Difference between revisions of "Character Recognition"
| Line 9: | Line 9: | ||
* [[Capabilities]] | * [[Capabilities]] | ||
| + | * [[Image Retrieval / Object Detection]] | ||
* [http://www.slideshare.net/DataWorksMD/multilingual-optical-character-recognition-ocr-in-unconstrained-image-and-video Multilingual Optical Character Recognition (OCR) in Unconstrained Image and Video | David Etter] | * [http://www.slideshare.net/DataWorksMD/multilingual-optical-character-recognition-ocr-in-unconstrained-image-and-video Multilingual Optical Character Recognition (OCR) in Unconstrained Image and Video | David Etter] | ||
** Tools/Standards: | ** Tools/Standards: | ||
Revision as of 12:20, 29 June 2019
YouTube search... ...Google search
- Capabilities
- Image Retrieval / Object Detection
- Multilingual Optical Character Recognition (OCR) in Unconstrained Image and Video | David Etter
- Tools/Standards:
- Pillow file format support, an efficient internal representation, and fairly powerful image processing capabilities
- Face Recognition Vendor Test (FRVT) | NIST
- Datasets/Networks:
- Tools/Standards:
- Media Distillery understanding video to engage customers
- Detect text in images | Google - Optical Character Recognition (OCR)
- Amazon Textract service that automatically extracts text and data from scanned documents
- Recommends ingredients and recipes based on a photo of food
- A gentle introduction to OCR | Gidi Shperber - Toward Data Science
