基于ORB改进的图像匹配套准系统  

Image Matching and Registration System Based on Improved ORB

作　　者：赵梓平 徐长波 

机构地区：[1]北京印刷学院信息工程学院,北京

出　　处：《图像与信号处理》2025年第1期92-99,共8页Journal of Image and Signal Processing

摘　　要：为了解决当前国内市场中多色套印技术在曲面丝网印刷中的精确对准难题,研究提出了一种基于ORB图像匹配算法的多色套印系统,该系统结合了几何约束和RANSAC筛选算法,使传统曲面丝网印刷不再局限于单色制品,满足了市场对高质量、多色印刷日益增长的需求。通过实验验证了系统的有效性,结果表明匹配正确率超过95%,处理速度达26帧/秒,色板套印精度控制在± 0.03毫米以内。这种方法显著提升了复杂多色图案在曲面物体上的印刷质量和精度,具备广泛的应用前景。To address the challenges of precise alignment in multi-color overprinting for curved surface screen printing in the domestic market, this study proposes a multi-color overprinting system based on the ORB image matching algorithm, incorporating geometric constraints and the RANSAC filtering algorithm. This approach extends traditional curved surface screen printing beyond single-color applications, meeting the increasing market demand for high-quality, multi-color printing. Experimental results verify the system’s effectiveness, demonstrating a matching accuracy rate exceeding 95%, a processing speed of 26 frames per second, and an overprinting accuracy within ± 0.03 mm. This method significantly enhances the print quality and precision of complex multi-color patterns on curved objects, with broad application potential.

关 键 词：曲面丝网印刷 多色套印 图像匹配 ORB算法 RANSAC筛选 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]