Pre-processing of Image Affected by Contemporaneous Alterations for Surface Measurement of the Human Lymphocyte Micro-Nucleus

摘要

In order to improve the performance of the method based on the cascade of the pattern matching analysis and the blob analysis to recognize and evaluate the surface of the Micro Nucleuses (MNs) into human lymphocytes, the aspects concerning the detection and the correction of the image alterations are investigated. The random alterations considered are those introduced by the movement of the lymphocytes, the optical and the electronic components of the acquisition system of the flow cytometer. The correction method is pointed out in order to: (i) make the image able to be correctly processed by the cascade of the pattern matching analysis and the blob analysis, (ii) minimize the doubtful detections, (iii) enhance the confidence that in the rejected images can not be detected the MNs, and (iv) increase the accuracy of the surface evaluation of MN. Experimental tests confirm the fitness of the detection and the correction method.