摘要
目的为了进一步提高卷积神经网络的收敛性能和识别精度,增强泛化能力,提出一种自适应增强卷积神经网络图像识别算法。方法构建自适应增强模型,分析卷积神经网络分类识别过程中误差产生的原因和误差反馈模式,针对分类误差进行有目的地训练,实现分类特征基于迭代次数和识别结果的自适应增强以及卷积神经网络权值的优化调整。自适应增强卷积神经网络与多种算法在收敛速度和识别精度等性能上进行对比,并在多种数据集上检测自适应卷积神经网络的泛化能力。结果通过对比实验可知,自适应增强卷积神经网络算法可以在很大程度上优化收敛效果,提高收敛速度和识别精度,收敛时在手写数字数据集上的误识率可降低20.93%,在手写字母和高光谱图像数据集上的误识率可降低11.82%和15.12%;与不同卷积神经网络优化算法对比,误识率比动态自适应池化算法和双重优化算法最多可降低58.29%和43.50%;基于不同梯度算法的优化,误识率最多可降低33.11%;与不同的图像识别算法对比,识别率也有较大程度提高。结论实验结果表明,自适应增强卷积神经网络算法可以实现分类特征的自适应增强,对收敛性能和识别精度有较大的提高,对多种数据集有较强的泛化能力。这种自适应增强模型可以进一步推广到其他与卷积神经网络相关的深度学习算法中。
Objective Deep learning has been widely used in computer vision and possesses increased number of network layers, which is its major difference from shallow learning. Deep learning can learn data through multi-level networks, con- struct a complex nonlinear function model to extract data features, combine low-level features into high-level features, and complete the classification and recognition of data. Deep learning can extract accurate features and avoid the subjectivity and randomness of artificial selection without human participation in the process of feature extraction. Convolutional neural network （CNN） is an important model of deep learning and is widely used in image classification and recognition tasks. Im- proving the convergence speed and recognition rate can promote the application development of CNN. CNN possesses strong robustness because of its convolution and pooling operation during the feature extraction phase. It also exhibits powerful ca- pability of learning owing to its multiple layers and rich parameters. Many researchers have improved the CNN for its appli- cation in different fields. In this study, an adaptively enhanced CNN algorithm is proposed to improve the convergence speed and recognition accuracy of the CNN, reduce the difficulty of training, optimize the convergence effect, and enhance the generalization capability. Method CNN mainly includes forward and back propagations for classifying and recognizing images. Forward propagation includes feature extraction and target classification, and back propagation includes feedback of classification error and updating of weights. The proposed algorithm is aimed at adding an error adaptively enhanced process between forth and back propagations, building the adaptively enhanced model, constructing the CNN on the basis of the a- daptively enhanced model, analyzing the causes of error classification and error feedback pattern during the process of CNN classification and recognition, and training the classification error purposefully. Th
出处
《中国图象图形学报》
CSCD
北大核心
2017年第12期1723-1736,共14页
Journal of Image and Graphics
基金
国家自然科学基金项目(61172144)
辽宁省教育厅科学技术研究一般项目(L2015216)~~
关键词
深度学习
卷积神经网络
图像处理
分类识别
特征提取
特征自适应增强
deep learning
convolutional neural network
image processing
classification and recognition
feature extrac- tion
feature enhanced adaptively
