, PCA,LDA and so on,construction of LTF. Finally,deep supervised learning network is built,fusion of deep features and the library of typical features with supervision. The result shows that this scheme can lower error rate of handwritten recognition by 50%,compared with the typical features of the present.关键词
深度学习/特征融合/特征提取/手写数字识别/主成分分析/梯度方向直方图Key words
deep learning/feature fusion/feature extraction/handwritten numeral recognition/principal component analysis/histogram of oriented gradient分类
数学引用本文复制引用
陈浩翔,蔡建明,刘铿然,林秋爽,张文玲,周涛..手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(7):19-23,29,6.基金项目
国家自然科学基金资助项目(61273248,61075033) （61273248,61075033）
