基于改进的PSO进化神经计算进行苹果颜色快速分级

为克服在苹果颜色分级中存在的速度慢、误差大等缺点,基于再现群智能的粒子群进化算法和神经计算技术,提出了一种新颖、快速的智能分级方法,即首先通过计算机视觉技术获取苹果表面颜色的色度,并提取其特征;然后采用改进的带自适应惯性权值的粒子群优化算法训练神经网络结构,最后用训练好的神经网络进行苹果颜色分级。实际应用表明该方法切实可行且效果显著,不仅分级速度快,而且分级正确率高达98%以上。

Apple color grading at high speed based on improved PSO evolutionary neural computation

In order to eliminate the shortcomings in apple color grading,such as slow speed and high error rate,a novel fast intelligent grading method is presented based on the improved particle swarm optimization(PSO) algorithm with adaptive inertia weight and the neural computation technology.The main process is to acquire the colority of apple surface by computer vision technology and to identifity its features,then train the neural network architectures by improved PSO algorithm,and finally grade the apple color with the trained network.The actual application shows that the method can achieve high precision,and get very fast grading speed.In apple color grading,the application effect is very notable.