Black-and-white image colorizing method based on two-sided filter

Abstract

The invention relates to a black-and-white image colorizing method based on a two-sided filter in the field of image processing, comprising the following steps of: labeling a black-and-white image; carrying out distance conversion on the black-and-white image to obtain the processing priority of an image block; calculating a geometrical distance weight and an average gray gradient value between the current block and an adjacent block under the frame of the two-sided filter, wherein if the average gray gradient value is greater than a threshold value, the similarity of the adjacent block and the current block is insufficient, and therefore, the average gray gradient value can not be used for forecasting the current block; conversely, if the average gray gradient value is less than the threshold value, calculating gray value variable weights of the current and the adjacent blocks; and finally obtaining the recovery value of the current block by the current block, the geometrical distance weight and the gray change weight. The invention overcomes the defect of the dependence assumption of brightness and chromaticity in the colorizing process, effectively colorizes the damaged black-and-white image, and has short used time and high signal to noise ratio of an obtained peak value.

Description

technical field [0001] The invention relates to a method in the technical field of image processing, in particular to a black and white image colorization method based on a bilateral filter. Background technique [0002] Black and white image colorization is the process of adding color to black and white images. Early colorization techniques were mainly used for black-and-white photos or movies, and often artificial coloring was used to process photos or movies. The workload of doing this is huge. With the advent of computer technology, computer-aided colorization methods have greatly improved the efficiency of processing. Computer-aided colorization methods are usually divided into: template-based methods and semi-manual intervention methods. The biggest challenge of the former is to obtain a suitable image template; while the latter is to accurately add the target by adding human intervention. color. Therefore, compared with the colorization method of template matching...

AI Technical Summary

Problems solved by technology

However, this technology fails to consider the lack of brightness information, that is, the damage of the original black and white image

In addition, since the luminance information of the damaged area is lost, the correct weighting of the chromaticity space cannot be obtained, which brings the problem of wrong coloring of the damaged area

Images