Recognition and identification of red blood cell size using Zernike moments and multicolor scattering images

In this paper, a new apparatus device and a novel method for the estimation of the human Red Blood Cells' (RBC) size and shape in the blood, using color scattering images presented. The information retrieval process includes, image normalization, features extraction using the Zernike moments and features dimension reduction using both Independent Component Analysis (ICA) and Principal Component Analysis (PCA). A Radial Basis Neural Network (RBF-NN) estimates the RBC geometrical properties. The proposed method was evaluated in both regression and identification tasks by processing images of simulated device used to acquire scattering phenomena of moving RBCs. The experimental setup consists of a multicolor polarized light source at 570, 587 and 628 nm and moving RBCs in a thin glass. The evaluation database includes 1575 simulated scattering images of 50 × 50 pixels each obtained by a new scattering acquisition device. The regression and identification accuracy of actual RBC sizes is estimated using three feature sets in the presence of additive white Gaussian noise from 60 to 10 dB SNR, giving a mean error rate less than 1 percent of the actual RBC size, and more than 99 percent mean identification rate.