The main intent of this study is for analyzing how image processing filters denoise images of children with autism taken at different times. Digital images usually contain noise during the image capture process and must be preprocessed before they can be used for any purpose. These captured photographs are upgraded with the help of various preprocessing filtering approaches particularly mean, median, Gaussian and FABF filters. The analysis on the working of these images is validated against quality of the picture’s performance metrics such as mean squared error [MSE], peak signal-to-noise ratio [PSNR], and structural similarity index [SSIM]. It is clear from this work that the FABF filter gives superior results compared to other approaches of filtering namely mean filter, median filter, and Gaussian filter used in this work.