Image classification and display method and device, analysis instrument and storage medium

Abstract

The invention discloses an image classification and display method and device, an analysis instrument and a storage medium. The method includes: calculating the similarity between the segmented image to be identified and each target component category in the target component set; using the component category to which the maximum similarity belongs as the initial component category of the segmented image to be identified; displaying the segmented image to be identified in the initial In the frame selection area of ​​the component category; in response to the segmented image to be identified being selected, the top n similarities with the highest numerical values ​​among the multiple similarities and their component categories are displayed, so as to determine the final component category of the segmented image to be identified. By adopting the technical solution in the embodiment of the present invention, the component category can be further discriminated based on the image processing result, and the accuracy rate of image component recognition can be improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an image classification and display method and device, an analysis instrument and a storage medium. Background technique [0002] With the expansion of the application of image processing technology in the medical field, more and more medical devices need to realize their functions based on image processing technology. Taking the urine sediment analyzer as an example, its working principle is: the urine sample is photographed by a camera into an image sequence, and then image processing technology is used to realize the segmentation and identification of the formed components in each image. While improving the detection efficiency of the equipment, there are also Help reduce the workload of doctors. There are many formed elements in urine, including: red blood cells, white blood cells, crystals, sperm, hyaline casts, pathological casts, etc. And in addition to the form...

AI Technical Summary

Problems solved by technology

For component images with small grayscale pixel differences and morphological differences, it is difficult to accurately identify them only by image processing technology. How to further distinguish component categories based on image processing results has become an urgent problem to be solved.

Images