计算机科学与探索 ›› 2014, Vol. 8 ›› Issue (9): 1041-1048.DOI: 10.3778/j.issn.1673-9418.1405007

• 综述·探索 • 上一篇    下一篇

表面缺陷检测综述

罗  菁1,2,董婷婷1,2+,宋  丹1,2,修春波1,2   

  1. 1. 天津工业大学 电工电能新技术天津市重点实验室,天津 300387
    2. 天津工业大学 电气工程与自动化学院,天津 300387
  • 出版日期:2014-09-01 发布日期:2014-09-03

A Review on Surface Defect Detection

LUO Jing1,2, DONG Tingting1,2+, SONG Dan1,2, XIU Chunbo1,2   

  1. 1. Key Laboratory of Advanced Electrical Engineering and Energy Technology, Tianjin Polytechnic University, Tianjin 300387, China
    2. School of Electrical Engineering and Automation, Tianjin Polytechnic University, Tianjin 300387, China
  • Online:2014-09-01 Published:2014-09-03

摘要: 基于机器视觉的表面缺陷检测技术已经广泛地应用在视觉检测各个领域中,它是确保自动化生产中产品质量的一个非常重要的环节。然而表面缺陷检测技术仍然面临着缺陷和非缺陷区域之间的低对比度,噪音和细微缺陷的相似性,检测速度慢和识别精度低等难题。为此,给出了近年来表面缺陷检测技术的最新进展。将表面检测技术分为3类:统计法、频谱法和模型法。对几种典型的表面缺陷检测技术进行了深入比较,包括特征提取、识别算法和算法性能,并分析了方法有效性的原因。最后,总结了表面缺陷检测技术面临的挑战和未来的发展趋势。

关键词: 表面检测, 缺陷检测, 缺陷分类, 质量控制

Abstract: Surface defect detection based on machine vision has been widely used in the various fields, which is important for ensuring the product quality during automatic production. However, there are some challenges on the surface inspection, such as low contrast, shape similarity between defect regions and non-defect regions, tiny defect detection, inspection speed and accuracy. So, this paper gives the recent advances in surface defect detection. The surface defect detection is categorized into three types: statistics, spectrum and model approach. Then this paper compares several typical approaches in detail, including feature extraction, detecting algorithms and the performance of the algorithms, and analyzes the effectiveness of the algorithms deeply. Finally, this paper summarizes the challenge and future trend.

Key words: surface detection, defect detection, defect classification, quality control