模糊聚类和混沌自适应粒子群的神经网络色彩匹配

目的研究基于混沌理论、粒子群算法、模糊聚类和人工神经网络的色彩匹配模型。方法结合混沌理论和动态自适应策略,对粒子群算法进行改进,得到混沌自适应粒子群算法,并应用于径向基人工神经网络的基函数中心,以及扩展常数和网络权值的优化中;通过模糊聚类分类样本数据,得到混沌自适应粒子群径向基人工神经网络色彩匹配模型,并将模型与其他色彩匹配方法进行比较。结果CSAPSO RBF ANN色彩匹配模型的平均绝对误差、均方根误差和色差平均值分别为0.0106,0.000 96和1.9122。结论 CSAPSO RBF ANN色彩匹配模型具有良好的普遍性、通用性和泛化能力。

Neural Network Color Matching Model Based on Chaotic Self-adaptive Particle Swarm Optimization and Fuzzy Clustering

The aim of this work was to study the color matching model based on chaos theory, particle swarm optimization algorithm, fuzzy clustering and artificial neural network. Particle swarm optimization algorithm was improved by the combined use of chaos theory and adaptive strategy, obtaining the chaotic self-adaptive particle swarm optimization algorithm. The algorithm was then used to optimize the hidden centers, spreads and weights of radial basis function artificial neural network. Fuzzy clustering was used to classify the sample data, to obtain the CSAPSO RBF ANN model, which was then compared with other color matching methods. The average absolute deviation, mean square error and color difference of CSAPSO RBF ANN were 0.0106, 0.000 96 and 1.9122, respectively. The performance of CSAPSO RBF ANN model for color matching was superior with good universality, versatility and generalization ability.