Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import cv2 | |
| import numpy as np | |
| from skimage.metrics import structural_similarity as ssim | |
| def preprocess_image(image, blur_value): | |
| # Convert to grayscale | |
| gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) | |
| # Apply Gaussian blur to reduce noise | |
| blurred = cv2.GaussianBlur(gray, (blur_value, blur_value), 0) | |
| return blurred | |
| def compare_images(image1, image2, blur_value, technique, threshold_value): | |
| # Preprocess images | |
| gray1 = preprocess_image(image1, blur_value) | |
| gray2 = preprocess_image(image2, blur_value) | |
| # Compute SSIM between the two images | |
| score, diff = ssim(gray1, gray2, full=True) | |
| diff = (diff * 255).astype("uint8") | |
| if technique == "Adaptive Threshold": | |
| _, thresh = cv2.threshold(diff, 30, 255, cv2.THRESH_BINARY_INV) | |
| elif technique == "Otsu's Threshold": | |
| _, thresh = cv2.threshold(diff, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU) | |
| else: # Simple Binary | |
| _, thresh = cv2.threshold(diff, threshold_value, 255, cv2.THRESH_BINARY) | |
| # Find contours of differences | |
| contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE) | |
| # Filter out small noise using contour area threshold | |
| filtered_contours = [cnt for cnt in contours if cv2.contourArea(cnt) > 500] | |
| # Create a mask to isolate only the significant added object | |
| mask = np.zeros_like(image1) | |
| cv2.drawContours(mask, filtered_contours, -1, (255, 255, 255), thickness=cv2.FILLED) | |
| # Apply the mask to highlight the object added in the second image | |
| highlighted = cv2.bitwise_and(image2, mask) | |
| # Overlay the difference in magenta over the first image | |
| diff_colored = cv2.cvtColor(diff, cv2.COLOR_GRAY2BGR) | |
| diff_colored[:, :, 1:] = 0 # Keep only red channel for magenta effect | |
| overlayed = cv2.addWeighted(image1, 0.7, diff_colored, 0.3, 0) | |
| return highlighted, overlayed | |
| def update_threshold_visibility(technique): | |
| return gr.update(visible=(technique == "Simple Binary")) | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# Object Difference Highlighter\nUpload two images: one without an object and one with an object. The app will highlight only the newly added object and show the real differences in magenta overlayed on the original image.") | |
| with gr.Row(): | |
| img1 = gr.Image(type="numpy", label="Image Without Object") | |
| img2 = gr.Image(type="numpy", label="Image With Object") | |
| blur_slider = gr.Slider(minimum=1, maximum=15, step=2, value=5, label="Gaussian Blur") | |
| technique_dropdown = gr.Dropdown(["Adaptive Threshold", "Otsu's Threshold", "Simple Binary"], label="Thresholding Technique", value="Adaptive Threshold", interactive=True) | |
| threshold_slider = gr.Slider(minimum=0, maximum=255, step=1, value=50, label="Threshold Value", visible=False) | |
| technique_dropdown.change(update_threshold_visibility, inputs=[technique_dropdown], outputs=[threshold_slider]) | |
| output1 = gr.Image(type="numpy", label="Highlighted Differences") | |
| output2 = gr.Image(type="numpy", label="Raw Difference Overlay (Magenta)") | |
| btn = gr.Button("Process") | |
| btn.click(compare_images, inputs=[img1, img2, blur_slider, technique_dropdown, threshold_slider], outputs=[output1, output2]) | |
| demo.launch() |