Image processing method, device, equipment and readable storage medium

Abstract

The invention discloses an image processing method, device, equipment and a readable storage medium. The image processing method includes: receiving an image to be processed, and performing region division processing on the image to be processed to obtain each region of interest; calling a pre-stored full convolutional network structure model to detect each region of interest to obtain each region of interest. A probabilistic image segment, wherein the pre-stored fully convolutional network structure model includes a fully convolutional structure that replaces a linear regression layer with an equivalent convolutional layer, and the pre-stored fully convolutional network structure model removes the full-volume The blank filling operation layer and the up-sampling layer in the product structure; performing synthesis processing on each probability image segment to obtain the target probability image. The invention solves the technical problem of high calculation redundancy in the high-density prediction process of the existing pathological images, resulting in low processing efficiency of the pathological images.

Description

technical field [0001] The present invention relates to the field of image technology, in particular to an image processing method, device, equipment and readable storage medium. Background technique [0002] At present, the specific process of pathological image processing mostly uses a sliding window frame to continuously slide to intercept picture blocks, and input the intercepted picture blocks into a specific convolutional neural network (Convolutional Neural Networks, CNN for short) to obtain each image block. The predicted values ​​of the blocks are finally spliced ​​to form the entire probability map. However, due to the continuous sliding of the sliding window frame to intercept the picture blocks, there are inevitably overlapping redundant areas, which leads to high calculation redundancy in the prediction process, resulting in the pathological image. The processing efficiency is low. Contents of the invention [0003] The main purpose of the present invention i...

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to provide an image processing method, device, equipment and readable storage medium, aiming to solve the technical problem of high computational redundancy in the probability prediction process of the existing pathological images, resulting in low processing efficiency of pathological images

Images