|
|
import supervision as sv |
|
|
import gradio as gr |
|
|
from ultralytics import YOLO |
|
|
import sahi |
|
|
import numpy as np |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
sahi.utils.file.download_from_url( |
|
|
"https://www.erbanotizie.com/wp-content/uploads/2014/01/Casello.jpg", |
|
|
"ocr1.jpg", |
|
|
) |
|
|
sahi.utils.file.download_from_url( |
|
|
"https://media-cdn.tripadvisor.com/media/photo-s/15/1d/03/18/receipt.jpg", |
|
|
"ocr2.jpg", |
|
|
) |
|
|
sahi.utils.file.download_from_url( |
|
|
"https://upload.forumfree.net/i/ff11450850/b5ef33b7-01da-4055-9ece-089b2a35a193.jpg", |
|
|
"ocr3.jpg", |
|
|
) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
annotatorbbox = sv.BoxAnnotator() |
|
|
annotatormask=sv.MaskAnnotator() |
|
|
model = YOLO("best_Receipt.pt") |
|
|
|
|
|
|
|
|
def yolov8_inference( |
|
|
image: gr.inputs.Image = None, |
|
|
conf_threshold: gr.inputs.Slider = 0.5, |
|
|
iou_threshold: gr.inputs.Slider = 0.45, |
|
|
): |
|
|
|
|
|
image=image[:, :, ::-1].astype(np.uint8) |
|
|
model = YOLO("https://huggingface.co/spaces/devisionx/first-demo/blob/main/best_Receipt.pt") |
|
|
results = model(image,imgsz=320,conf=conf_threshold,iou=iou_threshold)[0] |
|
|
image=image[:, :, ::-1].astype(np.uint8) |
|
|
detections = sv.Detections.from_yolov8(results) |
|
|
annotated_image = annotatormask.annotate(scene=image, detections=detections) |
|
|
annotated_image = annotatorbbox.annotate(scene=annotated_image , detections=detections) |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
return annotated_image |
|
|
''' |
|
|
image_input = gr.inputs.Image() # Adjust the shape according to your requirements |
|
|
|
|
|
inputs = [ |
|
|
gr.inputs.Image(label="Input Image"), |
|
|
gr.Slider( |
|
|
minimum=0.0, maximum=1.0, value=0.25, step=0.05, label="Confidence Threshold" |
|
|
), |
|
|
gr.Slider(minimum=0.0, maximum=1.0, value=0.45, step=0.05, label="IOU Threshold"), |
|
|
] |
|
|
|
|
|
outputs = gr.Image(type="filepath", label="Output Image") |
|
|
title = "OCR Demo" |
|
|
''' |
|
|
examples = [ |
|
|
["ocr1.jpg", 0.6, 0.45], |
|
|
["ocr2.jpg", 0.25, 0.45], |
|
|
["ocr3.jpg", 0.25, 0.45], |
|
|
] |
|
|
outputs_images = [ |
|
|
["1.jpg"], |
|
|
["2.jpg"] |
|
|
,["3.jpg"] |
|
|
] |
|
|
|
|
|
readme_html = """ |
|
|
<html> |
|
|
<head> |
|
|
<style> |
|
|
.description { |
|
|
margin: 20px; |
|
|
padding: 10px; |
|
|
border: 1px solid #ccc; |
|
|
} |
|
|
</style> |
|
|
</head> |
|
|
<body> |
|
|
<div class="description"> |
|
|
<p><strong>More details:</strong></p> |
|
|
<p>We present a demo for performing object segmentation using a model trained on OCR-Receipt dataset. The model was trained on 54 training images and validated on 15 images.</p> |
|
|
<p><strong>Usage:</strong></p> |
|
|
<p>You can upload receipt images, and the demo will provide you with your segmented image.</p> |
|
|
<p><strong>Dataset:</strong></p> |
|
|
<p>This dataset comprises a total of 77 images, which are divided into three distinct sets for various purposes:</p> |
|
|
<ul> |
|
|
<li><strong>Training Set:</strong> It includes 54 images and is intended for training the model.</li> |
|
|
<li><strong>Validation Set:</strong> There are 15 images in the validation set, which is used for optimizing model parameters during development.</li> |
|
|
<li><strong>Test Set:</strong> This set consists of 8 images and serves as a separate evaluation dataset to assess the performance of trained models.</li> |
|
|
</ul> |
|
|
<p><strong>License:</strong> This dataset is made available under the Creative Commons Attribution 4.0 International License (CC BY 4.0).</p> |
|
|
<p>To access and download this dataset, please follow this link: <a href=" https://universe.roboflow.com/study-0w9zw/ocr-receipt" target="_blank">Dataset Download</a></p> |
|
|
|
|
|
|
|
|
</body> |
|
|
</html> |
|
|
""" |
|
|
with gr.Blocks() as demo: |
|
|
gr.Markdown( |
|
|
""" |
|
|
<div style="text-align: center;"> |
|
|
<h1>OCR Demo</h1> |
|
|
Powered by <a href="https://Tuba.ai">Tuba</a> |
|
|
</div> |
|
|
""" |
|
|
) |
|
|
|
|
|
|
|
|
|
|
|
with gr.Row(): |
|
|
image_input = gr.inputs.Image() |
|
|
|
|
|
|
|
|
outputs = gr.Image(type="filepath", label="Output Image") |
|
|
|
|
|
|
|
|
with gr.Row(): |
|
|
conf_slider=gr.Slider(minimum=0.0, maximum=1.0, value=0.25, step=0.05, label="Confidence Threshold" ) |
|
|
with gr.Row(): |
|
|
IOU_Slider=gr.Slider(minimum=0.0, maximum=1.0, value=0.45, step=0.05, label="IOU Threshold") |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
button = gr.Button("Run") |
|
|
|
|
|
|
|
|
|
|
|
button.click(fn=yolov8_inference, inputs=[image_input, conf_slider,IOU_Slider], outputs=outputs, api_name="yolov8_inference") |
|
|
|
|
|
gr.Examples( |
|
|
fn=yolov8_inference, |
|
|
examples=examples, |
|
|
inputs=[image_input, conf_slider,IOU_Slider], |
|
|
outputs=[outputs] |
|
|
) |
|
|
|
|
|
|
|
|
gr.Markdown(readme_html) |
|
|
|
|
|
demo.launch(share=False) |
