摘要
LeNet-5卷积神经网络(CNN)虽然在手写数字识别上取得很好的分类效果,但在具有复杂纹理特征的数据集上分类精度不高。为提高网络在复杂纹理特征图像上分类的正确率,提出一种改进的LeNet-5网络结构。引入跨连思想,充分利用网络提取的低层次特征;把Inception V1模块嵌入LeNet-5卷积神经网络,提取图像的多尺度特征;输出层使用softmax函数对图像进行分类。在Cifar-10和Fashion MNIST数据集上进行的实验结果表明,改进的卷积神经网络在复杂纹理特征数据集上具有很好的分类能力。
Although the Le Net-5 Convolutional Neural Network(CNN)achieves good classification results in handwritten digit recognition, the classification accuracy is not high on datasets with complex texture features. In order to improve the accuracy of network class-ification on complex texture feature images, an improved Le Net-5 network structure is proposed.The idea of cross-connection is introduced to make full use of the low-level features of network extraction. The Inception V1 module is embedded in the LeNet-5 convolutional neural network to extract multi-scale features of the image. The output layer uses the softmax function to classify the image. Experimental results on the Cifar-10 and Fashion MNIST dataset show that the improved convolutional neural network has good classification ability on complex texture feature datasets.
引文
[1]黄凯奇,任伟强,谭铁牛.图像物体分类与检测算法综述[J].计算机学报,2014,37(6):1225-1240.
[2]卢宏涛,张秦川.深度卷积神经网络在计算机视觉中的应用研究综述[J].数据采集与处理,2016,31(1):1-17.
[3]郝占龙,罗晓曙,赵书林.基于同层多尺度核CNN的单细胞图像分类[J].计算机工程与应用,2018,54(15):181-184.
[4]胡良田,潘海为,谢晓芹,等.基于NSCT的乳腺图像分类方法[J].计算机科学与探索,2018,12(4):618-628.
[5]张巨萍,高光来,苏向东.融合光谱滤波的高光谱图像分类深度网络[J].计算机科学与探索,2018,12(11):1806-1814.
[6] Wen L,Li X,Gao L,et al.A new convo-lutional neural network-based data-driven fault diagnosis method[J].IEEE Transactions on Industrial Electronics,2018,65(7):5990-5998.
[7] Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[8] Krizhevsky A,Sutskever I,Hinton G E.Image net classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems,2012:1097-1105.
[9] Le Cun Y,Bottou L,Bengio Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2342.
[10] Zeiler M D,Fergus R.Visualizing and understanding convolutional networks[C]//European Conference on Computer Vision.Zurich,Switzerland:Springer,2014:818-833.
[11] Simonyan K,Zisserman A.Very deep convolutional networks for large scale image recognition[EB/OL].(2016-05-16).http://arxiv.org/abs/1409.1556.
[12] Szegedy C,Liu W,Jia Y Q,et al.Going deeper with convolutions[C]//IEEE Conference on Computer Vision and Pattern Recognition,2015:1-9.
[13] He K M,Zhang X Y,Ren S Q,et al.Deep residural learning for image recognition[J].arXiv:1409.4842,2014.
[14] Han Xiao,Kashif R,Roland V.Fashion-MNIST:a novel image dataset for benchmarking machine learning algorithms[J].arXiv:1708.07747,2017.
[15]张婷,李玉鑑,胡海鹤,等.基于跨连卷积神经网络的性别分类模型[J].自动化学报,2016,42(6):858-865.
[16] Sun Y,Wang X G,Tang X O.Deep learning face representation from predicting 10,000 classes[J].Proceedings of the IEEE,2014:1891-1898.
[17]李勇,林小竹,蒋梦莹.基于跨连LeNet-5网络的面部表情识别[J].自动化学报,2018,44(1):176-182.
[18] Lin M,Chen Q,Yan S.Network in network[C]//Proceedings of the 2014 International Conference on Learning Representations.Banff,Canada:Computational and Biological Learning Society,2014.
[19] Ranzato M,Hinton G E.Modeling pixel means and covariances using factorized third-order boltzmann machines[C]//IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2010.
[20] Yu K,Zhang T.Improved local coordinate coding using local tangents[C]//International Conference on Machine Learning,2010.
[21] Chan T H,Jia Kui.PCANet:a simple deep learning baseline for image classification?[J].arXiv:1404.3606v2,2014.
[22] Zeiler M,Fergus R.Stochastic pooling for regularization of deep convolutional neural networks[EB/OL].(2016-05-16).http://arXiv.org/abs/1301.3557.
[23] Goodfellow I J,Warde-Farley D,Mirza M,et al.Maxout networks[J].arXiv:1302.4389,2013.
[24] Srivastava R K,Greff K,Schmidhuber J.Highway networks[J].arXiv:1505.00387,2015.