基于元学习的小样本图像非对称缺陷检测方法

doi:10.13229/j.cnki.jdxbgxb20211301

摘要/Abstract

摘要：

以准确检测小样本图像非对称缺陷为研究核心，提出基于元学习的小样本图像非对称缺陷检测方法。使用基于调制度的小样本图像自适应滤波方法，去除小样本图像的噪声，优化小样本图像质量；通过基于边界检测的滤波后小样本图像缺陷特征提取方法，提取滤波后小样本图像缺陷特征；将所提取特征作为基于改进元学习的小样本图像非对称缺陷特征检测方法的检测样本，实现小样本图像非对称缺陷检测。实验结果表明：本文方法对小样本图像滤波效果较好，检测多种非对称缺陷时，当小样本图像缺陷特征数量增多后，本文方法的检测结果交并比最小值是0.9，交并比数值理想，可准确检测小样本图像非对称缺陷。

关键词: 元学习, 小样本, 图像, 非对称, 缺陷检测, 梯度下降法

Abstract:

Taking the accurate detection of asymmetric defects in small sample images as the research core， a small sample image asymmetric defect detection method based on meta learning is proposed. The adaptive filtering method of small sample image based on modulation is used to remove the noise of small sample image and optimize the quality of small sample image； Through the defect feature extraction method of filtered small sample image based on boundary detection， the defect feature of filtered small sample image is extracted； The extracted features are used as the detection samples of the small sample image asymmetric defect feature detection method based on improved meta learning to realize the small sample image asymmetric defect detection. The experimental results show that the proposed method has good filtering effect on small sample images. When detecting a variety of asymmetric defects， when the number of defect features of small sample images increases， the minimum value of intersection and union ratio of this method is 0.9， and the value of intersection and union ratio is ideal， which can accurately detect asymmetric defects of small sample images.

Key words: meta learning, small samples, image, asymmetric, defect detection, gradient descent method

中图分类号:

TP391.4

黄彭奇子,段晓君,黄文伟,晏良. 基于元学习的小样本图像非对称缺陷检测方法[J]. 吉林大学学报(工学版), 2023, 53(1): 234-240.

Peng-qi⁃zi HUANG,Xiao-jun DUAN,Wen-wei HUANG,Liang YAN. Asymmetric defect detection method of small sample image based on meta learning[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(1): 234-240.

图/表 10

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

参考文献 15

1	蔡彪, 沈宽, 付金磊,等.基于Mask R-CNN的铸件X射线DR图像缺陷检测研究[J].仪器仪表学报, 2020, 41(3): 61-69.
	Cai Biao, Shen Kuan, Fu Jin⁃lei, et al. Research on defect detection of X-ray DR images of casting based on Mask R-CNN[J]. Chinese Journal of Scientific Instrument, 2020, 41(3): 61-69.
2	张红岩, 王永志, 刘庆红.图像识别技术在食品包装缺陷检测中的应用[J].食品与机械, 2020, 36(8): 225-228.
	Zhang Hong-yan, Wang Yong-zhi, Liu Qing-hong. Application of image recognition technology in food packaging defect monitoring[J]. Food and Machinery, 2020, 36(8): 225-228.
3	马浩鹏, 朱春媚, 周文辉, 等.基于深度学习的乳液泵缺陷检测算法[J].液晶与显示, 2019, 34(1): 81-89.
	Ma Hao-peng, Zhu Chun-mei, Zhou Wen-hui, et al. Defect detection algorithm of lotion pump based on deep learning[J]. Chinese Journal of Liquid Crystals and Displays, 2019, 34(1): 81-89.
4	王昕钰, 王倩, 程敦诚, 等.基于三级级联架构的接触网定位管开口销缺陷检测[J].仪器仪表学报, 2019, 40(10): 74-83.
	Wang Xin-yu, Wang Qian, Chen Dun-cheng, et al. Detection of split pins defect in catenary positioning tube based on three-level cascade architecture[J]. Chinese Journal of Scientific Instrument, 2019, 40(10): 74-83.
5	杨正伟, 谢星宇, 李胤, 等.激光扫描热成像无损检测关键参数影响分析[J].红外与激光工程, 2019, 48(11): 91-101.
	Yang Zheng-wei, Xie Xing-yu, Li Yin, et al. Influence analysis of key parameters in laser scanning thermography nondestructive testing[J]. Infrared and Laser Engineering, 2019, 48(11): 91-101.
6	戴铭, 叶木超, 周智恒, 等.基于先验分布活动轮廓模型的纹理缺陷检测[J].控制与决策,2020, 35(5): 1226-1230.
	Dai Min, Ye Mu-chao, Zhou Zzhi-heng, et al. Texture defects detection based on prior distribution active contour model[J]. Control and Decision, 2020, 35(5): 1226-1230.
7	于重重, 萨良兵, 马先钦, 等.基于度量学习的小样本零器件表面缺陷检测[J]. 仪器仪表学报, 2020, 41(7): 214-223.
	Yu Chong-chong, Liang-bing Sa, Ma Xian-qin,et al. Few-shot parts surface defect detection based on the metric learning[J]. Chinese Journal of Scientific Instrument, 2020, 41(7): 214-223.
8	袁桂霞, 周先春.基于分类和模糊滤波的X光图像椒盐噪声滤除算法[J].计算机应用研究, 2019, 36(1): 299-302.
	Yuan Gui-xia, Zhou Xian-chun. Salt and pepper noise filtering algorithm for X-ray images with multi-level classification and fuzzy filtering[J]. Application Research of Computers, 2019, 36(1): 299-302.
9	武昊男, 储成群, 任勇峰, 等.基于FPGA的图像自适应加权均值滤波设计[J].电子技术应用, 2019, 45(3): 32-35, 41.
	Wu Hao-nan, Chu Cheng-qun, Ren Yong-feng, et al. Self-adaption image weighted mean filter design based on FPGA[J]. Journal of Electronic Technology Application, 2019, 45(3): 32-35, 41.
10	方斌, 周辉奎, 陈家益, 等.去除脉冲噪声的快速开关中值图像滤波[J].控制工程, 2021, 28(6): 1243-1249.
	Fang Bin, Zhou Hui-kui, Chen Jia-yi, et al. A Fast switching median image filter for impulse noise removal[J]. Control Engineering of China, 2021, 28(6): 1243-1249.
11	罗凯鑫, 吴美平, 范颖.基于最大熵方法的鲁棒自适应滤波及其应用[J]. 系统工程与电子技术, 2020, 42(3): 667-673.
	Luo Kai-xin, Wu Mei-ping, Fan Yin. Robust adaptive filtering based on maximum entropy method and its application[J]. Journal of Systems Engineering and Electronics, 2020, 42(3): 667-673.
12	吴一全, 邹宇, 刘忠林.基于Franklin矩的亚像素级图像边缘检测算法[J].仪器仪表学报, 2019, 40(5): 221-229.
	Wu Yi-quan, Zhou Yu, Liu Zhong-lin. Sub-pixel level image edge detection algorithm based on Franklin moments[J], Journal of Scientific Instrument, 2019, 40(5): 221-229.
13	罗元, 王薄宇, 陈旭.基于深度学习的目标检测技术的研究综述[J]. 半导体光电, 2020, 41(1): 1-10.
	Luo Yuan, Wang Bo-yu, Chen Xu. Research progresses of target detection technology based on deep learning[J]. Semiconductor Optoelectronics, 2020, 41(1): 1-10.
14	罗会兰, 陈鸿坤.基于深度学习的目标检测研究综述[J].电子学报, 2020, 48(6): 1230-1239.
	Luo Hui-lan, Chen Hong-kun. A review of object detection study based on deep learning[J]. Acta Electronica Sinica, 2020, 48(6): 1230-1239.
15	刘尚争, 刘斌, 高庆华.关于多维图像Criminisi自适应识别仿真研究[J].计算机仿真, 2020, 37(6): 379-382, 447.
	Liu Shang-zheng, Liu Bin, Gao Qing-hua. Simulation study on criminisi adaptive recognition of multidimensional images[J]. Computer Simulation, 2020, 37(6): 379-382, 447.

