This paper deals with the segmentation problem of cervical cell images. Knowing that the malignity criteria appear on the morphology of the core and the cytoplasm of each cell, then, the goal of this segmentation is to separate each cell on its component, that permits to analyze separately their morphology (size and shape) in the recognition step, for deducing decision about the malignity of each cell. For that. we use a multifractal algorithm based on the computation of the singularity exponent on each point of the image. For increasing the quality of the segmentation, we propose to add an optimization step based on genetic algorithms. The proposed processing has been tested on several images. Herein, we present some results obtained by two cervical cell images.

Recently, the clinical role of image processing has been developed considerably. The resources of this new technology were exploited for the needs of doctors in their practice. In this study, we propose a computer vision for tracking the uterine collar cancer. Here, we present three stages: preprocessing, segmentation, and classification. The segmentation stage uses a multifractal algorithm based on the computation of the singularity exponents; its role is separating each cell on its core and its cytoplasm, which permits the analysis of each one in the recognition stage for deducing a response about the malignity of the cell. However, the classification is performed by an algorithm of area growth. Knowing that there are four layers in the epithelium, the classification allows for learning the type of each cell in an image for organizing the research in the recognition stage. Thus, we contribute to the creation of a database for the recognition stage. This base contains the core and cytoplasm images with information about the type of each cell. Promising results were obtained with a short execution time that permits the start of the recognition stage.

No abstract

No abstract

We present in this paper the design of a frequency selective surface (FSS) with developed curvilinear coordinate based method (C-method) and Genetic Algorithms (GAs). The C-method analyzes the rough surface and transforms the boundary-value problem to scalar Eigen equation that is solved in the spectral domain. In addition, the study of the reflectivity of a stack constituted by this rough surface and dielectric layers necessitates the development of the S-matrix algorithm and shooting method. Because the GAs are powerful in the exploration of the research spaces, in the hope to minimize the reflectivity over the studied frequency band, the synthesis with GAs is used and allows for the determination of the appropriate geometry characteristics and material properties. We present numerical results in the X band frequency.