Random weight network partitioning method for blood leukocyte microscopic image

Abstract

The invention discloses a random weight network partitioning method for a blood leukocyte microscopic image. The automatic partitioning technology is composed of four sub-processes of category coding and training library establishment, random weight network training, decoding partitioning and morphological operator repair, blood leukocyte partitioning is converted into classification, the leukocyte microscopic image is automatically partitioned in a classified mode, and integral and communicated cytoplasm and cell nucleus zones are acquired. The method has the advantages that the effective categories of pixel points of the blood leukocyte image are coded, a stable blood leukocyte classification training library is established, an optimal coding decision making model is acquired through a quick and efficient random weight network, an optimal code of the leukocyte image to be partitioned is acquired, and a final partitioning result is acquired. By the adoption of the method, the leukocyte microscopic image is efficiently partitioned.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a random weight network segmentation method of blood white blood cell microscopic images. Background technique [0002] The classification, recognition and counting of blood leukocytes play an important role in the clinical diagnosis and treatment of viral or fungal infections, tumors and AIDS. It is undoubtedly a boring, time-consuming and labor-intensive task to classify and count manually, which puts forward requirements for automatic identification of blood leukocyte microscopic images. [0003] The automatic classification of blood leukocytes mainly includes three steps: cell segmentation, feature extraction and classification realization. Among them, cell segmentation is the key, and the quality of cell segmentation directly affects the effect of subsequent feature extraction and classification. [0004] The current leukocyte segmentation methods have defects in va...

AI Technical Summary

Problems solved by technology

[0004] The current white blood cell segmentation methods have various defects in terms of practicability and complexity.

For example, although the segmentation method based on color histogram and the segmentation method based on Schmidt orthogonalization are simple and fast, they cannot segment the cytoplasmic region; while the method based on watershed and active contour model has complicated steps, and The effect of segmentation depends on the microscopic image of blood leukocytes; although the method based on multispectral image technology can obtain an effective segmentation of leukocyte components, it takes a lot of money

Therefore, these methods do not meet the actual application requirements of leukocyte segmentation, which puts forward an urgent demand for new fast and effective blood leukocyte segmentation methods

Images