Abstract
Digital Image Processing is a method to obtain image or to take out useful details or feature from image. The noise will cause the results of error in the image acquisition process. Generation of higher noise levels in the low light condition environment will often result in oversmoothed edges and textures during the denoising process because of lower signal levels in the image. Thus, this study goal is to improve denoising techniques for Poisson noise removal in low light condition for surveillance images. The Patch-Based Noise Level Estimator is designed to estimate the noise level of noisy image. The noisy image then fed to either OTSU WIE-WATH Filter or OTSU KU-WIE-WATH Filter automatically based on the noise level of image. The OTSU WIE-WATH Filter is used for low and medium Poisson noise removal while OTSU KU-WIE-WATH Filter is used mainly for high Poisson noise removal. The proposed denoising technique performances are analyzed with other existing denoising techniques in terms of Mean Absolute Error (MAE), computational time and visual effect inspection. The results verified that proposed technique is effective in removing different level Poisson noise in low light condition surveillance images.
Highlights
Digital image processing techniques help in manipulation of the digital images by using computers
OTSU WIEWATH Filter and OTSU KU-WIE-WATH Filter [4] that proposed recently improve the performance of eliminated the Poisson noise in an effective way
The noise estimation denoising technique developed by combining Patch-based Noise Level Estimator for noise estimation with the OTSU WIE-WATH Filter [4] and OTSU KU-WIE-WATH Filter [4] to eliminate the Poisson noise effectively in real application
Summary
Digital image processing techniques help in manipulation of the digital images by using computers. Smaller sensors in the camera resulting in generation of higher noise levels [2]. This will often result in oversmoothed edges and textures during the denoising process because of lower signal levels in the image. There are two types of image denoising model, linear model and non-linear model. Linear model (e.g. Mean Filter and Wiener Filter) are commonly used for image denoising. The models usually unable to preserve edges of the images in an efficiently. Non-linear models (e.g. Bilateral Filter, Median Filter, Maximum Filter and Minimum Filter) are known to be effective in preserving edges in a much better way than linear models but slower since they are usually computationally expensive [3]. The filter allows the noisy pixels in the dark regions to be removed while preserving the texture regions to avoid over smoothing of test images
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
