app.py

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

image = gr.Image()
output = gr.Textbox(label="Output")

ocr_app = gr.Interface(
    generate_ocr,
    image,
    output,
    title="Optical Character Recognition",
    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()