Fast-OCR is a new lightweight detection network that incorporates features from existing models focused on the speed/accuracy trade-off, such as YOLOv2, CR-NET, and Fast-YOLOv4.
Source: Towards Image-based Automatic Meter Reading in Unconstrained Scenarios: A Robust and Efficient ApproachPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Optical Character Recognition (OCR) | 2 | 33.33% |
License Plate Detection | 1 | 16.67% |
License Plate Recognition | 1 | 16.67% |
Scene Text Recognition | 1 | 16.67% |
Image-based Automatic Meter Reading | 1 | 16.67% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |