基于BP神经网络的轮毂分类与识别算法研究  

Research on Hub Classification and Recognition Algorithm Based on BP Neural Network

作　　者：葛艳[1] 刘杏杏 GE Yan;LIU Xingxing(Institute of Information Science and Technology,Qingdao University of Science and Technology,Qingdao 266061)

机构地区：[1]青岛科技大学信息科学技术学院,青岛266061

出　　处：《计算机与数字工程》2020年第4期748-752,945,共6页Computer & Digital Engineering

基　　金：国家自然科学基金项目(编号:61273180);山东省高等学校科技计划项目(编号:J14LN74)资助

摘　　要：针对传统的基于统计学的轮毂分类识别算法容错性低的问题,论文提出了基于BP神经网络的轮毂分类识别算法。对轮毂图像进行预处理后,使用坐标公式改进的Hough变换算法得到圆心坐标和半径,在此基础上提取其它特征值。构建三层BP神经网络,以轮毂特征值集作为网络的输入,对应的轮毂类型作为网络的输出,通过训练得到轮毂分类模型。实验结果验证了基于BP神经网络的轮毂分类与识别算法的有效性。In order to solve the problem of low fault-tolerance of traditional hub classification and recognition algorithm based on statistics,this paper proposes a hub classification and recognition algorithm based on BP neural network.After the hub image is preprocessed,the center coordinates and radius are obtained by the improved Hough transform algorithm based on coordinate formula,and other feature values are extracted on this basis.The three layer BP neural network is constructed.The feature values of a hub are used as the input of the network,and the corresponding hub type is used as the output of the network,and the hub classification model is obtained by training.The experiment results show the effectiveness of the wheel classification and recognition algorithm based on BP neural network.

关 键 词：轮毂图像预处理 特征提取 BP神经网络 识别分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]