Learning Deep Gradient Descent Optimization for Image Deconvolution
Objective
Proposed a Recurrent Gradient Descent Network (RGDN) by systematically incorporating deep neural networks into a fully parameterized gradient descent scheme for image deconvolution.
Abstract
The main objective of this work is to develop a Recurrent Gradient Descent Network (RGDN) which serves as an optimizer to de-convolute the images. Image deconvolution, also known as image deblurring, aims to recover a sharp image from an observed blurry image. Single image deconvolution is challenging and mathematically ill-posed due to the unknown noise and the loss of the high-frequency information.
Many conventional methods resort to different natural image priors based on manually designed empirical statistics, which usually shows inferior results and time-consuming in optimization. We propose a Recurrent Gradient Descent Network (RGDN) by systematically incorporating deep neural networks into a fully parameterized gradient descent scheme.
Keywords: Image Deconvolution, Image Deblurring, Learning to Optimize, Deep Gradient Descent.
NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.
Block Diagram
Specifications
Software & Hardware Requirements:
Software: Matlab 2018a or above
Hardware:
Operating Systems:
- Windows 10
- Windows 7 Service Pack 1
- Windows Server 2019
- Windows Server 2016
Processors:
Minimum: Any Intel or AMD x86-64 processor
Recommended: Any Intel or AMD x86-64 processor with four logical cores and AVX2 instruction set support
Disk:
Minimum: 2.9 GB of HDD space for MATLAB only, 5-8 GB for a typical installation
Recommended: An SSD is recommended A full installation of all MathWorks products may take up to 29 GB of disk space
RAM:
Minimum: 4 GB
Recommended: 8 GB
Learning Outcomes
- Introduction to Matlab
- What is EISPACK & LINPACK
- How to start with MATLAB
- About Matlab language
- Matlab coding skills
- About tools & libraries
- Application Program Interface in Matlab
- About Matlab desktop
- How to use Matlab editor to create M-Files
- Features of Matlab
- Basics on Matlab
- What is an Image/pixel?
- About image formats
- Introduction to Image Processing
- How digital image is formed
- Importing the image via image acquisition tools
- Analyzing and manipulation of image.
- Phases of image processing:
- Acquisition
- Image enhancement
- Image restoration
- Color image processing
- Image compression
- Morphological processing
- Segmentation etc.,
- About Artificial
Intelligence (AI)
- About Machine Learning
- About Deep Learning
- About layers in AI (input, hidden and output layers)
- Building AI (ANN/CNN) architecture using Matlab
- We will able to know, what’s the term “Training” means in Artificial Intelligence
- About requirements that can influence the AI training process:
- Data
- Training data
- Validation data
- Testing data
- Hardware requirements to train network
- How to optimize the object using AI
- How to extend our work to another real time applications
- Project development Skills:
- Problem analyzing skills
- Problem solving skills
- Creativity and imaginary skills
- Programming skills
- Deployment
- Testing skills
- Debugging skills
- Project presentation skills
- Thesis writing skills
Related Projects
Paper Publishing
Request Call Back
Would you like to receive a free callback now?
Choose the best time for callback:
Leave your message and we will contact you as soon as possible
Disclaimer - Takeoff Edu Group Projects, are not associated or affiliated with IEEE, in any way. The IEEE Projects mentioned here are mentioned in the context of student projects, whose ideas are derived from IEEE publications, and not projects of or by IEEE.
