Detection of Defects in Process Balls Based on BP Neural Network

Li Gang; Wang Renhuang; Li Pei

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Detection of Defects in Process Balls Based on BP Neural Network

更新时间：2026-05-27

- Detection of Defects in Process Balls Based on BP Neural Network
- Vol. 29, Issue 1, Pages: 46-49(2012)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Online First：25 March 2012，
  
  Published：2012
- 稿件说明：
移动端阅览
李刚, 汪仁煌, 李佩. 基于BP神经网络的工艺球缺陷检测[J]. 广东工业大学学报, 2012, 29(1): 46-49.

Li Gang, Wang Renhuang, Li Pei. Detection of Defects in Process Balls Based on BP Neural Network[J]. 2012, 29(1): 46-49.
李刚, 汪仁煌, 李佩. 基于BP神经网络的工艺球缺陷检测[J]. 广东工业大学学报, 2012, 29(1): 46-49. DOI：

Li Gang, Wang Renhuang, Li Pei. Detection of Defects in Process Balls Based on BP Neural Network[J]. 2012, 29(1): 46-49. DOI：

摘要

对羽毛球工艺球图像经过预处理，得到缺陷形状信息图像.提取图像的5个极半径不变矩特征、圆心度、球体外圆和球头圆心偏差总共7个特征参数构成图像特征向量组，建立三层结构的BP神经网络，以这7个不变量特征值组成的特征向量归一化后作为神经网络的输入，根据神经网络的输出进行缺陷检测，实验结果证明了该方法能有效地用于羽毛球工艺球的缺陷检测.

Abstract

The image of the information about the shape of defects in the shuttlecock process ball was obtained after pretreatment of the images of the shuttlecock process ball. Then

the five polar-radius moment invariants

circularity

and the difference between the cylindrical part and the center of the ball in processed images were extracted. The seven normalized eigenvalues were input into the BP neural network

based on Levenberg-Marquardt algorithm

and the trained network was used to be a detector to recognize the image pattern. Experimental results show that a relatively good recognition performance can be achieved to detect defects in shuttlecock process balls.

关键词

Keywords

references

韩斌，徐之，王士同. 离散不变矩的比例不变性研究[J]. 数据采集与处理，2008，23（5）：555-558.

曹茂永，孙道银，郁道银. 用于模式识别的极半径不变矩[J]. 计算机学报，2004，27（6）：861-864.

张惠斌，方欣欣. 基于极半径不变矩的平面单足足迹识别[J]. 电子测量技术， 2009，32（12）：72-76.

Wohler C，Anlauf J K. Real-time object recongnition on image sequences with the adaptable time delay neural network algorithm-applications for autonomous vehicles [J]. Image and Vision Computing，2001，19（10）：593-168.

李国祥，张显全，秦芳远. 基于不变矩和BP神经网络的剪纸纹样识别[J]. 计算机工程与应用，2010，46（29）：158-160.

秦钟. 基于图像不变矩特征和BP神经网络的车型分类[J]. 华南理工大学学报：自然科学版，2009，37（2）：86-90.

成诚. 基于不变矩的PDF417条码检测算法的研究[J]. 计算机科学，2009，36（4）：237-238.

韩英莉，颜云辉. 基于BP神经网络的带钢表面缺陷的识别与分类[J]. 仪器仪表学报，2006，26（12）：1692-1694.

曾子铭，韩忠华，刘春光，等. 基于扇形特征和BP神经网络算法的字符识别[J]. 沈阳建筑大学学报，2009，32（12）：604-608.

吴一全，武燕燕，唐艳亮. 利用Krawtchouk矩不变量实现基于形状的图像检索[J] . 光电工程，2010，37（5）：97-103.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Surface Defect Detection of Lithium Battery Electrodes Based on Improved Unet Network

A Fault Diagnosis Method of Wind Turbine Gearbox Based on BP Neural Network Optimized by Crisscross Optimization Algorithm

Design of Multi-parameter Classifying System in Ceramic Tiles Based on M achine Vision

Neural Network Face Recognition Based on Length Extension Technique

Research and Implementation of a Pulsed Laser Ranging Method Based on Digital Mixing

Related Author

Chen Xiao-rong

Yang Xue-rong

Cheng Si-yuan

Liu Guo-dong

Ma Liu-yang

Meng An-bo

Ge Jia-fei

ZOU Qing-Sheng

Related Institution

School of Electromechanical Engineering, Guangdong University of Technology

School of Automation, Guangdong University of Technology

AI问答

⁰