One way of testing color vision is with a color-blindness plate (CBP) consisting of a set of brilliant colored dots to form a pattern (a figure) and a set of other colored dots to form a background. Classification of such a type of color image into a pattern and a background with a traditional technique is difficult. Based on a self-organizing feature map and a labeling process as well as spatial distance computation, an effective approach to the segmentation of a CBP image is presented. We describe the principle of a CBP segmentation and then introduce the CBP. The proposed approach is described, and its experimental results are presented. We conclude that the method can segment the CBP image into a pattern and a background successfully.
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Denoted as [r(m), g(m), b(m)]T, with each color component in the range from 0 to 255.
To facilitate the spatial distance computation, we renumber the selected six output nodes as k = 1, 2,…, 6. Their corresponding color planes are shown in Figs. 1(d)–1(i), respectively.
Denoted as [r(m), g(m), b(m)]T, with each color component in the range from 0 to 255.
To facilitate the spatial distance computation, we renumber the selected six output nodes as k = 1, 2,…, 6. Their corresponding color planes are shown in Figs. 1(d)–1(i), respectively.