基于改进Canny算子的手势图像边缘检测

doi:10.16180/j.cnki.issn1007-7820.2020.07.010

摘要/Abstract

摘要：

针对手势检测不准确,手势边缘检测有偏差等问题,文中提出了一种改进的Canny算子用于检测手势图像边缘。改进的Canny算子使用自适应中值滤波与双边滤波相结合的方法去除图像噪声,并在Sobel的基础上扩展45°和135°方向的梯度幅值计算,自适应获取最佳阈值判别图像边缘。最后,使用哈夫变换与像素点的梯度方向相结合检测边缘,连接边缘、增强边缘。实验表明,改进后Canny算子检测的结果8连通数比传统Canny算子检测的结果8连通数多,边缘连续性较好,检测精度更高且自适应性增强。

关键词: 改进Canny算子, 边缘检测, 降噪, 自适应中值滤波, 哈夫变换检测, 连接边缘

Abstract:

Aim at the problem that the existed gesture detection was inaccurate and the gesture edge detection was deviated, an improved Canny operator was proposed to detect the edge of the gesture image. The improved Canny operator used adaptive median filtering combined with bilateral filtering to remove image noise. On the basis of Sobel, the gradient amplitude calculation in the 45° and 135° directions was extended, and the optimal threshold was adaptively obtained to discriminate the image edge. Finally, the Huff transform combined with the gradient direction of the pixel was used to detect, connect and enhanced the edge. Experiments showed that the results of the improved Canny operator detection were more connected than the traditional Canny operator. The edge continuity was better, the detection accuracy was higher, and the adaptability was enhanced

Key words: improved Canny operator, edge detection, noise reduction, adaptive median filtering, Huff transform detection, connection edge

中图分类号:

TP391

柏丽银,彭亚雄,陆安江. 基于改进Canny算子的手势图像边缘检测[J]. 电子科技, 2020, 33(7): 46-50.

BAI Liyin,PENG Yaxiong,LU Anjiang. Gesture Image Edge Detection Based on Improved Canny Operator[J]. Electronic Science and Technology, 2020, 33(7): 46-50.

