Upload 5 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+captcha_model.hdf5 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -0,0 +1,89 @@
+import gradio as gr
+import cv2
+import numpy as np
+from captcha_solver_hf import solve_captcha
+
+def predict_captcha(image):
+    if image is None:
+        return "Please upload an image."
+    img_array = np.array(image)
+    img_cv = cv2.cvtColor(img_array, cv2.COLOR_RGB2BGR)
+    result = solve_captcha(img_cv)
+    return result
+
+# Example images (replace these with actual CAPTCHA images)
+examples = [
+    "example_captcha1.png",
+    "example_captcha2.png",
+    "example_captcha3.png"
+]
+
+css = """
+.gradio-container {
+    font-family: 'Arial', sans-serif;
+}
+.gr-button {
+    color: white;
+    border-color: black;
+    background: linear-gradient(45deg, #007bff, #00bcd4);
+}
+.gr-button:hover {
+    background: linear-gradient(45deg, #0056b3, #008ba3);
+}
+.gr-form {
+    flex-direction: column;
+    align-items: center;
+}
+.gr-image-input {
+    width: 100% !important;
+    max-width: 400px;
+    margin: auto;
+}
+.footer {
+    margin-top: 20px;
+    text-align: center;
+    color: #666;
+}
+h1, h3 {
+    text-align: center;
+}
+"""
+
+with gr.Blocks(css=css) as iface:
+    gr.Markdown(
+    """
+    # CAPTCHA Solver
+    ### Unlock the Power of AI-Driven CAPTCHA Recognition
+    Upload your CAPTCHA image and let our advanced AI model decipher it instantly!
+    """
+    )
+    with gr.Column(scale=1):
+        input_image = gr.Image(type="numpy", label="Upload CAPTCHA Image")
+        output_text = gr.Textbox(label="Predicted Text")
+    
+    solve_button = gr.Button("Solve CAPTCHA", variant="primary")
+    solve_button.click(fn=predict_captcha, inputs=input_image, outputs=output_text)
+    
+    gr.Examples(examples, inputs=input_image)
+    
+    gr.Markdown(
+    """
+    ### How It Works
+    1. Upload a CAPTCHA image
+    2. Click "Solve CAPTCHA"
+    3. Get instant results!
+    
+    Our state-of-the-art AI model processes your image and provides accurate text recognition.
+    """
+    )
+    
+    gr.Markdown(
+    """
+    <div class="footer">
+    Developed with ❤️ by Arnav Agarwal | © 2024 All Rights Reserved
+    </div>
+    """
+    )
+
+if __name__ == "__main__":
+    iface.launch()

captcha_model.hdf5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc5e6a8bd85d16acaaede3bc8050c9ff1f9f4ea8c2602f2bee16bc846d5e11a
+size 8045424

captcha_solver_hf.py

@@ -0,0 +1,62 @@
+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

requirements.txt

@@ -0,0 +1,5 @@
+numpy
+imutils
+sklearn
+tensorflow
+keras