Mural classification model based on high- and low-level vision fusion

Abstract

The rapid classification of ancient murals is a pressing issue confronting scholars due to the rich content and information contained in images. Convolutional neural networks (CNNs) have been extensively applied in the field of computer vision because of their excellent classification performance. However, the network architecture of CNNs tends to be complex, which can lead to overfitting. To address the overfitting problem for CNNs, a classification model for ancient murals was developed in this study on the basis of a pretrained VGGNet model that integrates a depth migration model and simple low-level vision. First, we utilized a data enhancement algorithm to augment the original mural dataset. Then, transfer learning was applied to adapt a pretrained VGGNet model to the dataset, and this model was subsequently used to extract high-level visual features after readjustment. These extracted features were fused with the low-level features of the murals, such as color and texture, to form feature descriptors. Last, these descriptors were input into classifiers to obtain the final classification outcomes. The precision rate, recall rate and F1-score of the proposed model were found to be 80.64%, 78.06% and 78.63%, respectively, over the constructed mural dataset. Comparisons with AlexNet and a traditional backpropagation (BP) network illustrated the effectiveness of the proposed method for mural image classification. The generalization ability of the proposed method was proven through its application to different datasets. The algorithm proposed in this study comprehensively considers both the high- and low-level visual characteristics of murals, consistent with human vision.