[1]马 栎,冯占荣.doi: 10.3969/j.issn.1001-3849.2025.02.007基于改进Otsu算法的金属器件镀锌表面缺陷识别方法[J].电镀与精饰,2025,(02):46-53.
　Ma Li*,Feng Zhanrong.Improved Otsu algorithm for galvanized surface defect recognition of metal devices[J].Plating & Finishing,2025,(02):46-53.
点击复制

doi: 10.3969/j.issn.1001-3849.2025.02.007基于改进Otsu算法的金属器件镀锌表面缺陷识别方法()

《电镀与精饰》[ISSN:1001-3849/CN:12-1096/TG]

卷:
期数:
2025年02
页码:
46-53
栏目:
出版日期:
2025-02-28

文章信息/Info

Title:
Improved Otsu algorithm for galvanized surface defect recognition of metal devices
作者:
马 栎1; 冯占荣2
(1. 江西工业职业技术学院,江西 南昌 330000 ;2. 南昌航空大学 航空制造工程学院,江西 南昌 330063 )
Author(s):
Ma Li1*;  Feng Zhanrong2
(1. Jiangxi Industry Polytechnic College, Nanchang 330000, China; 2. School of Aeronautical Manufacturing Engineering, Nanchang Hangkong University, Nanchang 330063, China)
关键词:
Otsu算法; 金属器件; 镀锌表面; 缺陷识别; 二阶振荡粒子群优化算法; 最优灰度阈值; Gabor小波 变换
Keywords:
Otsu algorithm;  metal devices;  galvanized surface;  defect identification;  second order oscillatory particle swarm optimization algorithm;  optimal grayscale threshold;  Gabor wavelet transform
分类号:
TP391
文献标志码:
A
摘要:
镀锌表面纹理、颜色以及亮度变化的复杂度往往较高，且不同的光照条件会对金属表面的反射和阴影产生显著影响，当前固定的阈值选择方式难以适应这种复杂多变的识别环境，影响当前人工智能领域中表面缺陷的识别效果，故提出了基于改进Otsu算法的金属器件镀锌表面缺陷识别方法。首先，针对金属器件镀锌表面图像，根据结构张量提取图像的轮廓信息，利用Itti模型提取图像颜色和亮度信息，并分别生成各通道显著图。经规范化处理后，通过线性组合构成视觉显著图，用于初步判断图像中是否存在表面缺陷；然后，在常规的Otsu算法中，引入二阶振荡粒子群优化算法多次调整灰度阈值，利用最优的灰度阈值分割出缺陷区域；最后，利用加权马氏距离表示协方差距离，突出缺陷边缘像素特征，使缺陷兴趣区域更加显著，再采用连通区域标记的方式准确识别表面缺陷。实验结果表明，在金属器件镀锌表面缺陷人工智能识别中，该方法可以准确检索到缺陷区域，识别结果的敏感度和特异性较高。由此可以说明，该方法具有良好的应用效果。
Abstract:
The complexity of texture, color, and brightness changes on galvanized surfaces is often high, and different lighting conditions can have a significant impact on the reflection and shadow of metal surfaces. The current fixed threshold selection method is difficult to adapt to this complex and changing recognition environment, which affects the recognition effect of surface defects in the field of artificial intelligence. Therefore, a method for identifying surface defects on galvanized metal devices based on an improved Otsu algorithm was proposed. Firstly, for the galvanized surface image of metal devices, the contour information of the image was extracted based on the structural tensor. The Itti model was used to extract the color and brightness information of the image, and the saliency maps of each channel were generated separately. After standardization, a visual saliency map was constructed through linear combination to preliminarily determine whether there were surface defects in the image; Then, in the conventional Otsu algorithm, a second-order oscillation particle swarm optimization algorithm was introduced to adjust the grayscale threshold multiple times, and the optimal grayscale threshold was used to segment the defect area; Finally, the weighted Mahalanobis distance was used to represent the covariance distance, highlighting the pixel features of defect edges to make the defect interest region more prominent. Then, the connected region labeling method was used to accurately identify surface defects. The experimental results showed that in the artificial intelligence recognition of surface defects on galvanized metal devices, this method could accurately retrieve the defect area, and the sensitivity and specificity of the recognition results were high. This indicated that the method had good application effects.

