A General Approach for Color Feature Extraction of Microorganisms in Urine Smear Images

Urinary tract infection is one of the most common bacterial infection in humans and a major cause for outpatient consults. Spotting of pathogens in urine smears is taken to be the first clue that infection is present. In this paper, a new algorithm is proposed for color-feature extraction of microorganisms present in urine smear images. The proposed method was implemented on 60 test image samples. The results indicate that our method is a promising approach towards fully automating segmentation, identification and counting of Candida, Gram-Negative Bacilli and Gram-Positive Cocci in urine smear images.