Abstract
The average accuracy of the fusion of color harmony and composition features is 75.17%, which is higher than that of a single feature. The classification accuracy of NP-DP-DCNN structure is about 1% higher than that of other methods and 1.77% higher than that of NP-DCNN. Traditional image aesthetic evaluation methods are only effective for specific image sets or specific style images and are not suitable for all types of images. Based on the introduction of the partial differential equation image filtering method, through the parallel supervised learning of aesthetic attribute labels, this paper extracts the global aesthetic depth features, adopts the partial differential equation to evolve the contour C constant, and constructs a convolution neural network. The structure of a convolution kernel learned by using parallel network structure achieves better classification performance. Through the aesthetic evaluation experiment, the overall test accuracy is improved by 0.58% and the average accuracy of the integration of color harmony and composition features is 75.17%, which is higher than that of a single feature. The classification accuracy of NP-DP-DCNN structure is about 1% higher than that of other methods and 1.83% higher than that of NP-DCNN. It has achieved better test accuracy than before in the seven subcategories with discrimination between high aesthetic and low aesthetic images. It has achieved better classification performance than the traditional feature extraction methods in the public dataset CUHK database, and it has excellent aesthetic reference value.
Highlights
With the development of science and technology and the popularization of digital products, the number of digital images on the network is increasing explosively
Traditional image aesthetic evaluation methods design features based on the original image data and input the extracted features into the classifier to train the classification model
To solve the above problems, this paper proposes an improved color harmony algorithm and the method of integrating composition features, which is conducive to improving the accuracy of image aesthetic classification and has good robustness to all kinds of images
Summary
With the development of science and technology and the popularization of digital products, the number of digital images on the network is increasing explosively. This paper uses the Advances in Mathematical Physics deep learning method to automatically learn features and applies it to the image aesthetic evaluation system. Based on the experimental research of traditional denoising methods, this paper introduces the directional diffusion method in the partial differential equation image filtering method and combines with lifting wavelet transform to diffuse each low-frequency and high-frequency subimage after transformation. Traditional image aesthetic evaluation methods design features based on the original image data and input the extracted features into the classifier to train the classification model. This paper uses the deep learning method to automatically learn features and applies it to the image aesthetic evaluation system
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
