计算机工程与应用 ›› 2019, Vol. 55 ›› Issue (7): 188-193.DOI: 10.3778/j.issn.1002-8331.1805-0238

• 图形图像处理 • 上一篇    下一篇

基于联合稀疏变换学习的工件去噪方法研究

刘秀平1,薛婷婷1,韩丽丽2,杜勇辰1,张凯兵1,闫焕营3   

  1. 1.西安工程大学 电子信息学院,西安 710048
    2.西安理工大学 机械与精密仪器学院,西安 710048
    3.深圳罗博泰尔机器人有限公司,广东 深圳 518109
  • 出版日期:2019-04-01 发布日期:2019-04-15

Denoising Based on Union-of-Transforms Learning for Workpieces

LIU Xiuping1, XUE Tingting1, HAN Lili2, DU Yongchen1, ZHANG Kaibing1, YAN Huanying3   

  1. 1.College of Electronices and Information, Xi’an Polytechnic University, Xi’an 710048, China
    2.College of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, China
    3.Shenzhen Municipal Robotel Robot Technology Co., Ltd., Shenzhen, Guangdong 518109, China
  • Online:2019-04-01 Published:2019-04-15

摘要: 针对视觉测量中给光好坏会直接影响工件检测精度和效率的问题,提出了一种基于联合稀疏变换学习对不同光源下工件图像去噪的方法。该方法首先从噪声图像中提取噪声图像块,通过稀疏编码和稀疏变换更新交替运算对噪声图像块进行内部聚类变换学习;然后计算每个噪声图像块中聚类信号的稀疏水平,并选择最小稀疏水平作为该去噪块的稀疏水平;最后对去噪块进行聚类并用最后一次迭代去噪块的均值估计去噪图像。实验结果表明,提出的方法对不同光源下工件图像的去噪效果和计算速度均优于其他算法,具有较好的去噪性能。

关键词: 联合稀疏变换学习, 光源, 工件图像, 去噪块

Abstract: As the quality of light in visual measurement will directly affect the accuracy and efficiency of workpiece detection, to address the problem, an approach is proposed to denoise the workpiece image under different light sources with union-of-transforms learning. The proposed method firstly extracts the noise image patches from noise images, and studies the intra-cluster transform learning of the noise patches by alternated between sparse coding and transform update steps. Next, the transform sparse levels of clustering signal in each noise patch are calculated, and the minimum sparse level is selected as the sparse level of the denoising patches. Finally, denoised patches are clustered and the denoised image is estimated by the mean value of the final iterative denoised patches. The experimental results show that the proposed mothed is superior to the other algorithms in terms of both denoising effect and algorithm speed for workpiece images under different light sources, and gains better denoise performance.

Key words: union-of-transforms learning, light sources, workpieces pictures, denoising patches