captcha_solver_hf.py

import numpy as np
import cv2
import pickle
from keras.models import load_model
from helpers import resize_to_fit

# Ensure these files are in the same directory as your script
MODEL_FILENAME = "captcha_model.hdf5"
MODEL_LABELS_FILENAME = "model_labels.dat"

# Load the model and labels
with open(MODEL_LABELS_FILENAME, "rb") as f:
    lb = pickle.load(f)

model = load_model(MODEL_FILENAME)

def solve_captcha(image):
    # Convert the image to grayscale
    image = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

    # Add some extra padding around the image
    image = cv2.copyMakeBorder(image, 20, 20, 20, 20, cv2.BORDER_REPLICATE)

    # Threshold the image
    thresh = cv2.threshold(image, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]

    # Find contours
    contours, _ = cv2.findContours(thresh.copy(), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)

    letter_image_regions = []

    for contour in contours:
        (x, y, w, h) = cv2.boundingRect(contour)
        if w / h > 1.25:
            half_width = int(w / 2)
            letter_image_regions.append((x, y, half_width, h))
            letter_image_regions.append((x + half_width, y, half_width, h))
        else:
            letter_image_regions.append((x, y, w, h))

    if len(letter_image_regions) != 4:
        return "Error: Could not identify 4 letters in the CAPTCHA"

    letter_image_regions = sorted(letter_image_regions, key=lambda x: x[0])

    predictions = []

    for letter_bounding_box in letter_image_regions:
        x, y, w, h = letter_bounding_box
        letter_image = image[y - 2:y + h + 2, x - 2:x + w + 2]
        letter_image = resize_to_fit(letter_image, 20, 20)
        letter_image = np.expand_dims(letter_image, axis=2)
        letter_image = np.expand_dims(letter_image, axis=0)

        prediction = model.predict(letter_image)
        letter = lb.inverse_transform(prediction)[0]
        predictions.append(letter)

    captcha_text = "".join(predictions)
    return captcha_text

# We don't need a test function here anymore, as testing will be done through the Gradio interface