Application of improved wavelet threshold de-noising algorithm in work piece inspection

Image de-noising is an important step to improve the AOI (automated optical inspection) image quality of automobile work piece. After analyzing the theory of wavelet transform and the characteristics of traditional soft and hard wavelet threshold de-noising methods, an improved threshold de-noising method was proposed. The new method overcomes the discontinuous in hard threshold de-noising method and reduces the permanent bias in soft threshold de-noising method. At last hard threshold de-noising, soft threshold de-noising method and improved threshold de-noising are used to reduce noises in the same image of workpiece. The results show that the improved threshold method is superior to the traditional soft and hard wavelet threshold de-noising methods in decreasing RMSE and improving PSNR.