基于多通道可分离网络的古代壁画分类方法

古代壁画艺术价值高、内容丰富,对壁画种类进行准确分类是研究者的难题之一.传统的壁画分类任务繁重且需要有经验的研究者完成;现有的图像分类算法已不适于分类含有较强背景噪声的壁画图像.针对以上问题提出了一种新的多通道可分离网络模型(multi-channel separable network model,MCSN)的解决方案.以GoogLeNet网络模型为基本框架,用小卷积核对壁画背景特征进行浅层提取,然后将7×7、3×3等较大卷积核十字分离成7×1、1×7和3×1、1×3等较小的卷积核提取壁画重要的深层次特征信息;使用软阈值化激活缩放策略(activation scaling)增加网络训练时的稳定性,最后通过softmax对壁画分类;使用小批量随机梯度下降(min-batch SGD)算法更新参数.精确率、召回率和F1值分别为88.16％、90.01％和90.38％.与主流分类算法相比,分类准确率、泛化能力、稳定性有了一定的提升,提高了壁画分类效率.

Ancient mural classification method based on multi-channel separable network

Ancient murals have high artistic value and rich content. It is one of the problems for researchers to accurately classify the types of murals. Traditional mural classification tasks are arduous and require experienced researchers to complete. The existing image classification algorithms are no longer suitable for classifying mural images with strong background noise. To solve the above problems, this paper proposed a new multi-channel separable network model. Using the GoogLeNet network model as the basic framework, it used a small convolution kernel to extract the background features of the murals in a shallow layer, and then separated the larger convolution kernels such as 7×7 and 3×3 into 7×1, 1×7 and 3×1, 1×3 and other smaller convolution kernels for extraction the important deep-level feature information of murals. Using activation scaling to increase the stability of the network during training, and finally classified the murals through softmax, then used a small batch stochastic gradient descent algorithm to update parameters. The precision rate, recall rate and F1 value are 88.16%, 90.01%, and 90.38%, respectively. Compared with mainstream classification algorithms, it improves classification accuracy, generalization ability, and stability to a certain extent, which improves the efficiency of mural classification.