图/表 7

图1

图2

图3

表1

图4

图5

表2

参考文献 16

[1]	杨红玲. 基于多特征融合的手势识别技术研究[D]. 南宁:广西民族大学, 2018.
	Yang Hongling. Research on gesture recognition technology based on multi-feature fusion[D]. Nanning: Guangxi University for Nationalities, 2018.
[2]	巨志勇, 王超男. 基于二次曲面拟合的子像素边缘检测算法[J]. 电子科技, 2016,29(6):8-10.
	Ju Zhiyong, Wang Chaonan. Subpixel edge detection algorithm based on quadric surface fitting[J]. Electronic Science and Technology, 2016,29(6):8-10.
[3]	杨少令, 刁燕, 罗华, 等. 一种改进的Canny图像分割算法[J].计算机与现代化, 2018(8):57-60.
	Yang Shaoling, Diao Yan, Luo Hua, et al. An improved Canny image segmentation algorithm[J].Computer and Modernization, 2018(8):57-60.
[4]	徐蕾, 彭月平, 贺科宁. 基于改进双边滤波与随机共振的图像去噪算法研究[J]. 激光杂志, 2018,39(8):142-148.
	Xu Lei, Peng Yueping, He Kening. Research on image denoising algorithm based on improved bilateral filtering and stochastic resonance[J]. Journal of Lasers, 2018,39(8):142-148.
[5]	姒绍辉, 胡伏原, 张伟, 等. 一种改进的双边滤波图像去噪算法[J]. 计算机工程与应用, 2015,51(2):185-189.
	Si Shaohui, Hu Fuyuan, Zhang Wei, et al. An improved bilateral filtering image denoising algorithm[J]. Computer Engineering and Applications, 2015,51(2):185-189.
[6]	吴成茂, 胡伟, 王辉. 小波自适应阈值和双边滤波的图像去噪[J]. 西安邮电大学学报, 2013,18(4):5-8.
	Wu Chengmao, Hu Wei, Wang Hui. Image denoising based on wavelet adaptive threshold and bilateral filtering[J]. Journal of Xi’an University of Posts and Telecommunications, 2013,18(4):5-8.
[7]	钱红莹. 基于改进Canny算子的医学图像边缘检测算法[J]. 软件导刊, 2019,18(2):45-48.
	Qian Hongying. Medical image edge detection algorithm based on improved Canny operator[J]. Software Guide, 2019,18(2):45-48.
[8]	孙妤喆, 卢磊, 罗晓曙, 等. 结合非局部均值滤波的双边滤波图像去噪方法[J]. 广西师范大学学报(自然科学版), 2017,35(2):32-38.
	Sun Yuzhe, Lu Lei, Luo Xiaoshu, et al. Bilateral filter image denoising method combined with nonlocal mean filtering[J]. Journal of Guangxi Normal University(Natural Science Edition), 2017,35(2):32-38.
[9]	许宏科, 秦严严, 陈会茹. 一种基于改进 Canny 的边缘检测算法[J]. 红外技术, 2014,36(3):210-214.
	Xu Hongke, Qin Yanyan, Chen Huiru. An edge detection algorithm based on improved Canny[J]. Infrared Technology, 2014,36(3):210-214.
[10]	易三莉, 张桂芳, 贺建峰, 等. 基于最大类间方差的最大熵图像分割[J]. 计算机工程与科学, 2018,40(10):162-169.
	Yi Sanli, Zhang Guifang, He Jianfeng, et al. Maximum entropy image segmentation based on maximum inter-class variance[J]. Computer Engineering and Science, 2018,40(10):162-169.
[11]	赵芳, 周旺辉, 陈岳涛, 等. 改进的Canny算子在裂缝检测中的应用[J]. 电子测量技术, 2018,41(20):107-110.
	Zhao Fang, Zhou Wanghui, Chen Yuetao, et al. Application of improved Canny operator in crack detection[J]. Electronic Measurement Technology, 2018,41(20):107-110.
[12]	郎俊, 白国振, 周媛. 基于改进的 LVQ 神经网络图像边缘提取研究[J], 电子科技, 2018,31(6):70-74.
	Lang Jun, Bai Guozhen, Zhou Yuan. Research on image edge extraction based on improved LVQ neural network[J]. Electronic Science and Technology, 2018,31(6):70-74.
[13]	杨花雨, 詹华蕊. 基于中值滤波技术的视频图像边缘检测算法[J]. 科学技术与工程, 2019,19(9):143-147.
	Yang Huayu, Zhan Huarui. Video image edge detection algorithm based on median filtering technology[J]. Science Technology and Engineering, 2019,19(9):143-147.
[14]	Gong Y J, Zhou Y, Zhang X. A superpixel segmentation algorithm based on differential evolution[C].Seattle: Proceedings of IEEE International Conference on Multimedia and Expo(ICME), 2016.
[15]	孙智鹏, 邵仙鹤, 王翥, 等. 改进的自适应Canny边缘检测算法[J]. 电测与仪表, 2016,53(6):17-21.
	Sun Zhipeng, Shao Xianhe, Wang Zhu, et al. Improved adaptive Canny edge detection algorithm[J]. Electrical Measurement and Instrumentation, 2016,53(6):17-21.
[16]	向应霞, 丁岳伟. 三阶差分运算与传统图像边缘检测算法的对比分析[J]. 电子测量技术, 2018,41(23):49-54.
	Xiang Yingxia, Ding Yuewei. Comparative analysis of third-order difference operation and traditional image edge detection algorithm[J]. Electronic Measurement Technology, 2018,41(23):49-54.

算法	图3SNR	图3RMSE
未降噪	38.07	2.3e-03
传统Canny算法	52.01	5.78e-04
本文算法	58.08	3.16e-04

手势	1	2	3	4	5
传统Canny算法	1 714	1 664	1 301	1 852	2 064
本文算法	2 330	2 175	1 695	2 224	2 263