Abstract
Color transfer is a useful image editing technology that transfers the color style of a reference image to a source image. In this paper, a novel automatic perception color transfer method based on salient features mapping was proposed. Firstly, the saliency maps of the reference image and source image are built to predict the human visual attention regions. Secondly, the gradient map is calculated by convolving the image pair with Sobel filter. Thirdly, the saliency map and gradient map are combined to produce a weighted attention map. Fourthly, by thresholding the attention map the reference image and the source image are segmented into regions of salient and non-salient pixels, and mean and standard deviation of these two regions are calculated in the three channels of the YUV space, respectively. Finally, on the salient and non-salient pixels an execution similar to Reinhard's is performed, and the two results are combined to generate the final output. The experiments result show the superiority of our method by its pleasant natural appearance with color similarity and image details preservation, high time efficiency and easy implementation.
Highlights
Color transfer is an image editing technology aiming to transfer the color style of a reference image to a source image, which is widely used in various image and video processing applications, such as image colorization, image enhancement and special effects for videos
Color mapping ensures that the color of the reference image be properly transferred to the source image while keeping the color similarity; and the preservation of color content requires that the structure and texture of the resulting image be consistent with source image after the process
Dominant color mapping [9], Gaussian Mixture Models [10]–[12], directive local color transfer methods [13], [14], probabilistic moving least square algorithms [15], [16], local texture-based method [17], etc. belong to the former group. The latter group includes color style changed with neural network [18], deep learning framework [19], and colorization with the SVM algorithm [20]. These local color transfer methods can be classified as automatic methods [4], [12], [18]–[21] and interactive methods [17], [22]–[25], where the former ones refer to the automatic local color mapping without manual intervention to region matching, and the latter means the allowance of users in defining the correspondence by sketches or rectangles
Summary
Color transfer is an image editing technology aiming to transfer the color style of a reference image to a source image, which is widely used in various image and video processing applications, such as image colorization, image enhancement and special effects for videos. The latter group includes color style changed with neural network [18], deep learning framework [19], and colorization with the SVM algorithm [20] These local color transfer methods can be classified as automatic methods [4], [12], [18]–[21] and interactive methods [17], [22]–[25], where the former ones refer to the automatic local color mapping without manual intervention to region matching, and the latter means the allowance of users in defining the correspondence by sketches or rectangles.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.