参考文献/References:

[1].金泉军, 梁韬, 吕玲芳, 等. 不同腐蚀试验方法对镀锌材料的防腐性能评价研究[J]. 材料保护, 2023, 56(2): 51-56, 76.
[2].桂根生. 车用镀锌钢多维腐蚀分析与评估应用研究[J]. 电镀与精饰, 2021, 43(12): 23-28.
[3].周经中, 王晓芳, 陈云, 等. 输电杆塔用热镀锌钢在模拟东南沿海大气环境中的加速腐蚀试验方法研究[J]. 材料保护, 2021, 54(11): 57-62.
[4].王道累, 刘易腾, 杜文斌, 等. 基于级联孪生密集网络的金属表面缺陷检测方法[J]. 计算机辅助设计与图形学学报, 2022, 34(6): 946-952.
[5].王一, 龚肖杰, 程佳, 等. 基于改进YOLOv5的金属工件表面缺陷检测[J]. 包装工程, 2022, 43(15): 54-60.
[6]. Jiang Y F, Zhou X, Zhang W Y. A surface defect detection method for rolling magnesium alloy sheet based on computer vision[J]. Metalurgija, 2021, 60(1-2): 63-66.
[7]. Chen W, Zou B, Yang J Z, et al. The machined surface defect detection of improved superpixel segmentation and two-level region aggregation based on machine vision[J]. Journal of manufacturing processes, 2022, 80(8): 287-301.
[8]. 南柄飞, 郭志杰, 王凯, 等. 基于视觉显著性的煤矿井下关键目标对象实时感知研究[J]. 煤炭科学技术, 2022, 50(8): 247-258.
[9]. Sun X M, Han Y, Chen Y, et al. Aerial image defogging method based on nonlocal feature structure tensor by UAV cameras with three-channel RGB cameras[J]. Journal of Applied Remote Sensing, 2022, 16(4): 1-17.
[10]. 胡荣明, 苏瑞鹏, 竞霞, 等.融合改进小波去噪与T-Taylor的井下定位算法[J]. 测绘通报, 2023(2): 46-51.
[11]. 霍银磊, 裴学胜, 李梦瑶. 曲梁缓冲器的大变形及变形能的椭圆函数解[J]. 振动与冲击, 2023, 42(3): 43-49.
[12]. 闫本超, 潘如如, 周建, 等. 基于改进Itti显著模型的织物疵点实时检测[J]. 纺织学报, 2023, 44(7): 95-102.
[13]. 赵川翔. 590 MPa级低合金高强度热镀锌钢板表面亮点缺陷分析[J]. 金属热处理, 2022, 47(6): 270-273.
[14]. 陈浩然, 范方辉, 牟天. 基于OTSU图像分割算法的碎米检测[J]. 食品研究与开发, 2023, 44(20): 175-183, 8.
[15]. 海涛, 程沛源, 杨嘉芃, 等. 基于二阶振荡粒子群优化算法的最大功率跟踪[J]. 科学技术与工程, 2022, 22(26): 11402-11408.
[16]. 姚宏, 于七龙, 那琳. 基于粒子群优化算法-广义回归神经网络的磷化膜耐蚀性预测模型[J]. 电镀与精饰, 2021, 43(11): 1-6.
[17]. Mejjaoli H, Shah, F A. A new class of uncertainty principles for the Gabor transform[J]. International journal of geometric methods in modern physics, 2022, 19(7): 19-41.
[18]. 唐励勤, 刁节涛, 陈长林, 等. 面向大规模卷积计算的多忆阻器阵列互连结构设计[J]. 国防科技大学学报, 2023, 45(5): 222-230.
[19]. 文娟. 应用加权马氏距离与退化模型预测丝杠副寿命[J]. 高技术通讯, 2023, 33(9): 957-966.

更新日期/Last Update: 2025-02-19