An Image Denoising and Enhancement Algorithm for Inner and Outer Ring of Wavelet Bearings Based on Improved Threshold
Jingjuan Liang, Jun Zhao, Yongxin Hao · Journal of Physics Conference Series · 2018
In the bearing inner and outer ring surface defect detection, the traditional wavelet threshold algorithm is general effective for image processing of bearing images with insufficient illumination or uneven illumination. This paper proposes a method to improve the wavelet denoising enhancement of the threshold function. Firstly, the multilevel decomposition of bearing image is carried out by wavelet;Furthermore, adopted the improved algorithm and adaptive algorithm respectively to conduct the denoising enhancement for the first to third levels of wavelet coefficients;Finally, the wavelet coefficients and scaling coefficients are processed by wavelet inverse transform. Experiments showed that this algorithm can effectively denoise and enhance the contrast of images, processing images with good results,which is better than the traditional enhancement algorithms.