-
Hi,
This is a first of a series of issues on reimagining content recognition feature:
### Background:
Currently, NVDA supports text recognition via Windows OCR and a collection of recognizer ad…
-
I ran single ocr on M1 chip with 16GB of ram, set `--batch_multiplier` to 2, `--max_pages` to 14, and I encountered this:
```
Loaded detection model vikp/surya_det3 on device mps with dtype torch…
-
Hi,
Follow-up to #17405:
### Background:
In addition to Windows OCR, add-ons were developed to offer alternative content recognition strategies such as use of online AI/language model services.…
-
ตัวอย่างการใช้ผลจาก YOLO dectector ดึงส่วนของภาพออกมาและใช้ `surya-ocr` ในการอ่านข้อความ
``` py
from pathlib import Path
from ultralytics import YOLO
checkpoint = Path("best_detection_yolo.pt"…
-
Description:
- We have already applied OCR to Pecha images, but the current approach struggles to recognize text from certain publishers.
- This approach focuses on preprocessing the images to enhanc…
-
### Please confirm the following:
- [X] I have carefully read the [README](https://github.com/tisfeng/Easydict#readme)
- [X] I have searched through the [issues](https://github.com/tisfeng/Easydic…
-
[Figma, see the "Search Results" frame](https://www.figma.com/design/jagzws5rTk1VVPfwa62XBy/Figma-basics?m=auto&t=BbwfZUthr71MirDu-1).
[See video](https://drive.google.com/file/d/14ALKFdkZFIuju7pGcEY…
-
### Is your feature request related to a problem? Please describe.
The `contentRecog` module is currently only used by the OCR and so some of the code is written only to that end. The OCR presents it…
-
Hi
i have set the langs to 'zh' when i using the OCR，but the recognize result appear japanese word or other language word。how can i fix it or limit the ocr result in my word dict.
thx
-
The OCR is pretty good but a high proportion of the unknown ingredients are as a result of very minor errors such as a missing comma between ingredients or common characters such as 'o' and 'a', 'i' a…