相关文章 15

[1]	郭现峰,李浩华,魏金玉. 基于Fibonacci变换和改进Logistic-Tent混沌映射的图像加密方案[J]. 吉林大学学报(工学版), 2023, 53(7): 2115-2120.
[2]	刘培勇,董洁,谢罗峰,朱杨洋,殷国富. 基于多支路卷积神经网络的磁瓦表面缺陷检测算法[J]. 吉林大学学报(工学版), 2023, 53(5): 1449-1457.
[3]	张振海,季坤,党建武. 基于桥梁裂缝识别模型的桥梁裂缝病害识别方法[J]. 吉林大学学报(工学版), 2023, 53(5): 1418-1426.
[4]	姜宇,潘家铮,陈何淮,符凌智,齐红. 基于分割方法的繁体中文报纸文本检测[J]. 吉林大学学报(工学版), 2023, 53(4): 1146-1154.
[5]	白琳,刘林军,李轩昂,吴沙,刘汝庆. 基于自监督学习的单目图像深度估计算法[J]. 吉林大学学报(工学版), 2023, 53(4): 1139-1145.
[6]	王俊杰,农元君,张立特,翟佩臣. 基于施工场景的视觉关系检测方法[J]. 吉林大学学报(工学版), 2023, 53(1): 226-233.
[7]	赵宏伟,张健荣,朱隽平,李海. 基于对比自监督学习的图像分类框架[J]. 吉林大学学报(工学版), 2022, 52(8): 1850-1856.
[8]	申铉京,张雪峰,王玉,金玉波. 像素级卷积神经网络多聚焦图像融合算法[J]. 吉林大学学报(工学版), 2022, 52(8): 1857-1864.
[9]	曲福恒,丁天雨,陆洋,杨勇,胡雅婷. 基于邻域相似性的图像码字快速搜索算法[J]. 吉林大学学报(工学版), 2022, 52(8): 1865-1871.
[10]	李娜,谭韶生. 基于空间邻域信息的击剑连续动作图像分割[J]. 吉林大学学报(工学版), 2022, 52(7): 1639-1644.
[11]	王震,盖孟,许恒硕. 基于虚拟现实技术的三维场景图像表面重建算法[J]. 吉林大学学报(工学版), 2022, 52(7): 1620-1625.
[12]	王生生,姜林延,杨永波. 基于最优传输特征选择的医学图像分割迁移学习[J]. 吉林大学学报(工学版), 2022, 52(7): 1626-1638.
[13]	杨怀江,王二帅,隋永新,闫丰,周跃. 简化型残差结构和快速深度残差网络[J]. 吉林大学学报(工学版), 2022, 52(6): 1413-1421.
[14]	刘铭,杨雨航,邹松霖,肖志成,张永刚. 增强边缘检测图像算法在多书识别中的应用[J]. 吉林大学学报(工学版), 2022, 52(4): 891-896.
[15]	贾海洋,夏睿,吕安祺,管噌璇,陈娟,王雷. 基于模板融合的超声医学影像全景拼接方法[J]. 吉林大学学报(工学版), 2022, 52(4): 916-924.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed