Detection of Red Blood Cell in Urine Micrograph

The classical method of red cells examination in urine micrograph is counted by manpower, which has the following deficiencies such as low efficiency, strong subjectivity and poor reliability. This paper focuses on the detection of red blood cells in urine image captured under microscope by image processing. After the urine image is preprocessed by improved Sobel operator, red blood cells are localized using Hough transform and their features, which are extracted and selected by principal component analysis (PCA), can be classified with LDA (linear discriminant analysis). It provides a reliable and convenient detective method for medical research.