A Method for Extracting Target Candidate Regions Based on Image Background Mask

Abstract

The invention relates to a method for extracting a target candidate region based on an image background mask, comprising the following steps: (1) building an image background mask data set; (2) building a GAN model, and adding a background mask to the image by means of training GAN ; (3) Define the loss function: In order to process the high-frequency structural information details in the image and make the generated image and the training target image as similar as possible, the loss function is defined as the objective function of GAN and the one norm of the synthesized image. The combination of distance loss; (4) model training.

Description

technical field [0001] The invention belongs to the field of target detection and deep learning, and relates to a method for extracting target candidate regions in natural images by applying a generative confrontation network model based on the idea of ​​image masking. Background technique [0002] The extraction of the target candidate area is to find out the area where the target object may exist in the image, which belongs to the category of target detection. Traditional object detection methods usually use a sliding window method. This region selection strategy that traverses the entire image is not targeted, has high time complexity, and has redundant windows. On the basis of region nomination, by using the texture, edge, color and other information in the image, the possible location of the target object in the image can be found in advance. A commonly used region nomination algorithm is the selective search algorithm. [0003] Inspired by the structure of the visual...

AI Technical Summary

Problems solved by technology

Traditional object detection methods usually use a sliding window method. This region selection strategy that traverses the entire image is not targeted, has high time complexity, and has redundant windows.

Images