Spaces:
Running
Running
Update README.md
Browse files
README.md
CHANGED
@@ -19,7 +19,6 @@ This project provides a simple interface for Optical Character Recognition (OCR)
|
|
19 |
## Features
|
20 |
- Extract text from images using OCR.
|
21 |
- Classify extracted text as either "Spam" or "Not Spam."
|
22 |
-
- Save the extracted text and classification results to a local JSON and CSV file.
|
23 |
|
24 |
## How It Works
|
25 |
1. **OCR**: The app uses one of the three OCR methods to extract text from the uploaded image:
|
@@ -29,7 +28,6 @@ This project provides a simple interface for Optical Character Recognition (OCR)
|
|
29 |
|
30 |
2. **Classification**: The extracted text is passed to a pre-trained DistilBERT model that classifies the text as either "Spam" or "Not Spam."
|
31 |
|
32 |
-
3. **Save Results**: The extracted text and classification results are saved locally in both JSON and CSV formats, allowing easy retrieval and review.
|
33 |
|
34 |
## Installation
|
35 |
|
@@ -90,7 +88,7 @@ print(result)
|
|
90 |
|
91 |
| Parameter | Type | Description |
|
92 |
|-----------|------|-------------|
|
93 |
-
| `method` | `Literal['PaddleOCR', 'EasyOCR', 'KerasOCR']` | Choose the OCR method to be used for text extraction. Default is "PaddleOCR." |
|
94 |
| `img` | `dict` | The image input, which can be provided as a URL, path, or base64 encoded image. |
|
95 |
|
96 |
#### Image Input Details
|
|
|
19 |
## Features
|
20 |
- Extract text from images using OCR.
|
21 |
- Classify extracted text as either "Spam" or "Not Spam."
|
|
|
22 |
|
23 |
## How It Works
|
24 |
1. **OCR**: The app uses one of the three OCR methods to extract text from the uploaded image:
|
|
|
28 |
|
29 |
2. **Classification**: The extracted text is passed to a pre-trained DistilBERT model that classifies the text as either "Spam" or "Not Spam."
|
30 |
|
|
|
31 |
|
32 |
## Installation
|
33 |
|
|
|
88 |
|
89 |
| Parameter | Type | Description |
|
90 |
|-----------|------|-------------|
|
91 |
+
| `method` | `Literal['PaddleOCR', 'EasyOCR', 'KerasOCR', 'TesseractOCR']` | Choose the OCR method to be used for text extraction. Default is "PaddleOCR." |
|
92 |
| `img` | `dict` | The image input, which can be provided as a URL, path, or base64 encoded image. |
|
93 |
|
94 |
#### Image Input Details
|