Search

Precise and content-aware style transfer in oil painting remains a significant research focus. This involves preserving the semantic content of the original image while accurately emulating the desired painting style. Developing robust algorithms for accurate recognition and classification of various patterns within oil paintings remains a challenge which identify and categorize styles, textures and visual elements to contribute comprehensive understanding of the artwork. The conventional image style transfer algorithm mainly relies on mathematical modeling to characterize image texture facilitating the combination of a content image with a style image to realize style transfer effects. These algorithms neglect the distribution of image edges leading to blurred contours in the resulting images. To address these limitations, this paper proposed a novel decoration pattern style migration algorithm based on SRCNN (Super Resolution Convolutional Neural Network) model using UNet-based architecture. The algorithm leverages the Laplace operator for image sharpening by accentuating edge distributions. Downsampling techniques are used to generate low-resolution images mitigating the protracted duration of image style transfer iterations. The incorporation of Gaussian sampling and a parallelization algorithm contributes to the efficacy of this method in facilitating the transfer of oil painting styles. The proposed model achieves better results using Facades data set, i.e., variance (6.35%), standard deviation (8.67%), uncertainty (11.21%), SSIM score (94.45%), PSNR score (40.24%), MSE score (6.21%) and accuracy (95.00%). For the Monet2photo data set, i.e., variance (7.25%), standard deviation (9.78%), uncertainty (12.78%), SSIM score (91.69%), PSNR score (43.71%), MSE score (8.67%) and accuracy (92.00%). Our proposed method outperforms classical methods using both data sets. [ABSTRACT FROM AUTHOR]

The colorization of grayscale images is a challenging task in image processing. Recently, deep learning has shown remarkable performance in image colorization. However, the detail loss and color distortion are still serious problem for most existing methods, and some useful features may be lost in the processes of various convolutional layers because of the vanishing gradient problem. Therefore, there is still a considerable space to reach the roof of image colorization. In this work, we propose a deep convolutional auto-encoder with special multi-skip connections for image colorization in YUV color space, and the specific contributions or designs of this work are shown as the following five points. First, a given gray image is used as the Y channel to input a deep learning model to predict U and V channel. Second, the adopted encoder-decoder consists of a main path and two branch paths, and the branch path has two skip connection ways that include one shortcut in each three layers and one shortcut in each six layers. Third, the convolutional kernel size is set as 2*2 that is a special consideration in the path of one shortcut in each six layers. Fourth, a composite loss function is proposed based on the mean square error and gradient that is defined to calculate the errors between the ground truth and the predicted result. Finally, we also discuss the reasonable network parameters, such as the way of shortcut connection, the convolutional kernel size of shortcut connection, and loss function parameters. Experiments on different image datasets show that the proposed image colorization model is effective, and the scores of the PNSR, RMSE, SSIM, and Pearson correlation coefficient are, respectively, to 27.0595, 0.1311, 0.561, and 0.9771. [ABSTRACT FROM AUTHOR]