Spaces:
Sleeping
Sleeping
File size: 4,160 Bytes
d47a89d bea12a5 d47a89d bea12a5 d47a89d bea12a5 ff5f533 d47a89d ff5f533 d47a89d bea12a5 ff5f533 d47a89d ff5f533 c02f435 d47a89d bea12a5 ff5f533 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 |
import gradio as gr
import cv2
import easyocr
from PIL import Image
# Functions for OCR steps
def get_grayscale(image):
return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
def thresholding(src):
return cv2.threshold(src,127,255, cv2.THRESH_TOZERO)[1]
def ocr_with_easy(img):
gray_scale_image = get_grayscale(img)
thresholded_image = thresholding(gray_scale_image)
cv2.imwrite('image.png', thresholded_image)
reader = easyocr.Reader(['en'])
bounds = reader.readtext('image.png', paragraph="False", detail=0)
bounds = ''.join(bounds)
return bounds
def generate_ocr(img):
text_output = ''
if (img).any():
if img is not None:
text_output = ocr_with_easy(img)
else:
raise gr.Error("Please upload an image!!!!")
return text_output
# Interactive questions
questions = [
{
"question": "What is the first step in OCR?",
"options": ["Binarization", "Grayscale conversion", "Edge detection"],
"answer": "Grayscale conversion"
},
{
"question": "What is the purpose of thresholding in OCR?",
"options": ["To detect edges", "To convert image to grayscale", "To binarize the image"],
"answer": "To binarize the image"
},
{
"question": "Which library is used for OCR in this app?",
"options": ["Tesseract", "EasyOCR", "OpenCV"],
"answer": "EasyOCR"
},
{
"question": "What format is the image saved in after preprocessing?",
"options": ["JPG", "PNG", "TIFF"],
"answer": "PNG"
},
{
"question": "What does OCR stand for?",
"options": ["Optical Character Recognition", "Optical Character Reading", "Optical Code Recognition"],
"answer": "Optical Character Recognition"
}
]
def quiz_interface():
def check_answer(question_idx, selected):
if questions[question_idx]["answer"] == selected:
return "Correct!"
else:
return "Incorrect. The correct answer is: " + questions[question_idx]["answer"]
interfaces = []
for idx, question in enumerate(questions):
radio = gr.Radio(choices=question["options"], label=question["question"])
button = gr.Button("Submit")
output = gr.Textbox(label="Result")
def create_submit_fn(idx):
def submit(selected):
return check_answer(idx, selected)
return submit
interfaces.append(gr.Interface(
create_submit_fn(idx),
radio,
output,
live=True
))
return interfaces
# Explanation text
explanation_text = """
**Welcome to the OCR Tutorial!**
Optical Character Recognition (OCR) is a technology used to convert different types of documents, such as scanned paper documents, PDF files, or images captured by a digital camera, into editable and searchable data.
**Steps in the OCR Process:**
1. **Grayscale Conversion:** The first step in OCR is converting the image to grayscale. This simplifies the image and reduces the amount of data the OCR algorithm needs to process.
2. **Thresholding:** This step converts the grayscale image into a binary image, where the text is in black, and the background is in white. This makes it easier for the OCR algorithm to distinguish text from the background.
3. **OCR using EasyOCR:** We use the EasyOCR library to recognize and extract text from the preprocessed image.
Now that you understand the basics, you can try the OCR tool below and then proceed to answer the questions in the other tabs.
"""
image = gr.Image()
output = gr.Textbox(label="Output")
explanation = gr.Markdown(explanation_text)
ocr_app = gr.Interface(
fn=generate_ocr,
inputs=image,
outputs=output,
title="Optical Character Recognition",
description=explanation_text,
css=".gradio-container {background-color: lightgray} #radio_div {background-color: #FFD8B4; font-size: 40px;}"
)
quiz_app = gr.TabbedInterface(
[ocr_app] + quiz_interface(),
["OCR Tool"] + [f"Question {i+1}" for i in range(len(questions))],
title="OCR Tutorial and Quiz"
)
quiz_app.launch()
|