The Research Of Key Techniques For Auto Recognition Tuberculosis Cells

In these years, incidence of tuberculosis is rising gradually. Lots of information has shown that: once tuberculosis is diagnosed, 80 pencent of them has belonged to advanced stage and most patients have lost the good chance to be cured. It has become a key problem to detect and cure the cases in their early stage. So timely diagnoses and timely therapy have become the questions for impendency.Image recognition is an important task in Digital Image Processing. Also it plays an essential role in Computer Aided Diagnosis. Applying image recognition technology to diagnosis can improve the identity of diagnosis and reduce the subjectivity and partially replace the doctor's work. Cell analysis is an important way to pre- tuberculosis diagnosis. We can use cell images to do cytology quantitative analysis, improve the recognition ratio of pre-tuberculosis. So it is a complex and important task for both medical field and image processing field.In this paper, based on lots of researching of the present technology fruits, the microscopic images of bacilli the tuberculosis cells fallen into are processed, and features are extracted from them. Then use the Bayes classifier,...