Image detection method and device, electronic equipment and medium

Abstract

The invention relates to the artificial intelligence technology, and discloses an image detection method. The method comprises: carrying out feature extraction of different scales on a to-be-detectedimage by using a feature pyramid network, and then obtaining a plurality of fine feature maps of different scales; performing feature distillation on the fine feature map by using a pre-constructed feature distillation sub-network to generate a to-be-extracted feature map; extracting a to-be-detected region in the to-be-extracted feature map by using a pre-constructed region extraction network, and generating a prediction bounding box of the to-be-detected region; and performing classification identification on the to-be-detected area to obtain an identification result, performing regression positioning on the prediction bounding box to obtain a positioning result, and performing marking in the to-be-detected image according to the identification result and the positioning result to obtaina detection result of the to-be-detected image. The invention also relates to a blockchain technology, and the to-be-detected image can be stored in a blockchain. According to the invention, the function of automatically detecting the focus in the image can be realized.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an image detection method, device, electronic equipment and computer-readable storage medium. Background technique [0002] In the field of medicine, intelligent detection of target areas in images through artificial intelligence, image processing and other methods can assist doctors in disease diagnosis and provide reliable imaging indicators for the formulation of treatment plans. [0003] However, the current intelligent analysis and processing of OCT images of the anterior segment mainly focuses on the segmentation of corneal tissue, and there is no research on the automatic detection of multiple lesions in OCT of the anterior segment using deep learning methods. Contents of the invention [0004] The invention provides an image detection method, device, electronic equipment and computer-readable storage medium, the main purpose of which is to realiz...

AI Technical Summary

Problems solved by technology

[0003] However, at present, the intelligent analysis and processing of anterior segment OCT images mainly focus on the segmentation of corneal tissue, and there is no research on the automatic detection of multiple lesions in anterior segment OCT using deep learning methods.

Images