Automated recognition of urinary epithelial cells

Urine analysis reveals the presence of many problems and diseases in human body. Manual microscopic urine analysis is time consuming, subjective to human observation, and causes mistakes. Computer aided automatic microscopic analysis can overcome these problems. This paper introduces a comprehensive approach for automating procedures for detecting and recognition of epithelial cells in microscopic urine images. Images were segmented, textural features were extracted, features selection was applied, and five classifiers were tested to get the best results. Repeated experiments were done for adjusting factors to produce the best evaluation results. A very good performance was achieved compared with many related works.