计算机工程 ›› 2018, Vol. 44 ›› Issue (6): 249-252,258.doi: 10.19678/j.issn.1000-3428.0046599

• 图形图像处理 • 上一篇    下一篇

基于词袋特征算法的药品分层缺陷检测

刘玉环 1,唐庭龙 2,陈胜勇 1,2   

  1. 1.天津理工大学 计算机与通信工程学院,天津 300384; 2.浙江工业大学 计算机科学与技术学院,杭州 310023
  • 收稿日期:2017-03-30 出版日期:2018-06-15 发布日期:2018-06-15
  • 作者简介:刘玉环(1991—),女,硕士研究生,主研方向为图像处理、模式识别、机器学习;唐庭龙,博士研究生;陈胜勇,教授。
  • 基金项目:
    国家自然科学基金(U1509207)。

Defect Inspection of Hierarchical Drug Based on Feature of Bag Algorithm

LIU Yuhuan  1,TANG Tinglong  2,CHEN Shengyong  1,2   

  1. 1.School of Computer and Communication Engineering,Tianjin University of Technology,Tianjin 300384,China; 2.School of Computer Science and Technology,Zhejiang University of Technology,Hangzhou 310023,China
  • Received:2017-03-30 Online:2018-06-15 Published:2018-06-15

摘要: 在制药领域,人工检测药品速度慢、效率低,而图像处理的方法需要大量样本且适应性差。针对以上问题,提出特征提取与机器学习相结合的方法,介绍用于目标区域特征提取的词袋特征(BOF)算法,分析BOF算法的最佳参数取值,并采用支持向量机对药品分层缺陷进行分类检测。实验结果表明,该方法能使药品达到较高的分类精度,并且满足工业生产实时检测的要求。

关键词: 药品分层, 缺陷检测, 特征提取, 机器学习, 词袋模型, 支持向量机

Abstract: During the pharmaceutical process,manual inspection suffers from time consuming and inefficiency.Image processing method needs plenty of samples and has poor adaptability.To address these problems,a method based on feature extraction and machine learning is developed.The Bag of Feature(BOF) algorithm is introduced to extract the features of the target region and its optimum parameter value is analyzed.Support Vector Machine(SVM) is applied to inspect the defects of the hierarchical drug.Experimental results show that the proposed method can achieve higher classification accuracy and meet the requirements of real-time inspection in the process of industrial production.

Key words: hierarchical drug, defect inspection, feature extraction, machine learning, Bag of Word(BOW)model, Support Vector Machine(SVM)

中图分类号: