Learning Deep Gradient Descent Optimization for Image Deconvolution

This paper presents deblurring of image using the convolutional neural network (CNN) model in deep learning. It has become an important task to remove noise and blurs from the image and restore a high-quality image in order to process image further for the purpose like object segmentation, detection, tracking etc. This analysis is done by adding blur noise to the image and then applying CNN model to deblur it.  Here the CNN model mainly consists of the encoder and decoder layers that which will help in making the image to be deblur. The results from the analysis and experiment show that the CNN model can remove blur and restore the image details and data than any other traditional/standard image filtering techniques.

Keywords: Image deblurring, blur noise, convolutional neural network, Deep Learning