End-to-end image segmentation processing method and system

Abstract

The invention relates to the technical field of image processing, and discloses an end-to-end image segmentation processing method and system. The end-to-end image segmentation processing method includes the steps: acquiring an image for testing end-to-end image segmentation processing, and taking the image as a sample image for training; establishing an end-to-end image segmentation network, and using the sample image to perform training learning; and according to an obtained image segmentation network model, segmenting a target image so as to realize segmentation of the target image and outputting the segmentation result of the whole target image for one time. The end-to-end image segmentation processing method has the advantages of being relatively high in accuracy of image segmentation, having no demand for segmenting small images, saving the storage resource of a computer, and reducing the time of preparing images, and can output the segmentation result of the whole image for one time, thus improving the segmentation speed and simplifying the steps of image segmentation.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an end-to-end image segmentation processing method and system. Background technique [0002] Image segmentation is the technology and process of dividing an image into several specific regions with unique properties and proposing objects of interest. [0003] In the existing image segmentation technology, the image segmentation technology based on neural network (take the neural network graph as an example, but not limited to the neural network graph) is better than other algorithms in terms of segmentation performance because of its algorithm characteristics of simulating human perception. There is a significant improvement. However, such methods generally use the mode of cutting into small images for training and learning. The training data needs to be cut into small images to obtain a large number of training samples; correspondingly, the test images must als...

AI Technical Summary

Problems solved by technology

However, such methods generally use the mode of cutting into small images for training and learning. The training data needs to be cut into small images to obtain a large number of training samples; correspondingly, the test images must also be cut into small images of the same size. Figure for testing

Therefore, part of the time is spent in the process of cutting small images in the training process, and most of the time is spent in the process of cutting small images and stitching them into a whole image in the testing process.

Therefore, the existing technical solutions generally have serious time-consuming problems

In addition, the cut small images need to be stored for training, which will also cause a waste of resources such as computer storage.

Images