Fast Learning Artificial Neural Network (FLANN) Based Color Image Segmentation in R-G-B-S-V Cluster Space

In a previous paper, we introduced a biologically inspired binocular vision system, the CogV, that exhibits partial characteristics of human vision and attention. To further the work, the investigation focused onto partitioning the image space into regions of interests that may simulate exogenous attention. The first step for human to perceive an environment is through a series of attention cues that may summon portions of edges, regions, colors, and prevailing thoughts in order to understand the prevailing environment. Through this process, the brain then decides to focus on some region to extract further information from it. This paper proposes a fast color image segmentation algorithm which may be used for vision applications. This approach is based on Fast Learning Artificial Neural Networks (FLANN) clustering and segmentation based on coherence between neighboring pixels. The proposed segmentation algorithm has been incorporated into the existing CogV system as a simplified model that we relate loosely to the superior colliculus (SC). The purpose of this module is to gain an initial overall perception of the environment and highlight regions of interest that the perceptual system may concern itself with. In the process, the SC provides a means to detect exogenous stimuli and thus reducing the initial search domain for object positions.