Method and device for detecting target object in image, electronic equipment and readable storage medium

Abstract

The invention relates to the technology of image detection, and discloses a method for detecting a target object in an image, and the method comprises the steps: obtaining a target object detection model comprising a classification screening sub-model, a shared coding sub-model and a detection sub-model, and carrying out the coding of a training image set through the shared coding sub-model, and the classification screening sub-model is utilized to screen the coding features obtained by coding, the detection sub-model is utilized to perform target object detection on the screening result, thetarget object detection model is optimized according to the detection result and the standard result of the training image, and the optimized standard object detection model is utilized to perform image detection on the to-be-detected target object image. Detection results are obtained. In addition, the invention also relates to a blockchain technology, and the training image set can be stored ina node of a blockchain. The invention further provides a device for detecting the target object in the image, electronic equipment and a computer readable storage medium. According to the invention, the problem that the accuracy is low when the target object detection is carried out on the image can be solved.

Description

technical field [0001] The present invention relates to the technical field of image detection, in particular to a method, device, electronic equipment and computer-readable storage medium for object detection in an image. Background technique [0002] In the information age, with the enrichment and development of electronic products, myopia has become a burden on global public health. High myopia among myopia patients is likely to cause macular retinopathy, and then develop into pathological myopia. Therefore, a medical method based on detection of target objects such as patchy atrophy and retinal detachment in color photos of the fundus has been produced. [0003] Most of the existing methods for detecting objects in images rely on deep learning models to analyze images to detect objects in images. This method is too dependent on the quality of the image, but the image quality is often not guaranteed in practical applications, resulting in the model missing the detection ...

Images