Automatic particle focusage method and system based on sparse matrix and storage medium

Abstract

The invention discloses a particle automatic focusage method and system based on a sparse matrix and a storage medium. The method comprises the following steps: performing image collection on a to-be-detected blood sample; preprocessing the collected sample image; performing sparse processing on the preprocessed image according to a sparse matrix; carrying out blood cell motion trail deduction onthe image subjected to the sparse processing; and constructing a focusing recognition model, and recognizing and extracting an automatic focusing area of the blood cells. According to the particle automatic focusage method and system based on the sparse matrix and the storage medium, the focusing area automatic recognition technology of multi-feature + statistical machine learning is adopted, theproblem that single-feature representation is incomplete is avoided, a statistical machine learning model is simple, the calculated amount is low, the cell focusing automatic recognition accuracy is higher, and the robustness is higher.

Description

technical field [0001] The invention relates to the field of blood cell detection, in particular to a sparse matrix-based particle automatic focusing method, system and storage medium. Background technique [0002] Bedside in vitro diagnosis can give rapid diagnosis at the place closest to the patient, and has been extensively and in-depth researched by scholars in recent years. For projects such as biochemical immunity, relevant POCT equipment has already entered the clinic, but the most commonly used blood routine project for in vitro diagnosis is still in the laboratory testing stage. Signal method and image method are currently the main methods of blood cell detection. Among them, the signal method requires many types of equipment, complex circuits, POCT is difficult and costly; the image method is currently the gold standard method for clinical blood routine detection, and the equipment and devices are simple. More suitable for POCTization. However, since human blood ...

AI Technical Summary

Problems solved by technology

However, since human blood cells are suspended cells, the cells are not in the same focal plane during image acquisition, so it is difficult to collect images in which all cells are in focus; high-value blood cells tend to aggregate at the bottom, resulting in slow measurement speed and poor recognition accuracy of image-like blood cell POCT equipment Low

Images