Multicolor recognition based on mini-max color threshold

Abstract

This paper discusses the multi-color recognition using the min-max color threshold for outdoor robot navigation. All colors used in this project are RGB orthogonal color space in order to see how much of each primary color between min and max that can be observed in the color to be recognized. The white color value in the color space is set as the object for which the target color to be recognized belongs, while the black color value is set as the object background. The recognition process is done by summing up first the values of the red, green and blue in each color to obtain the rgb sum value, which is then divided by the individual color element to obtain the color threshold. This threshold is compared to the originally color threshold for the recognition, where a satisfactory result is expected as the project is not yet finished.