Xiang Jin, Yang Yi, Bai Junwei
School of Art and Design, Wuhan Polytechnic University, Wuhan, China.
School of Industrial Design, Hubei Institute of Fine Arts, Hubei, Wuhan, China.
PeerJ Comput Sci. 2024 Oct 7;10:e2336. doi: 10.7717/peerj-cs.2336. eCollection 2024.
The current art image classification methods have low recall and accuracy rate issues . To improve the classification performance of art images, a new adaptive classification method is designed employing multi-scale convolutional neural networks (CNNs). Firstly, the multi-scale Retinex algorithm with color recovery is used to complete the enhancement processing of art images. Then the extreme pixel ratio is utilized to evaluate the image quality and obtain the art image that can be analyzed. Afterward, edge detection technology is implemented to extract the key features in the image and use them as initial values of the item to be trained in the classification model. Finally, a multi-scale convolutional neural network (CNN) is constructed by using extended convolutions, and the characteristics of each level network are set. The decision fusion method based on maximum output probability is employed to calculate different subclassifies' probabilities and determine the final category of an input image to realize the art image adaptive classification. The experimental results show that the proposed method can effectively improve the recall rate and precision rate of art images and obtain reliable image classification results.
当前的艺术图像分类方法存在召回率和准确率较低的问题。为了提高艺术图像的分类性能，设计了一种采用多尺度卷积神经网络（CNN）的新型自适应分类方法。首先，使用具有颜色恢复功能的多尺度Retinex算法完成艺术图像的增强处理。然后利用极端像素比来评估图像质量并获得可分析的艺术图像。之后，实施边缘检测技术以提取图像中的关键特征，并将其用作分类模型中待训练项的初始值。最后，通过使用扩展卷积构建多尺度卷积神经网络（CNN），并设置各级网络的特征。采用基于最大输出概率的决策融合方法来计算不同子分类的概率，并确定输入图像的最终类别，以实现艺术图像的自适应分类。实验结果表明，该方法可以有效提高艺术图像的召回率和精确率，并获得可靠的图像分类结果。
