Biological tissue image detection method, device, equipment and medium

Abstract

The biological tissue image detection method provided by the embodiment of the invention is used for a computer vision technology (CV). The method comprises: acquiring a first biological tissue image;determining image feature information of the first biological tissue image through a classification model; when the classification model identifies that the image feature information of the first biological tissue image does not meet the digestive tract detection condition, removing the first biological tissue image; when the classification model identifies that the image feature information of the first biological tissue image meets the digestive tract detection condition, transmitting the first biological tissue image to a detection model; and detecting the first biological tissue image through the detection model. The invention further provides a device, equipment and a medium, low-quality images are filtered out through classification of the classification model, so that it is ensuredthat the detection model only detects high-quality biological tissue images, and the detection efficiency and the detection accuracy of biological tissue image detection are improved under the condition that an existing detection model is not rewritten.

Description

technical field [0001] The present invention relates to the field of electronic technology, and more specifically, to a biological tissue image detection method, device, equipment and medium. Background technique [0002] Computer vision technology (computer vision, CV) is a science in artificial intelligence (AI) technology that studies how to make machines "see". Furthermore, it refers to the use of cameras and computers instead of human eyes to monitor the target. Machine vision such as recognition, tracking and measurement, and further graphics processing, so that computer processing becomes an image that is more suitable for human eyes to observe or sent to the instrument for detection. As a scientific discipline, computer vision studies related theories and technologies, trying to build artificial intelligence systems that can obtain information from images or multidimensional data. Computer vision technology usually includes technologies such as image processing, ima...

AI Technical Summary

Problems solved by technology

[0004] Among them, gastrointestinal endoscopy usually includes disease screening in the esophagus, throat, stomach, duodenum, and colorectum. In the human digestive system, the internal environment is diverse, and saliva, air bubbles, food residual, etc., so the endoscopic image cannot guarantee a clear, clean, high-quality image

Due to the similarities (shape, color, etc.) between foreign bodies such as saliva, air bubbles, and food residues and lesions, in the prior art, deep learning models are prone to misjudgment of foreign bodies and lead to false positives when predicting diseases. , which reduces the accuracy of disease detection

Images