Use TensorFlow.js for E2E OCR
Open
- Dominant language
- JavaScript
- Stars
- 6
- Forks
- 0
- PR merge metrics
- No merged PRs in 30d
Description
To realize no native dependencies.
[WebNN](https://webmachinelearning.github.io/webnn/) is also interesting to run CNN.
Contributor guide
No contributing guide indexed for this repository
Research direction
No files, tests, or entry points are named. Start by locating the existing OCR path and its native dependencies, then evaluate how TensorFlow.js could support end-to-end OCR without them; WebNN is noted as an alternative to investigate. Done means the OCR flow works without native dependencies and the chosen approach is verified in the extension.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- javascript
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100