Research On The Automatic Identification Of Parasitic Ovum Microscopic Image Based On Machine Vision

With the development of computer technology and the widely use of interdisciplinary in various fields,microscopic image automatic identification technology based on machine vision has also got rapid development in the medical field,which not only provides a reliable and efficient tool for clinical diagnosis,but also is convenience for the medical scientific research and teaching.The parasitic eggs detection is one of the important detections in the medicine,the traditional detection of parasite eggs mostly by manual microscopy,which is not only inefficient and has highintensity working,but also is subject to influence by the operator,and is unable to save complete case data,not conducive to clinical dynamic observation.Automatic detection based on machine vision is not only efficient,non-polluting,and adapt the requirements of modern medical information development.Based on the former research of parasite eggs and microscopic image recognition,this paper mainly studies the process of particles in parasite eggs microscopic image from the acquisition to the identification based on machine vision.The main contents are as follows:1.The hardware structure of the parasitic eggs microscopic image automatic identification system based on machine vision are emphatically discussed.The hardware structure includes the automatic acquisition device of parasitic eggs specimen,the automatic film device of microscope,the design of lighting system,CCD camera and image capture card and so on.2.According to the characteristics of high noise in the microscopic image of parasite eggs,the method of image preprocessing and segmentation is studied,an improved two-dimensional maximum entropy threshold genetic algorithm combined with mathematical morphology is proposed.This method can segment the parasitic eggs microscopic image effectively,the segmentation method is more accurate and fast.3.The features of several common types of parasitic eggs microscopic image are in detail introduced,and the feature extraction method is also studied.Then a set of feature vector is appropriate determined and regarded as the input of parasitic eggs microscopic image according the contrast.It can represent the characteristics of all kinds of parasitic eggs microscopic image.4.Several intelligent recognition algorithms are studied,such as the theory of BP(Back Propagation)neural network and SVM(Support Vector Machine).Accordingto the extracted features of parasitic eggs microscopic image,an automatic identification classifier based on BP neural network and support vector machine is designed respectively.The accuracy of their respective identification is counted.Then the results of classification of the two classifiers are compared,from which the high precision and efficiency classifier is elected.Through the research and experiment in this paper,it is proved that the automatic identification techniques based on machine vision are feasible,effective which has a certain practical value in medicine.