马超华, 张团善.基于SURF算法的数码印花缺陷检测系统[J].轻工机械,2021,39(1):52-56 |
基于SURF算法的数码印花缺陷检测系统 |
Digital Printing Defect Detection System based on SURF Algorithm |
|
DOI:10.3969/j.issn.1005 2895.2021.01.010 |
中文关键词: 数码印花 图像处理 加速稳健特征算法 差分算法 |
英文关键词:digital printing image processing SURF(speeded up robust features) algorithm difference algorithm |
基金项目: |
|
摘要点击次数: 519 |
全文下载次数: 0 |
中文摘要: |
针对数码印花生产过程中织物上出现的白丝、斑点以及褶皱等表面缺陷问题,课题组设计了基于加速鲁棒特征算法的印花织物表面缺陷检测系统。主要通过加速稳健特征算法(speeded up robust features,SURF)来进行图像配准;采用双向唯一性匹配法减少误配点,实现图像精准配准,并通过差分算法来提取缺陷信息。实验采用多幅图像对改进SURF算法的性能进行了验证。试验结果表明:新系统对印花织物表面缺陷的检测精度达到98%,达到了实际应用要求。 |
英文摘要: |
In view of the surface defects such as white silk surface, spots, wrinkles and other defects in the process of digital printing, a surface defect detection system for printed fabrics based on accelerated robust feature (SURF) algorithm was designed. The image registration was mainly carried out through the SURF algorithm, the two way unique matching method was used to reduce the mismatch points to realize the accurate image registration, and the difference algorithm was used to extract the defect information. The experimental results of multiple images were used to verify the performance of the improved SURF algorithm. The test results show that the detection accuracy of the designed system on the surface defects of printed fabrics reaches 98%, which conforms to the practical application. |
查看全文 查看/发表评论 下载PDF阅读器 |
关闭 |