Image annotation method based on small intestine focus characteristics

Abstract

The invention discloses an image annotation method. The method comprises the following steps: determining at least one image block in a to-be-annotated image; respectively determining feature information of each image block, wherein the feature information is used for uniquely representing the corresponding image block; when target feature information matched with reference feature information exists in the feature information, performing annotation on the image block corresponding to the target feature information, so that labeling of a labeling object in the to-be-labeled image is achieved, and the reference feature information corresponds to the labeling object. According to the image annotation mode, the image blocks are automatically annotated, so that the problem that in the prior art, manual annotation is low in efficiency is solved, and a foundation is laid for efficiently obtaining a training sample.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an image labeling method based on features of small intestinal lesions. Background technique [0002] In the research of image processing, the algorithm models proposed for the automatic image annotation problem all rely on the visual feature extraction of the image, while the traditional feature extraction algorithm only extracts various low-level visual features of the image, which reduces the expressive ability of visual features. . In recent years, deep learning has made breakthroughs, which mainly depend on the complex network structure and massive data support. It is difficult for most applications to provide sufficient training samples, which often leads to overfitting of the model and makes the training quality of the model poor. Existing unsupervised learning is not mature enough to be applied to existing deep learning for medical image detection. Through the semi-s...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide an image labeling method based on the characteristics of small intestinal lesions, which aims to solve the problem of slow labeling speed when the amount of labeling is large in the pathological image labeling problem, improve the labeling speed, and speed up model iterative training

Images