Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

DeepSeek OCR - More than OCR - Exploring Image-Based Text Compression

Sam Witteveen via YouTube

Overview

Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore DeepSeek OCR, an innovative approach that goes beyond traditional optical character recognition by using images to compress text representations more effectively. Examine the DeepSeek OCR paper and understand how this experimental technology leverages visual processing to achieve better text compression. Learn about the underlying architecture including Transformers and Vision Transformers (ViT) that power this system. Discover how to access DeepSeek-OCR through GitHub and Hugging Face platforms, and compare it with other OCR solutions like Nanonets and PaddleOCR-VL to understand the broader landscape of optical character recognition technologies.

Syllabus

00:00 Intro
00:30 DeepSeek OCR: Contexts Optical Compression Paper
03:37 Transformer
04:12 Vision Transformer ViT
10:11 DeepSeek-OCR GitHub and Hugging Face
10:32 Nanonets and PaddleOCR-VL

Taught by

Sam Witteveen

Reviews

Start your review of DeepSeek OCR - More than OCR - Exploring Image-Based Text Compression

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.