Video Frames Edge Detection of Red Blood Cells: A Performance Evaluation

Abstract

The boundary structure (shape and size) and numbers of Red Blood Cells (RBCs) play a significant role in controlling human physiology. Several blood related diseases including sickle hemoglobin, polycythemia, thalassemia, anemia, and leukemia that occur due to the alteration of RBCs structures need precise detection, analysis, and subsequent inhibition. Diverse boundary analyses that have already been developed to detect the frames edge of blood samples remained ineffective. Thus, an automated system needs to be designed for exact detection of the RBCs edges. The edges being the main features of image often provide vital information to separate regions within an object or to detect changes in illumination. Accordingly, edge detection is regarded as an important step in the analysis of images and extraction of valuable information. In this paper, we evaluated the performance of video frames edge detectors and compared it with different gradient based techniques including Robert, Sobel, Prewitt and Canny, Zero-crossing (Laplacian, Gaussian and fuzzy logic) by applying them on video of RBCs. Two criteria such as mean square error (MSE) and peak signal to noise ratio (PSNR)were exploited to achieve good quality of video frames edge detectors for RBCs. Canny edge and fuzzy logic based techniques revealed the optimum performance towards the detection of video frames edge of RBCs.