Textural analysis of bio-images for aid in the detection of abnormal blood cells

摘要

The parameters extraction defined by Haralick in textural analysis of bio-images often precedes a decision step to be able to distinguish normal or defective tissues, healthy or pathological biological cells and the types of defects. In this paper, we focus on the textural analysis of medical images, in order to detect abnormal blood cells using grey-level co-occurrence matrix (GLCM). The textural analysis is performed by quantifying correlations and relationships between grey levels of pixels depending on the distance. Our purpose is to develop a method based on the computation of Haralick's textural parameters in order to characterise and analyse blood cells by statistical methods. The main goal is to provide textural analysis to help haematologists to make a precise diagnosis allowing to identify anomalies by distinguishing healthy and abnormal cells which can be considered as potential cancerous cells: The results described in Figures 3-7 show one set of significant experimental results which are useful to differentiate between healthy and abnormal cells, and where the strong main parameter is the energy.