Multi-color recognition based on neighborhood contrast

In this work, we propose a new multi-color recognition method based on color constancy model, and present a realtime machine vision-based auto-sorting system corresponding to academic and industrial needs. The proposed color constancy computation method is computed by neighborhood contrast, and furthermore the relationship between the object color and the color constancy parameters is established. Extensive simulation results show that the proposed color recognition algorithm is robust and efficient, and the sorting system can intelligently and accurately distinguish the multi-color objects under the dynamic natural lighting conditions.