Color Transfer Algorithm between Images Based on a Two-Stage Convolutional Neural Network

Abstract

A color transfer algorithm between images based on two-stage convolutional neural network (CNN) is proposed. The first stage network is based on VGG19 architecture as the backbone. The reference image-based color transfer (RICT) model was used to extract the features of the reference image and the target image, so as to realize the color transfer between them. The second stage is based on progressive convolutional neural network (PCNN) as its backbone. The palette-based emotional color enhancement (PECE) model is adopted to enhance the emotional coloring of the resulting image by comparing the palette, emotional value and the proportion of each color of the reference image. Through five sets of experiments, it is proved that the visual effect processed by our model is obviously better than several main colorization methods in both subjective evaluation and objective data. It can be applied to various complex scenes, and in the near future, it can also be better applied to the fields of digital restoration of old image archives, medical image coloring, art restoration, remote sensing image enhancement, infrared image enhancement and other fields.