The goal of the research was to develop a method to automatically detect and count red blood cells in human urine using image processing algorithms. The researchers used Canny Edge Detection and Circle Hough Transform algorithms to identify and count the red blood cells. By setting specific parameters for the size of the cells, they were able to differentiate red blood cells from other types of cells. The automated counting method had an error rate of 9.561% and took an average of 0.4561 seconds per sample, which is faster and more accurate than manual counting by a medical technician.