Einstein Optical Character Recognition

Salesforce have introduced new Einstein Services to build custom AI for their business.

Einstein Optical Character Recognition (OCR) leverages computer vision to analyze documents and extract the relevant information, making repetitive tasks like data entry more efficient.

What is OCR ?

Electronic/Mechanical conversion of images , hyped or printed text into M/C encoded text which works for scanned or photos from document.


For example, a developer can build OCR into a Lightning Web Component to enable sales reps to easily upload a business card from a prospect and automatically analyze the unstructured data from the image file, translate that data into text and extract information that can then be updated in the corresponding Salesforce record.

Previous companies providing OCR Services : 

• Google:  https://cloud.google.com/vision/docs/ocr
• MS : https://marketplace.visualstudio.com/items?itemName=Erik-WINSOFT.OCRNET

Use Cases of OCR :

• Invoice Reading
• Business / I Card Reading 
• Contract Reading
• Automation of calculation by documentation and save time.

Current Status of OCR by Salesforce :

• Presently in Pilot (Refer https://help.salesforce.com/apex/HTViewSolution?id=000194013&language=en_US). Reach your AE for POC.
• Part of Apex AI services
• Apex AI Services are present in AITool Namespace.
• Present in Unmanage Package

Kind of Images OCR works in :

1. Images containing Text.
2. Handwritten not supprted yet.
3. Support JPG/PNG
4. Max size 5 MB.
5. Read upto 250 words.

How it works ?

1. AI Tool ML Service class in red comes from unmanage package.
2. From there it reads the characters automatically and salesforce the same in description object . The below class can be called directly from trigger which comes from the unmanage package under pilot program.

Previously Working Example:

https://springml.com/blog/using-salesforce-and-google-cloud-to-build-ocr-app/

Reference :

Salesforce.com

Youtube.com (Salesforce Developers)