Infrared Image Segmentation for Electrical Equipment based on Fuzzy Inference
-
摘要: 使用模糊理论处理电气设备红外图像分割的不确定性,提出了一种基于模糊推理的电气设备红外图像分割算法。首先分别利用电气设备红外图像故障区域的像素灰度、像素点与图像质心的马氏距离以及图像膨胀操作定义了强度特征、全局故障可能性特征和局部灰度特征;然后根据特征的模糊语言值制定了27条模糊规则,设计了一种模糊推理红外图像分割算法;最后,从主观和客观评价指标上将算法与传统Otsu算法和FCM算法进行了对比。实验表明,该算法的分割精度和误分割率比其他两种算法都有一定的改善,同时该算法能够滤除图像中具有高亮度的干扰区域,对具有小亮度差和小面积故障区域的红外图像有较好的分割效果。Abstract: Fuzzy theory is considered to address the uncertainty of infrared image segmentation of electrical equipment, and a new algorithm based on fuzzy inference for infrared image segmentation of electrical equipment is proposed in this paper. First, the intensity, global fault probability, and local grayscale features were defined using the pixel grayscale of the fault region in the infrared image of the electrical equipment, Mahalanobis distance between pixel points, image center of mass, and image dilation operation. Subsequently, 27 fuzzy rules were formulated based on the fuzzy language values of the features, and an infrared image segmentation algorithm based on fuzzy inference was designed. Finally, the algorithm was compared with the traditional Otsu and FCM algorithms in terms of subjective and objective evaluation indexes. Further, the experimental results show that the segmentation accuracy and misclassification error of the proposed algorithm are better than those of the other two algorithms. The algorithm can filter out interference regions with high luminance in infrared images, and exhibits a better segmentation effect on infrared images with small luminance differences and small fault areas.
-
Key words:
- fuzzy inference /
- infrared image segmentation /
- Mahalanobis distance /
- image dilation
-
表 1 基于多特征改进的模糊规则
Table 1. Fuzzy rules based on multi-feature improvement
Intensity characteristic Global failure possibility characteristics Local gray distributioncharacteristics Failure membership characteristics 1 small small small small 2 small small medium small 3 small small big medium 4 small medium small small 5 small medium medium medium 6 small medium big medium 7 small big small small 8 small big medium small 9 small big big big 10 medium small small medium 11 medium small medium medium 12 medium small big medium 13 medium medium small medium 14 medium medium medium medium 15 medium medium big big 16 medium big small medium 17 medium big medium medium 18 medium big big big 19 big small small medium 20 big small medium medium 21 big small big medium 22 big medium small medium 23 big medium medium medium 24 big medium big big 25 big big small medium 26 big big medium medium 27 big big big big 表 2 算法评价指标对比
Table 2. Algorithm evaluation index comparison
-
[1] 苏海锋, 赵岩, 武泽君, 等. 基于改进RetinaNet的电力设备红外目标精细化检测模型[J]. 红外技术, 2021, 43(11): 1104-1111. http://hwjs.nvir.cn/article/id/3233a6a1-cbf0-4110-baa5-2a56e551f092SU Haifeng, ZHAO Yan, WU Zejun, et al. Refined infrared object detection model for power equipment based on improved RetinaNet[J]. Infrared Technology, 2021, 43(11): 1104-1111. http://hwjs.nvir.cn/article/id/3233a6a1-cbf0-4110-baa5-2a56e551f092 [2] 陈飞. 改进的交互式Otsu红外图像分割算法[J]. 计算机测量与控制, 2020, 28(9): 248- 251. https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK202009049.htmCHEN Fei. An improved interactive Otsu infrared image segmentation algorithm[J]. Computer Measurement & Control, 2020, 28(9): 248-251. https://www.cnki.com.cn/Article/CJFDTOTAL-JZCK202009049.htm [3] YU X, ZHOU Z, GAO Q, et al. Infrared image segmentation using growing immune field and clone threshold[J]. Infrared Physics & Technology, 2018, 88: 184-193. http://www.sciencedirect.com/science/article/pii/S1350449517306308 [4] 冯振新, 周东国, 江翼, 等. 基于改进MSER算法的电力设备红外故障区域提取方法[J]. 电力系统保护与控制, 2019, 47(5): 123-128. https://www.cnki.com.cn/Article/CJFDTOTAL-JDQW201905015.htmFENG Zhenxin, ZHOU Dongguo, JIANG Yi, et al. Fault region extraction using improved MSER algorithm with application to the electrical system[J]. Power System Protection and Control, 2019, 47(5): 123-128. https://www.cnki.com.cn/Article/CJFDTOTAL-JDQW201905015.htm [5] HU F, CHEN H, WANG X. An intuitionistic Kernel-based fuzzy C-means clustering algorithm with local information for power equipment image segmentation[J]. IEEE Access, 2020, 8: 4500-4514. doi: 10.1109/ACCESS.2019.2963444 [6] QI C, LI Q, LIU Y, et al. Infrared image segmentation based on multi-information fused fuzzy clustering method for electrical equipment[J]. International Journal of Advanced Robotic Systems, 2020, 17(2): 1729881420909600. http://www.xueshufan.com/publication/3009600905 [7] WEI D, WANG Z, SI L, et al. An image segmentation method based on a modified local-information weighted intuitionistic Fuzzy C-means clustering and gold-panning algorithm[J]. Engineering Applications of Artificial Intelligence, 2021, 101: 104209. doi: 10.1016/j.engappai.2021.104209 [8] BAI X, LIU M, WANG T, et al. Feature based fuzzy inference system for segmentation of low-contrast infrared ship images[J]. Applied Soft Computing, 2016, 46: 128-142. doi: 10.1016/j.asoc.2016.05.004 [9] 王力斌, 刘树伟. 基于模糊推理的油门防误踩系统控制研究[J]. 控制工程, 2020, 27(8): 1462-1467. https://www.cnki.com.cn/Article/CJFDTOTAL-JZDF202008026.htmWANG Libin, LIU Shuwei. Research on the control system of preventing false stepping the accelerating pedal based on the fuzzy theory[J]. Control Engineering of China, 2020, 27(8): 1462-1467. https://www.cnki.com.cn/Article/CJFDTOTAL-JZDF202008026.htm [10] 张洪群, 顾吟雪, 郭擎. 灰色关联分析与模糊推理边缘检测图像融合法[J]. 遥感信息, 2020, 35(1): 15-27. https://www.cnki.com.cn/Article/CJFDTOTAL-YGXX202001003.htmZHANG Hongqun, GU Yinxue, GUO Qing. Image fusion based edge detection of grey relational analysis and fuzzy inference[J]. Remote Sensing Information, 2020, 35(1): 15-27. https://www.cnki.com.cn/Article/CJFDTOTAL-YGXX202001003.htm [11] Vijayakumar S, Santhi V. Speckle noise reduction in SAR images using fuzzy inference system[J]. International Journal of Fuzzy System Applications (IJFSA), 2019, 8(4): 60-83. [12] Arya K V. A new fuzzy rule based pixel organization scheme for optimal edge detection and impulse noise removal[J]. Multimedia Tools and Applications, 2020, 79(45): 33811-33837. doi: 10.1007/s11042-020-08707-x?utm_source=xmol&utm_content=meta [13] BAI X, CHEN Z, ZHANG Y, et al. Infrared ship target segmentation based on spatial information improved FCM[J]. IEEE Transactions On Cybernetics, 2015, 46(12): 3259-3271. http://ieeexplore.ieee.org/document/7026038/ [14] LONG J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015: 3431-3440.