【摘要】 绘画作品的数字化对有效使用绘画资源具有重要意义,传统图像分类方法并未考虑绘画作品主观特性,且大部分特征需要人工提取,存在细节特征丢失等问题.在此提出基于卷积神经网络的绘画图像分类方法,分析了卷积核大小、卷积神经网络结构宽度、训练样本数量对分类结果的影响,以优化网络结构和参数.实验结果表明,该方法对绘画图像分类的有效性,在不同绘画图像数据集的分类实验上也得到了较好的分类结果.更多还原

【Abstract】 It is significant to realize the digitalization of painting works for the effective use of painting resources. The traditional image classification methods do not take into account of the subjective characteristics of the painting works,and most of the features need to be extracted manually,thus the problem of easily missing detailed features. In this paper,a painting image classification method based on convolutional neural network( CNN) was proposed. We analyzed the influence to the classification results of the size of convolution kernel,the width of convolution neural network architectures,and the number of training samples to get a reference to optimize the network architectures and parameters. The experimental results show the effectiveness of the proposed method for the classification of painting images with good results on different data sets of painting images.更多还原