OCR

Image --> Text Conversion

Optical character recognition (OCR) is the conversion of images to text. In order to extract and repurpose data from scanned documents, camera images or PDFs, you need an OCR software that would single out letters on the image thus enabling you to access and edit the original document.

https://ocr-dsc-app.herokuapp.com/

---

Preview

• Important highlights from the Project
• 
• 

Functionalities

• HOME
• PROJECT DESCRIPTION
• UNSTRUCTURED TEXT DETECTION AND RECOGNITION IN IMAGES
• STRUCTURED TEXT DETECTION AND RECOGNITION IN IMAGES
• DOWNLOADING THE TEXT FILE IN NOTEPAD

Instructions to run

• Pre-requisites: (To be installed manually on Anaconda prompt or Command prompt)

  • pytesseract==0.3.7
  • imutils==0.5.4
  • matplotlib==3.3.4
  • numpy==1.20.1
  • pandas==1.2.3
  • Pillow==8.1.2
  • scipy==1.6.1
  • streamlit==0.78.0
  • cv2==4.5.1

• Directions to Install

pip install <package name>==<version number>

• Directions to Execute

Step 1: Download the zip folder and unzip
Step 2: Save the image you want to convert to text in the folder "Project_ocr"
Step 3: Open Anaconda prompt and type "cd" followed by path of Project_ocr folder [Eg: C:\Users\Desktop\OCR\Optical-Character-Recognition\Project_ocr]
Step 4: In Anaconda prompt type "streamlit run Final.py"
Step 5: A browser will open where you can finally run the project!

How to run:

• 
• 

Contributors

Shubham Gore

Shaswat Srivastava

Ved Dubey

Dhruv Kuncha

License

Made with ❤️ by DS Community SRM