Image coloring method based on multi-residual network and regularization transfer learning

Abstract

The invention discloses an image coloring method based on a multi-residual network and regularization transfer learning. The image coloring method comprises the steps that a gray level image data setis manufactured; extracting image features by using an image feature extraction module constructed based on a multi-residual network; training an image semantic feature extraction module based on a regularization transfer learning framework, and extracting image semantic features by utilizing the image semantic feature extraction module; inputting the image features and the image semantic featuresinto an image fusion module for fusion to obtain fusion features of the grayscale image; and inputting the fusion features of the grayscale image into an image coloring module constructed based on amulti-residual network for coloring to obtain a new color image. According to the invention, the image feature extraction module and the image coloring module are constructed based on the multi-residual network, so that the network performance is improved; an image semantic feature extraction module is trained based on a regularization transfer learning framework, image semantic features are extracted, and the accuracy of semantic feature extraction and the accuracy of image coloring are improved.

Description

technical field [0001] The invention relates to the technical field of image coloring, in particular to an image coloring method based on multiple residual networks and regularized transfer learning. Background technique [0002] The research and application of coloring technology has been carried out as early as the 1980s. From the beginning, people painted their favorite colors on black and white images by hand, to the earliest black and white film evolved into color images, images Coloring technology is becoming more and more mature and widely used. For example, in remote sensing and satellite fields, coloring technology plays a very important role; in the medical field, image coloring is also widely used in X-ray, CT, MR and other medical image processing. [0003] In recent years, deep learning methods have been introduced into the field of image coloring, which has greatly improved data-driven image coloring algorithms, and gradually formed a series of image coloring ...

AI Technical Summary

Problems solved by technology

However, the existing image coloring method based on deep learning has the problem that the coloring effect of some scenes in the image is not good.

Most of these methods will use semantic features to guide the image model when coloring, and there will be a problem of low accuracy of semantic feature extraction network

Images