作者：赵新秋1,2, 秦昆阳1, 冯斌1, 贺海龙1
作者单位：1. 燕山大学 河北省工业计算机控制工程重点实验室, 河北 秦皇岛 066004;
2. 燕山大学 国家冷轧板带装备及工艺工程技术研究中心, 河北 秦皇岛 066004
关键词：边缘检测;小波变换;模糊推理;自适应阈值;边缘细化
摘要：
针对传统模糊推理边缘检测算法存在抗噪性能差、边缘为非单像素边缘等缺点，提出一种基于模糊推理的边缘检测新方法。首先根据全向小波变换获得4个方向的小波变换幅值，并将该幅值作为模糊推理系统输入；然后通过比较解模糊之后的值和自适应阈值得到二值边缘图像，再细化边缘得到最终边缘图像。实验结果表明：与传统微分算法和模糊推理算法相比，该算法对图像中噪声和伪边缘的抑制以及边缘提取的完整性都具有很好的效果。
Edge detection algorithm based on fuzzy inference
ZHAO Xinqiu1,2, QIN Kunyang1, FENG Bin1, HE Hailong1
1. Key Laboratory of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao 066004, China;
2. National Engineering Research Center for Equipment and Technology of Cold Strip Rolling, Yanshan University, Qinhuangdao 066004, China
Abstract: For the shortcomings of traditional fuzzy inference edge detection algorithm, such as anti-noise performance is poor and the edge is not a single pixel edge, a new edge detection method based on fuzzy inference is proposed. Firstly, the wavelet transform amplitude in four directions is obtained based on the omni-directional wavelet transform and then the amplitude is input as the fuzzy inference system. Then, by comparing the value after defuzzification with the adaptive threshold, the binary edge image is obtained and then the edge is thinned to get a final edge image. The experimental results show that the algorithm has a good effect on the suppression of noise and pseudo edge in the image and the integrity of the edge extraction compared with the traditional differential algorithm and the fuzzy inference algorithm.
Keywords: edge detection;wavelet transform;fuzzy inference;adaptive threshold;edge thinning
2018, 44(5): 1-5 收稿日期: 2017-10-08;收到修改稿日期: 2017-12-09
基金项目: 河北省自然科学基金（F2016203249）
作者简介: 赵新秋(1969-),女,吉林辽源市人,副教授,博士,研究方向为冶金综合自动化、智能控制。
参考文献
[1] HAQ I, ANWAR S, SHAH K, et al. Fuzzy logic based edge detection in smooth and noisy clinical images[J]. Plos One,2015,10(9):e0138712.
[2] WU Y Q, ZHU L, HAO Y B, et al. Edge detection of river in SAR image based on contourlet modulus maxima and improved mathematical morphology[J]. Transactions of Nanjing University of Aeronautics and Astronautics,2014,31(5):478-483.
[3] 崔丽群,张月,田鑫. 融合双阈值和改进形态学的边缘检测[J]. 计算机工程与应用,2017,53(9):190-194.
[4] HAN D S, KIM H S. A novel implementation of rotation detection algorithm using a polar representation of extreme contour point based on sobel edge[J]. Journal of Semiconductor Technology Andence,2016,16(6):800-807.
[5] HU J P, TONG X, XIE Q, et al. An improved feature-centric LoG approach for edge detection[C]//International Conference on Computational Science and Its Applications,2016.
[6] 陈颖峰,李金文,张婕. 模糊推理在边缘检测中的应用[J].中国测试,2014,40(1):33-35.
[7] MELIN P, GONZALEZ C I, CASTRO J R, et al. Edge-detection method for image processing based on generalized type-2 fuzzy logic[J]. IEEE Transactions on Fuzzy Systems,2014,22(6):1515-1525.
[8] DU Y, TONG M, ZHOU L, et al. Edge detection based on retinex theory and wavelet multiscale product for mine images[J]. Applied Optics,2016,55(34):9625-9637.
[9] 李哲涛,李仁发,谢井雄. 基于全向小波的图像边缘检测算法[J]. 电子学报,2012,40(12):2451-2455.
[10] 易三莉,郭贝贝,马磊,等. 改进的模糊推理规则图像边缘检测算法[J]. 计算机工程与应用,2016,52(12):180-183.
[11] 许宏科,秦严严,潘勇. 一种改进的边缘细化方法[J]. 激光与红外,2014,44(3):319-324.
