Abstract
Advance in technology world has lots of contributions from artificial intelligence which is a highly growing area. The failure of traditional algorithms has led to the employment of deep learning algorithms in various fields like pattern recognition, recommendation systems and classification systems. Removal of noise from images can be done using traditional noise removal filters. These filters can either remove more noise that wanted or leave unwanted noise than what is needed in the data. Utilization of Convolutional neural networks designed based on the dataset requirements along with the noise removal filter can yield better results. In this work, evaluation of the performance of convolutional neural network (CNN) against existing image denoising algorithms has been successfully executed . The proposed model is a generalized CNN model which can recognize and classify any type of noisy image given. Two types of model were compared where one model 1 uses the Adam optimizer and model 2 uses the Stochastic Gradient Descent (SGD) optimizer. The image dataset used here is MNIST handwritten dataset, which is trained, tested and validated with both the models by adding three different types of noise viz, Poisson, Salt and Pepper as well as Gaussian Noise. More accuracy and better results were given by the model 2 which uses the SGD optimizer.
Highlights
Advance in technology world has lots of contributions from artificial intelligence which is a highly growing area
One class of deep neural network, Convolutional Neural Network (CNN), is based on mathematical operation of convolution. 2D CNNs are basically used for the recognition task as the dataset consists of images
Liu et al [4] designed and implemented the de-noising method based on a linear CNN model which will effectively remove Gaussian noise and improves the performance of traditional image filtering methods significantly
Summary
Usage of denoising in convolutional neural networks can generate a modification signal in the info-communication system transmitting a image as proposed by O. Fine-tuning for special filtering tasks can be carried out on a diverse image dataset using pre-trained correction elements. Loss function modification for Denoising Auto-encoders using entropy maximization principle, with constraint conditions of residual statistics has been proposed by Q. S. Suresh et al [3] has proposed a vision based system, a Convolutional Neural Network (CNN) model, which uses the images captured and can identify six different sign languages. Z. Liu et al [4] designed and implemented the de-noising method based on a linear CNN model which will effectively remove Gaussian noise and improves the performance of traditional image filtering methods significantly. Success of signal denoising applications is dependent on the correct selection of right thresholding technique and wavelet family
Sign-in/Register to view highlights & summary 
Published Version (
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