Black and white picture coloring method and system based on CNN-LSTM combination model

Abstract

The invention discloses a black and white picture coloring method and system based on a CNN-LSTM combination model, and the method comprises the steps: collecting a plurality of color initial images,converting the plurality of color initial images into a plurality of black and white images, and respectively forming a training set and a test set based on the plurality of color images and the plurality of black and white images; inputting the plurality of black and white images and the plurality of color images in the training set into a CNN-LSTM convolutional neural network model, respectivelygenerating black and white and color feature maps, and performing color matching test on the black and white feature maps and the generated color feature maps to finally obtain a coloring network model; and coloring the to-be-colored black and white image by utilizing the coloring network model. According to the invention, the coloring accuracy of the finally obtained coloring network model can be improved, the black and white images are automatically colored, and the color inconsistency of each frame-by-frame image is eliminated, so that smoother color images can be generated, and the overall beautiful viewing experience is obtained.

Description

technical field [0001] This application relates to the technical field of image recognition, in particular to a method and system for coloring black and white pictures based on the CNN-LSTM combination model. Background technique [0002] Image coloring is a basic means of image enhancement. It is a computer-aided processing technology that adds color to images or videos. Better visual effects can be obtained by complementing black and white pictures. It is used in entertainment, education, scientific research, and medical treatment. have very wide applications. [0003] Image coloring methods in the prior art mainly include the following two types, one is a coloring method based on user prompts, and the other is to color a black and white image without any coloring prompts. The first colorization method requires human intervention, which increases the cost of labor and time; the second colorization method is automatically extracted from a single image by using a deep learn...

AI Technical Summary

Problems solved by technology

However, the coloring effect of this method is not good, the coloring is single and the accuracy is relatively low

Images