基于复杂网络描述的图像深度卷积分类方法

Image deep convolution classification method based on complex network description

为了在不增加较多计算量的前提下,提高卷积网络模型用于图像分类的正确率,提出了一种基于复杂网络模型描述的图像深度卷积分类方法。首先,对图像进行复杂网络描述,得到不同阈值下的复杂网络模型度矩阵;然后,在图像度矩阵描述的基础上,通过深度卷积网络得到特征向量;最后,根据得到的特征向量进行K近邻(KNN)分类。在ILSVRC2014数据库上进行了验证实验,实验结果表明,所提出的模型具有较高的正确率和较少的迭代次数。

In order to improve the accuracy of image classification with convolution network model without increasing more computation,a new image deep convolution classification method based on complex network description was proposed.Firstly,the complex network model degree matrices under different thresholds were obtained by using complex network description of image.Then,the feature vector was obtained by deep convolution neural networks based on degree matrix description of image.Finally,the obtained feature vectors were used for image K-Nearest Neighbors(K NN)classification.The verification experiments were carried out on the ImageNet Large Scale Visual Recognition Challenge2014(ILSVRC2014)database.The experimental results show that the proposed model has higher accuracy and fewer iterations.