Color conversion and editing propagation-based method for enhancing seasonal feature of image

Abstract

The invention, which belongs to the computer vision field, relates to a method for enhancing a seasonal feature of an image, wherein the method is based on color conversion and editing propagation. The method comprises the following steps that: a target image is input and a specific seasonal image is selected from a scene database and is used as a reference image; and then color conversion is carried out on the target image; foreground extraction is carried out on the target image to obtain outline information of a foreground object; a specific foreground object is selected as a template and a repeated foreground object that is similar to the template is extracted from the target image; an insertion object that is in accordance with a specific seasonal feature is selected from an object database and an insertion position is assigned in a target scene; the insertion object is rotated and zoomed to ensure visual rationality and then editing propagation is automatically carried out on the processed insertion object; at last, fusion is carried out on all inserted objects and a scene image to form a final scene having an assigned seasonal feature. According to the invention, the method can be widely applied and popularized to fields like film and television manufacture and city planning and the like.

Description

technical field [0001] The invention relates to the fields of image processing, computer vision and augmented reality, in particular to an image seasonal feature enhancement method based on color conversion and editing propagation. Background technique [0002] In the field of digital images, one of the most common image processing methods is to change the visual effect of images. For art designers or photography enthusiasts, in order to obtain scene images of the same scene in different seasons, a large amount of manual editing or time-consuming fixed-point shooting will be performed. In fact, the same scene has many characteristics in different seasons. For example, the color of the scene is generally green in summer and golden yellow in autumn; flowers bloom in spring and wither in autumn, and so on. These highly distinguishable characteristics in different seasons provide feasible conditions for us to design a scene seasonal characteristic enhancement system. A scene w...

AI Technical Summary

Problems solved by technology

[0006] The technical solution adopted by the present invention is: an image seasonal feature enhancement method based on color conversion and editing propagation, which mainly includes converting the input target image and the reference image selected from the scene library from the RGB color space to the Lab color space; using 11 basic colors , color-classify the target image and the reference image, calculate the color mean value of each color class in the target image and the reference image respectively, and form the main color of the target image and the reference image; Value constructs a local linear relationship, overcomes the problem of poor results caused by color deviation during the hole color conversion process, and ensures the visual rationality of the filled image scene; uses the constraint optimization penalty function method to obtain the resulting image through energy minimization The color value of each pixel in the image, and convert it to RGB color space; use the Grabcut algorithm to extract the foreground of the target image, and remove the irrelevant background image in the target image; use the Active Contour algorithm to perform contour inspection on the extracted foreground image, and obtain The complete contour information of the foreground image; in the detection of the contour image, interactively specify a complete object contour, and use it as a contour template, scan the entire contour image, and detect all other objects of the same type; from the object library Select an object that meets the characteristics of the specified season, insert it into the scene, and scale and rotate it according to the size of the object detected in the scene; use the inserted object as a reference template, combined with the repeated elements found in the scene image Position information, automatically edit and disseminate, generate scene objects of the same type with different sizes and directions with seasonal characteristics; fuse the generated objects with the scene after color conversion, and generate the final scene with specified seasonal characteristics

Images