计算机与现代化

• 图像处理 • 上一篇    下一篇

基于K-means聚类和LVQ神经网络的 OLED缺陷像素识别

  

  1. (1.福州大学物理与信息工程学院,福建福州350100;
    2.华南师范大学广东省光信息材料与技术重点实验室,广东广州510006)
  • 收稿日期:2018-12-25 出版日期:2019-07-05 发布日期:2019-07-08
  • 作者简介:纪艳玲(1993-),女,山东烟台人,硕士研究生,研究方向:数字图像处理,机器学习,深度学习,E-mail: m13459181336@163.com; 通信作者:林志贤(1975-),男,教授,博士,研究方向:信息显示技术,平板显示器件驱动和图像处理技术,E-mail: lzx2005000@163.com。
  • 基金资助:
    国家重点研发计划资助项目(2016YFB0401503); 福建省科技重大专项(2014HZ0003-1); 广东省科技重大专项(2016B090906001); 广东省光信息材料与技术重点实验室开放基金资助项目(2017B030301007)

OLED Defective Pixel Recognition Based on K-means Clustering and LVQ Neural Network

  1. (1. College of Physics and Information Engineering, Fuzhou University, Fuzhou 350100, China; 2. Guangdong Provincial Key
     Laboratory of Optical Information Materials and Technology, South China Normal University, Guangzhou 510006, China)
  • Received:2018-12-25 Online:2019-07-05 Published:2019-07-08

摘要: 提出改进的K-means聚类分割和LVQ神经网络分类的方法,用于有机发光二极管显示面板喷墨打印制程中缺陷像素的识别。首先采用改进的K-means聚类算法对预处理后的打印像素进行分割,然后采用连通域水平矩形确定每一个打印像素的坐标及几何特征,再通过灰度共生矩阵提取其纹理特征,最后通过LVQ神经网络对所述特征进行分类,完成缺陷像素的标记及分类统计。结果表明,本文算法的识别率明显优于其他常用分类识别算法,平均缺陷检测率为100%,分类准确率达到98.9%,单像素检测时间为8.3 ms。

关键词: 有机发光二极管, 像素缺陷, K-means聚类, 连通域, 灰度共生矩阵, LVQ神经网络

Abstract: An improved K-means clustering segmentation and LVQ neural network classification method is proposed to identify defective pixels in inkjet printing process of organic light-emitting diode display panels. Firstly, the improved K-means clustering algorithm is used to segment the preprocessed printed pixels, then the connected-domain horizontal rectangle is used to determine the coordinates and geometric features of each printed pixel, and the texture features are extracted by the gray-scale co-occurrence matrix, finally, the features are classified by LVQ neural network to complete the marking and classification statistics of the defective pixels. The results show that the proposed algorithm recognition rate of the article is obviously better than other common classification recognition algorithms, the average defect detection rate of the algorithm is 100%, the classification accuracy rate is 98.9%, and the single pixel detection time is 8.3 ms.

Key words: organic light-emitting diode, pixel defect, K-means clustering, connected domain, gray level co-occurrence matrix, LVQ neural network

中图分类号: