Spaces:
Sleeping
Sleeping
Aravindh
commited on
Commit
•
1e36507
1
Parent(s):
bcdb129
init files
Browse files- .gitignore +1 -0
- Dockerfile +14 -0
- app.py +39 -0
- data/invoice.jpg +0 -0
- data/publay_sample.jpeg +0 -0
- data/simple.jpg +0 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
.DS_Store
|
Dockerfile
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
|
2 |
+
# you will also find guides on how best to write your Dockerfile
|
3 |
+
|
4 |
+
FROM python:3.9
|
5 |
+
|
6 |
+
WORKDIR /code
|
7 |
+
|
8 |
+
COPY ./requirements.txt /code/requirements.txt
|
9 |
+
|
10 |
+
RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
|
11 |
+
|
12 |
+
COPY . .
|
13 |
+
|
14 |
+
CMD ["python", "app.py"]
|
app.py
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from multiocr import OcrEngine
|
3 |
+
from multiocr.utils import draw_bounding_boxes
|
4 |
+
|
5 |
+
# Define a function that takes an input image and processes it
|
6 |
+
def process_image(input_image, ocr_type):
|
7 |
+
# Perform y`our internal processing here
|
8 |
+
# Example: Convert the image to grayscale
|
9 |
+
ocr = OcrEngine(ocr_type)
|
10 |
+
data = ocr.text_extraction(input_image)
|
11 |
+
json_response = ocr.text_extraction_to_df(data)
|
12 |
+
output_image = draw_bounding_boxes(input_image, data)
|
13 |
+
|
14 |
+
return output_image, json_response
|
15 |
+
|
16 |
+
# Define the Gradio interface
|
17 |
+
def app():
|
18 |
+
ocr_type = gr.inputs.Dropdown(choices=["tesseract", "paddle_ocr", "easy_ocr", "aws_textract"], label="selct one ocr")
|
19 |
+
# Create an input component for uploading the image
|
20 |
+
image_input = gr.inputs.Image(label="Upload Image", type="filepath")
|
21 |
+
|
22 |
+
# Create an output component for displaying the processed image
|
23 |
+
image_output = gr.outputs.Image(label="Output Image", type="pil")
|
24 |
+
|
25 |
+
# Create an output component for displaying the JSON response
|
26 |
+
df = gr.outputs.Dataframe(label="DataFrame", type="pandas")
|
27 |
+
|
28 |
+
# Create a function that will be called when the app is run
|
29 |
+
def process_and_display_image(input_image, ocr_type):
|
30 |
+
processed_image, json_response = process_image(input_image, ocr_type)
|
31 |
+
return processed_image, json_response
|
32 |
+
|
33 |
+
# Create the Gradio interface
|
34 |
+
examples = [["./data/simple.jpg"], ["./data/invoice.jpg"], ["./data/publay_sample.jpeg"]]
|
35 |
+
gr.Interface(fn=process_and_display_image, inputs=[image_input, ocr_type], outputs=[image_output, df], examples=examples).launch(server_port=7860,server_name="0.0.0.0")
|
36 |
+
|
37 |
+
if __name__ == "__main__":
|
38 |
+
# Run the app
|
39 |
+
app()
|
data/invoice.jpg
ADDED
data/publay_sample.jpeg
ADDED
data/simple.jpg
ADDED