A color correction method for structurally consistent stereoscopic images based on gradient preservation

A color correction and stereoscopic image technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of reducing image fidelity and losing detail information, and achieve the effect of improving fidelity
CN109461128AActive Publication Date: 2019-03-12FUZHOU UNIV
7 Cites 5 Cited by

Patent Information

Authority / Receiving Office
CN ยท China
Current Assignee / Owner
FUZHOU UNIV
Publication Date
2019-03-12

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a color correction method for structurally consistent stereoscopic images based on gradient preservation. Firstly, SIFT feature extraction and matching are respectively used for feature extraction and pixel matching of a reference image and a target image to obtain a structured image and a matching image. Secondly, the confidence map of matching image and target image is generated by using structural similarity algorithm, and the region with low confidence is mapped locally to generate the initial color correction result image. Finally, the gradient preservation algorithm is used to optimize the color and structure of the initial color correction result image, and the final result image is obtained. The invention solves the problem of the structural consistency ofthe local color correction algorithm and the problem of the regional color confusion of the global color correction calculation, and also retains the gradient information of the image and improves thefidelity of the image.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the fields of image and video processing and computer vision, in particular to a method for color correction of stereoscopic images with consistent structure based on gradient preservation. Background technique

[0002] Color correction is also known as color migration, color mapping, color repair or image style conversion, its purpose is to eliminate the color difference between two similar image pairs, or transfer the style of the reference image to the target image, so that the target image appears The style of the reference image. At present, there are many kinds of color correction algorithms, which can be divided into global color correction and local color correction from the perspective of correction area. The global color correction algorithm is currently the most common color correction algorithm. Its implementation method is simple and efficient, and it does not need to consider the image structure problems caused b...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More