Segmentation and recognition of color‐dot characters with complex background

Abstract

AbstractAs an example of character recognition from overlapping data, this paper presents the recognition of Ishihara's color vision test chart, where a color character composed of color dots is embedded in a background composed of color dots. The histogram is constructed on the normalized tri‐color coordinate, and the representative color is determined as the maximal point of the histogram. The distance pattern is constructed based on the representative colors, and the shape skeleton is extracted by the DP matching between the distance pattern and the category dictionary. The line width and the final position are determined by an examination based on the variance criterion. It is shown that the DP matching is useful in the hypothesis testing for the object, where both the background and the character are multivalued color textures.