中国机械工程2025，Vol.36Issue(9)：2039-2046,8.DOI:10.3969/j.issn.1004-132X.2025.09.016
快速单曝光高动态范围高反光金属表面缺陷辨识算法研究
Research on Rapid Single-exposure HDR Defect Recognition Algorithm for Highly Reflective Metal Surfaces
摘要
Abstract
A rapid single-exposure HDR defect recognition algorithm was proposed for highly reflec-tive metal surfaces.This algorithm was based on detail enhancement techniques and CycleGAN.The in-put low dynamic range(LDR)images were first converted to HSV color space and processed with guided filtering to obtain luminance and detail layers.The CycleGAN network was then used to enhance the dy-namic range of these layers separately.The enhanced luminance and detail layers were weighted and fused,followed by filtering and denoising to produce an HDR image suitable for defect recognition.Defects were identified in the HDR image using threshold segmentation,feature selection,and morphological process-ing.This single-exposure algorithm was experimentally compared with three classic single-exposure algo-rithms and one multi-exposure algorithm.The evaluation was based on five metrics:peak signal-to-noise ratio(PSNR),image entropy,processing time,gray histograms,and recognition results.The experimen-tal results indicate that the algorithm herein outperforms three other single-exposure algorithms in effec-tively addressing overexposure issues,achieving results comparable to multi-exposure algorithms.Addi-tionally,it has a shorter processing time,making it suitable for online detection.Furthermore,this algo-rithm demonstrates superior capability in extracting image detail information compared to other algorithms,resulting in higher accuracy in recognition.关键词
高反光金属/单曝光高动态范围成像/细节增强/循环一致性生成对抗网络Key words
highly reflective metal/single-exposure high dynamic range(HDR)imaging/detail en-hancement/cycle-consistent generative adversarial network(CycleGAN)分类
信息技术与安全科学引用本文复制引用
贾维昊,王鹏,陈凯,仝飞,王国彪..快速单曝光高动态范围高反光金属表面缺陷辨识算法研究[J].中国机械工程,2025,36(9):2039-2046,8.基金项目
宁波市重大科技任务攻关项目(2022Z055) （2022Z055）
