

The imagery colors of traditional ethnic costumes are unique and have great reference value for modern design. In this paper, 3 representative minority costume images of Miao, Tibetan, and Korean were respectively selected as imagery sources, and 20 different structure types of patterns were chosen as the object to be colored. Image pre-processing, adaptive color extraction, and multi-dimensional features extraction were executed to build a color nexus network model. Based on the color parsing results, an algorithm for color migration of clothing images was designed and developed, which could output multiple types of color schemes. The overall rating of each color scheme was compared to introduce the optimal scheme. Also, the experimental part tested the effect of the color schemes in various scenarios. The average pre-processing time cost of a single image is 0.05 seconds, the output time of the color network diagram is 0.38 seconds, and the output time of a single-color scheme is 1.44 seconds. The study can quickly provide an auxiliary decision for contemporary pattern color design.