A New Convolution Network Based on Laplacian Eigenmap

被引:0
作者
Kang, Pengxin [1 ]
He, Xiaohai [1 ]
Qing, Lingbo [1 ]
Teng, Qizhi [1 ]
Su, Jie [1 ]
机构
[1] Sichuan Univ, Coll Elect & Informat Engn, Chengdu 610065, Sichuan, Peoples R China
来源
PROCEEDINGS OF THE 2017 5TH INTERNATIONAL CONFERENCE ON MACHINERY, MATERIALS AND COMPUTING TECHNOLOGY (ICMMCT 2017) | 2017年 / 126卷
关键词
Convolution Network; Laplacian Eigenmap; texture classification; face recognition;
D O I
暂无
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The best is to read these instructions and follow the outline of this text. Recently, convolutional deep neural network (ConvNet) has been widely used in the field of image classification. In this work, we propose a new feedback free convolution network for image classification. The proposed network could hierarchically and effectively extract the features from an image through a manually designed convolution network without relying on back-propagation. The network is designed in a cascaded fashion, where the Laplacian Eigenmap filter is used as convolution kernel to extract features in each of the cascaded stage. The final output of the network is achieved by a simply binary hashing and histogram encoding, and could be served as distinguishing features for many classification tasks. Experiments on different database, e.g. FERET datasets for face recognition, CUReT for texture classification and MNIST for hand-written digits recognition, showed that the proposed method outperforms many other popular machine learning algorithms.
引用
收藏
页码:759 / 765
页数:7
相关论文
共 12 条
[11]   A Statistical Approach to Material Classification Using Image Patch Exemplars [J].
Varma, Manik ;
Zisserman, Andrew .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2009, 31 (11) :2032-2047
[12]   ML-KNN: A lazy learning approach to multi-label leaming [J].
Zhang, Min-Ling ;
Zhou, Zhi-Hua .
PATTERN RECOGNITION, 2007, 40 (07) :2038-2048