Fuzzy integration multiple classifier integration-based uterine neck cell image identification method and device

Abstract

The invention provides a fuzzy integration multiple classifier integration-based uterine neck cell image identification method and device. The uterine neck cell image feature identification method comprises the following steps: in step S10, a single uterine neck cell image is subjected to preprocessing operation, edges of cytoplasm and cell nucleuses can be highlighted on the cell image, and a uterine neck cell image background can be removed; in step S20, the preprocessed uterine neck cell image is subjected to improved CV model segmenting operation; in step S30, the segmented uterine neck cell image is subjected to feature extraction operation and then subjected to dimension reduction operation via a genetic algorithm; in step S40, three single classifiers are integrated via fuzzy integration, and then the uterine neck cell image with reduced dimensions is subjected to identifying operation. The uterine neck cell image identification method provided in the invention can be used for precisely segmenting the cytoplasm and the cell nucleuses of uterine neck cells, segmenting speed can be increased, defects of low precision of one single classifier can be compensated by multiple classifier integration, and therefore uterine neck cell identification rate can be improved.

Description

technical field [0001] The invention belongs to the field of medical cell image processing, and in particular relates to a cervical cell image recognition method and a cervical cell recognition device. Background technique [0002] The canceration of cervical cells is a process of continuous development. It generally takes a long time to develop from cervical cell lesions to severe invasive cancer. If it can be diagnosed and treated at an early stage, it is relatively less difficult and less expensive. Cancer, the diagnosis and treatment are very difficult and expensive. In my country, cervical cytology examination has gradually become a routine physical examination item for women, so the number of cell smears in hospitals has increased sharply, which is a new challenge for doctors who read films. desired goal. [0003] In the study of cervical cell identification, due to various factors in the actual production of cells, the obtained smear cells will have adhesion overlaps...

AI Technical Summary

Problems solved by technology

[0003] In the research of cervical cell identification, due to various factors in the actual production process of cells, the obtained smear cells in most cases will have adhesion overlaps, background impurities and inconsistent staining colors, and cervical cell images cannot be obtained. Accurate and effective segmentation leads to inaccurate subsequent feature extraction. At the same time, there are various defects in the use of a single classifier, resulting in misjudgment of the classification results and low recognition accuracy, which is not conducive to the automatic recognition and classification of cervical cell images.

Images