• Journal of information and communication convergence engineering
• /
• v.5 no.2
• /
• pp.155-158
• /
• 2007

An area distribution of Corneal Endothelial Cell(CEC) include important clinical information. In this paper, we present a two-step processing method of contour complement for the CEC. In the first step; we apply not only conventional Laplasian Gaussian filters(LGF) but also three-arrow-shaped LGFs which is newly developed to extract vertices of hexagonal shapes. In the second step; we complement the lacking part of CEC by using an energy minimum algorithm. Using the results, we measure areas of CEC.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.3
• /
• pp.102-112
• /
• 2013

In this paper, two step processing method of contour extraction and complement which contain hexagonal shape for low contrast and noisy images is proposed. This method is based on the combination of Laplacian-Gaussian filter and an idea of filters which are dependent on the shape. At the first step, an algorithm which has six masks as its extractors to extract the hexagonal edges especially in the corners is used. Here, two tricorn filters are used to detect the tricorn joints of hexagons and other four masks are used to enhance the line segments of hexagonal edges. As a natural image, a corneal endothelial cell image which usually has regular hexagonal form is selected. The edge extraction of hexagonal shapes in corneal endothelial cell is important for clinical diagnosis. The proposed algorithm and other conventional methods are applied to noisy hexagonal images to evaluate each efficiency. As a result, this proposed algorithm shows a robustness against noises and better detection ability in the aspects of the output signal to noise ratio, the edge coincidence ratio and the extraction accuracy factor as compared with other conventional methods. At the second step, the lacking part of the thinned image by an energy minimum algorithm is complemented, and then the area and distribution of cells which give necessary information for medical diagnosis are computed.