Creating a Modern OCR Pipeline Using Computer Vision and Deep Learning - Dropbox

In previous posts we have described how Dropbox’s mobile document scanner works. The document scanner makes it possible to use your mobile phone to take photos and "scan" items like receipts and invoices. Our mobile document scanner only outputs an image — any text in the image is just a set of pixels as far as the computer is concerned, and can’t be copy-pasted, searched for, or any of the other things you can do with text.

Creating a Modern OCR Pipeline Using Computer Vision and Deep Learning - Dropbox --> --> --> Creating a Modern OCR Pipeline Using Computer Vision and Deep Learning // By Brad Neuberg • Apr 12, 2017 In this post we will take you behind the scenes on how we built a state-of-the-art Optical Character Recognition (OCR) pipeline for our mobile document scanner . We used computer vision and deep learning advances such as bi-directional Long Short Term Memory (LSTMs), Connectionist Temporal Classification (CTC), convolutional neural nets (CNNs), and more. In addition, we will also dive deep into

saved by

• Li-Lian Ang

related reading

• Accelerating Document AIhuggingface.co
• Mistral OCR | Mistral AImistral.ai
• The Unreasonable Effectiveness of Recurrent Neural Networkskarpathy.github.io
• [2510.18234] DeepSeek-OCR: Contexts Optical Compressionarxiv.org
• The Annotated Transformernlp.seas.harvard.edu
• [1912.13318] LayoutLM: Pre-training of Text and Layout for Document Image Understandingarxiv.org
• The Annotated Transformernlp.seas.harvard.edu
• DeepSeek-OCR: Contexts Optical Compressionarxiv.org
• Sequence Modeling with CTCdistill.pub
• The Little Book of Deep Learningfleuret.org
• ImageNet Classification with Deep Convolutional Neural Networksproceedings.neurips.cc
• GitHub - longshangbang/SceneTextPapers: Tracking the latest progress in Scene Text Detection and Recognition: Must-read papers well organized · GitHubgithub.com