indranil143/Image_Denoiser
Exploring CNN autoencoder techniques for MNIST image denoising, from basic to advanced architectures.
This project helps anyone working with scanned documents or digital images of handwritten digits to clean up noisy inputs. It takes in blurry or corrupted grayscale images of single digits and outputs clearer, reconstructed versions, making them easier to read or process. This is ideal for researchers, archivists, or data entry specialists who need to improve the quality of digit images.
No commits in the last 6 months.
Use this if you need to automatically clean up pixel noise from scanned handwritten digits to improve their readability or prepare them for further analysis.
Not ideal if you are working with color images, complex scenes, or images containing anything other than single, isolated handwritten digits.
Stars
11
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
May 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/indranil143/Image_Denoiser"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
CAREamics/careamics
A deep-learning library for denoising images using Noise2Void and friends (CARE, PN2V, HDN...
yu4u/noise2noise
An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration...
rgeirhos/texture-vs-shape
Pre-trained models, data, code & materials from the paper "ImageNet-trained CNNs are biased...
NICALab/SUPPORT
Accurate denoising of voltage imaging data through statistically unbiased prediction, Nature Methods.
jaewon-lee-b/lte
Local Texture Estimator for Implicit Representation Function, in CVPR 2022