Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/gutenye/ocr
High accurate text detection (OCR) Javascript/Typescript library that runs on Node.js, Browser, React Native and C++. Based on PaddleOCR and ONNX runtime
https://github.com/gutenye/ocr
browser cpp javascript node ocr onnxruntime paddleocr react-native text-detection typescript
Last synced: 7 days ago
JSON representation
High accurate text detection (OCR) Javascript/Typescript library that runs on Node.js, Browser, React Native and C++. Based on PaddleOCR and ONNX runtime
- Host: GitHub
- URL: https://github.com/gutenye/ocr
- Owner: gutenye
- License: mit
- Created: 2024-05-01T08:03:27.000Z (10 months ago)
- Default Branch: main
- Last Pushed: 2024-12-13T09:18:56.000Z (2 months ago)
- Last Synced: 2025-01-28T01:11:19.344Z (15 days ago)
- Topics: browser, cpp, javascript, node, ocr, onnxruntime, paddleocr, react-native, text-detection, typescript
- Language: C++
- Homepage: https://gutenye-ocr.netlify.app/
- Size: 3.8 MB
- Stars: 51
- Watchers: 1
- Forks: 12
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Guten OCR
> [Demo](https://gutenye-ocr.netlify.app/) | [Roadmap](https://github.com/users/gutenye/projects/5/views/4)
**an OCR Javascript library runs on Node.js, Browser, React Native and C++**
Based on [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR) and [ONNX Runtime](https://github.com/microsoft/onnxruntime), supports PP-OCRv4 model
## Getting Started
### Node
> [Example](./packages/node/example/README.md)
```ts
bun add @gutenye/ocr-node
import Ocr from '@gutenye/ocr-node'
const ocr = await Ocr.create()
const result = await ocr.detect('a.jpg')
```
### Browser
> [Example](./packages/browser/example/README.md)
```ts
bun add @gutenye/ocr-browser
import Ocr from '@gutenye/ocr-browser'
const ocr = await Ocr.create({
models: {
detectionPath: '/assets/ch_PP-OCRv4_det_infer.onnx',
recognitionPath: '/assets/ch_PP-OCRv4_rec_infer.onnx',
dictionaryPath: '/assets/ppocr_keys_v1.txt'
}
})
const result = await ocr.detect('/a.jpg')
```
### React Native
> [Example](./packages/react-native/example/README.md)
```ts
bun add @gutenye/ocr-react-native
import Ocr from '@guenye/ocr-react-native'
const ocr = await Ocr.create()
const result = await ocr.detect('a.jpg')
```
### C++
> [Example](./packages/react-native/cpp/example/README.md)
```cpp
#include "native-ocr.h"
NativeOcr* ocr = new NativeOcr(..)
auto result = ocr->detect("a.jpg");
```
### API Reference
```ts
Ocr.create({
models?: {
detectionPath: string
recognitionPath: string
dictionaryPath: string
},
isDebug?: boolean
debugOutputDir?: string // Node only
recognitionImageMaxSize?: number // RN only
detectionThreshold?: number // RN only
detectionBoxThreshold?: number // RN only
detectionUnclipRatiop?: number // RN only
detectionUseDilate?: boolean // RN only
detectionUsePolygonScore?: boolean // RN only
useDirectionClassify?: boolean // RN only
onnxOptions?: {} // Node only. Pass to ONNX Runtime
}): Promise
ocr.detect(imagePath, {
onnxOptions?: {} // Node only. Pass to ONNX Runtime
}): Promise
TextLine {
text: string
score: number
frame: { top, left, width, height }
}
```
## Development
- Requires Git LFS to clone the repo
```sh
brew install git-lfs
git clone [email protected]:gutenye/ocr.git
```
- [Development](docs/Development.md)
## Related Projects
| Name | Platforms | Note |
| -------------------------------------------------------------- | --------- | ------------------------------- |
| [eSearch-OCR](https://github.com/xushengfeng/eSearch-OCR) | Electron | |
| [paddleocr-onnx](https://github.com/backrunner/paddleocr-onnx) | Node | Recogination part is incomplete |
| [ocrjs](https://github.com/SOVLOOKUP/ocrjs) | Node | Recogination part is incomplete |
| [Paddle-Lite-Demo](https://github.com/PaddlePaddle/Paddle-Lite-Demo) | Mobile, C++ | |