摘要
针对传统的人工分拣方式效率低和早期机器视觉系统识别成功率不高等问题,基于视觉采集系统联合halcon开发环境,进行不同颜色特征提取,研发高效率、高识别率的根据颜色分类的自动分拣系统。再利用MLP(Multi-Layer Perceptron)多层感知神经网络算法对其进行训练学习、识别分类。实验结果中识别率达到98.75%以上,且算法具有良好的鲁棒性。
Aiming at the problems of low efficiency of traditional manual sorting method and low recognition success rate of early machine vision system,different color features are extracted based on visual acquisition system combined with Halcon development environment,and an automatic sorting system with high efficiency and high recognition rate based on color classification is developed. Then,MLP(multi layer perception) neural network algorithm is used to train and classify them. The experimental results show that the recognition rate is above 98.75%,and the algorithm has good robustness.
作者
陈亮
陈德龙
邓裕鹏
CHEN Liang;CHEN De-long;DENG Yu-peng(School of Mechanical Engineering,Xihua University,Chengdu 610039,China)
出处
《装备制造技术》
2020年第7期68-70,共3页
Equipment Manufacturing Technology
