Detection and Counting of Red Blood Cells in Human Urine using Canny Edge Detection and Circle Hough Transform Algorithms

Abstract

Integration of image processing in order to detect red blood cells (RBCs) in human urine enables technology to reduce medical technician’s manual counting time and error factor. The general objective of this study was to detect and count the red blood cells in human urine using Canny Edge Detection (CED) and Circle Hough Transform (CHT) algorithms. CED is an edge detection algorithm used in order to identify a great variety of edges in an image. CHT is one of the features of the Hough Transform. Specifically, CHT is used in order to detect circular objects. The basis of the CHT operation will be dependent on the circular edges detected by the CED. In order to identify a specific circle size, the minimum and maximum radius must be set. Particularly, to differentiate the RBCs from other cells such as white blood cells. For this study, the minimum radius was 4 pixels while the maximum was 6. Compared to the manual counting of a medical technician, the automated counting of the device produced a percent error of 9.561% and an average counting time of 0.4561 seconds per sample.