Skip to content

AnandPaul4x4/ocr_ner

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
img
img
 
 
README.md
README.md
 
 
ner_results.csv
ner_results.csv
 
 
ocr_ner1.ipynb
ocr_ner1.ipynb
 
 
output_with_boxes.png
output_with_boxes.png
 
 
requirements.txt
requirements.txt
 
 

Repository files navigation

This task demonstrates a combined approach using Optical Character Recognition (OCR) with EasyOCR and OpenCV, along with Named Entity Recognition (NER) using spaCy.

The workflow involves extracting text from images and overlaying bounding boxes around detected text regions.

Since OCR can sometimes produce inaccurate or noisy text—especially from scanned or low-quality documents—TextBlob is used for basic text correction before applying NER.

This helps improve the accuracy of entity recognition by normalizing misspelled or distorted words.

After correction, the cleaned text is processed through NER to identify and classify entities such as names, dates, organizations, locations, and numerical values.

Model Used for NER - Spcay NER

Text Detection and Recognition - EasyOCR

Text correction - Text Correction

About

No description, website, or topics provided.

Resources

Readme
Activity

Stars

0 stars

Watchers

0 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

 
 
 

Contributors

Languages