Multi-sparse dictionary grayscale map colorization method based on feature classification detail enhancement

Abstract

The invention discloses a multi-sparse dictionary grayscale map colorization method based on feature classification detail enhancement. Feature classification and a multi-sparse dictionary are combined to establish a colorization processing model, thereby realizing colorization of a grayscale image; a corresponding local constraint algorithm is provided to solve a problem of inaccurate classification, so that the classification accuracy is improved and the colorization effect is enhanced; and then a detailed enhancement algorithm is provided based on a Laplacian pyramid so as to solve a problem of detail losses inherent in sparse representation, so that the detail loss problem is solved and the speed of image colorization is increased. Therefore, the grayscale image colorization effect that conforms to the visual habit of the human being and has the high natural sense is obtained. The method can be applied to other fields like colorization of a grayscale fusion image and an infrared image and color transmission between the color images.

Description

technical field [0001] The invention belongs to the technical field of grayscale image colorization processing, and relates to a multi-sparse dictionary grayscale image colorization method based on feature classification detail enhancement. Background technique [0002] At present, non-manual intervention algorithms for colorization processing based on sparse representation are mainly divided into two types: colorization processing based on a single dictionary and colorization processing based on multiple dictionaries. Among them, the traditional colorization algorithm based on a single dictionary can only be used in It can achieve better results on images with a single tone, but for images with rich color content, a large number of false color points will appear. In order to solve this problem, Uruma K et al. proposed an improved sparse optimization algorithm, which achieved relatively good results, but there are still many wrong coloring points in the colorization effect; ...

AI Technical Summary

Problems solved by technology

[0002] At present, non-manual intervention algorithms for colorization processing based on sparse representation are mainly divided into two types: colorization processing based on a single dictionary and colorization processing based on multiple dictionaries. Among them, the traditional colorization algorithm based on a single dictionary can only be used in It achieves better results on images with a single color tone, but for images with rich color content, a large number of false color points will appear

In order to solve this problem, Uruma K et al. proposed an improved sparse optimization algorithm, which achieved relatively good results, but there are still many wrong coloring points in the colorization effect; Liang Hai et al. proposed a colorization algorithm based on classification dictionaries and sparse representations. Algorithm, the algorithm is composed of training classification dictionary and dictionary matching and colorization based on the minimization of reconstruction error. On this basis, Liang Hai et al. proposed an image colorization algorithm based on joint dictionary and sparse representation. The algorithm realizes the colorization of multi-content target grayscale images, and the improved algorithm works better. However, neither of these two algorithms solves the problems of missing details and blurred edges caused by colorization through sparse dictionaries. Moreover, for color Rich images, but there are still many false coloring points

Images