| CPC G06T 7/12 (2017.01) [G06T 3/40 (2013.01); G06T 7/11 (2017.01); G06T 7/60 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30196 (2013.01)] | 17 Claims |

|
1. A method, comprising:
obtaining an original image and obtaining a to-be-processed image based on the original image;
recognizing the to-be-processed image through an image recognition model to obtain a silhouette array, wherein the silhouette array comprises a plurality of silhouette array elements, and the plurality of silhouette array elements comprise a plurality of first values corresponding to a region of interest of the to-be-processed image and a plurality of second values corresponding to a region of non-interest of the to-be-processed image;
generating a silhouette image based on the silhouette array;
generating a target image based on the original image and the silhouette image, wherein the target image corresponds to a region of interest of the original image;
calculating a silhouette matching degree between the silhouette array and a reference array of a reference image; and
inserting the target image into the reference image if the silhouette matching degree between the silhouette array and the reference array of the reference image is greater than a preset threshold.
|