Image Noise Detection and Classification Based on Combination of Deep Wavelet and Machine Learning

non

Abstract

In the last decade, the number of digital images has increased dramatically. Noise is unwanted particles or signals contaminating the image during the captured image and transmission. Image noise reduces the image quality and increases the processing failure ratio. It is highly recommended to remove the noise, and before removing the noise, we have to know the type of noise, which highly assists in suggesting the proper de-noise algorithm. This study introduces a method to effectively detect and recognize image noise of various types (Gaussian, lognormal, Rayleigh, Salt & Pepper, and Speckle). The proposed model consists of two stages: the first stage is detecting the noise in an image using Convolutional Neural Network. The second stage classifies the noisy images into one of five types of noise using a new method based on a combination of deep wavelet machine learning classifiers, we select five machine learning classifiers (support vector machine, decision tree, random forest, logistic regression, and K-nearest neighbor) to choose the more efficient classifier ultimately. The combination of wavelet with machine learning, specifically SVM, can highly enhance the results, where the accuracy was (91.30 %) through many experiments conducted to build a sturdy classification model.