Skip to content

SaijyotiTripathy/Optical-Character-Recognition-Model

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 

Repository files navigation

Optical-Character-Recognition-Model

OCR, or Optical Character Recognition, is a fascinating technology that transforms the seemingly magical world of text in images into a realm of practical possibilities. Imagine being able to extract text from a photograph or a scanned document with just a few clicks. OCR systems are the sorcerers behind this incredible feat. Using complex algorithms and pattern recognition techniques, they analyze images or scanned documents, identify characters, and convert them into editable and searchable text. This wizardry opens up a multitude of applications, from digitizing printed materials to enhancing accessibility for visually impaired individuals. OCR systems have truly cast a spell on the way we interact with and manipulate text, making the impossible a reality with a wave of their virtual wands.

OCR PPT

Explore our implementation goals, system design, performance analysis, and future work, as we aim to develop an accurate, efficient, and scalable OCR model.

OCR_PPT_upload.pdf

To use the pre-trained model :

Download the .h5 model from the repository and then test it using your own dataset.

Code to my CNN model :

  1. Download the given OCR_model.ipynb file.
  2. Follow the steps mentioned.
  3. All the datasets are uploaded in zip format in my Google Drive.
  4. Once the model is trained, test it on your dataset.

Training Dataset Link :

https://drive.google.com/drive/folders/1WskBeTKhqeXkSXeUx91TsdV6eGsJd4YK

About

Optical Character Recognition Model using CNN

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published