Upload 9 files

.gitignore

@@ -0,0 +1 @@
+__pycache__/

app.py

@@ -0,0 +1,132 @@
+import gradio as gr 
+from processes import * 
+
+
+def processing_pipeline(input_image):
+    # Convert Gradio image to OpenCV format
+    input_image = input_image.astype('uint8')
+
+    # Apply CLAHE
+    clahe_image = clahe(input_image)
+
+    # Apply sharpening
+    sharpened_image = sharpen(clahe_image, sharpen_strength=0.5)
+
+    # Apply denoising
+    onlyDenoising_image = denoise(clahe_image)
+
+    # Apply sharpening + denoising
+    denoised_image = denoise(sharpened_image, strength=10)
+
+    # apply denoiseing + shaprening
+    denoiseSharp_image = sharpen(denoise(input_image))
+
+    # Generate histograms
+    original_hist = plot_histogram(input_image)
+    clahe_hist = plot_histogram(clahe_image)
+    sharpened_hist = plot_histogram(sharpened_image)
+    denoised_hist = plot_histogram(denoised_image)
+    denoiseSharp_hist = plot_histogram(denoiseSharp_image)
+    onlyDenoising_hist = plot_histogram( onlyDenoising_image)
+
+    # Calculate SNR, CNR, and PSNR for each image
+    snr_original = "Cannot Calculate"
+    snr_clahe = calculate_snr(clahe_image, input_image - clahe_image)
+    snr_sharpened = calculate_snr(sharpened_image, input_image - sharpened_image)
+    snr_denoised = calculate_snr(denoised_image, input_image - denoised_image)
+    snr_denoiseSharp = calculate_snr(denoiseSharp_image,input_image - denoiseSharp_image)
+    snr_onlyDenoise = calculate_snr(onlyDenoising_image,input_image - onlyDenoising_image)
+
+    cnr_original = "Cannot Calculate"
+    cnr_clahe = calculate_cnr(clahe_image, input_image - clahe_image)
+    cnr_sharpened = calculate_cnr(sharpened_image, input_image - sharpened_image)
+    cnr_denoised = calculate_cnr(denoised_image, input_image - denoised_image)
+    cnr_denoiseSharp = calculate_cnr(denoiseSharp_image,input_image - denoiseSharp_image)
+    cnr_onlyDenoise = calculate_cnr(onlyDenoising_image,input_image - onlyDenoising_image)
+
+    psnr_original = "Cannot Calculate"
+    psnr_clahe = calculate_psnr(clahe_image, input_image)
+    psnr_sharpened = calculate_psnr(sharpened_image, input_image)
+    psnr_denoised = calculate_psnr(denoised_image, input_image)
+    psnr_denoiseSharp = calculate_psnr(denoiseSharp_image,input_image - denoiseSharp_image)
+    psnr_onlyDenoise = calculate_psnr(onlyDenoising_image,input_image - onlyDenoising_image)
+
+
+
+    return (input_image, clahe_image, sharpened_image, denoised_image,denoiseSharp_image,onlyDenoising_image,
+            original_hist, clahe_hist, sharpened_hist, denoised_hist,denoiseSharp_hist,onlyDenoising_hist ,
+            snr_original, snr_clahe, snr_sharpened, snr_denoised,snr_denoiseSharp,snr_onlyDenoise,
+            cnr_original, cnr_clahe, cnr_sharpened, cnr_denoised, cnr_denoiseSharp, cnr_onlyDenoise,
+            psnr_original, psnr_clahe, psnr_sharpened, psnr_denoised, psnr_denoiseSharp,psnr_onlyDenoise )
+
+
+with gr.Blocks() as demo:
+
+    inputImg = gr.Image(label="Input Image")
+    processs = gr.Button("Process")
+    gr.ClearButton()
+
+    with gr.Column():
+        # Original Image
+        with gr.Row():
+            org_image = gr.Image(label="Original")
+            org_image_histogram = gr.Image(label="Original Histogram")
+            with gr.Column():
+                org_image_snr = gr.Textbox(label="SNR - Original")
+                org_image_cnr = gr.Textbox(label="CNR - Original")
+                org_image_psnr = gr.Textbox(label="PSNR - Original")
+
+        with gr.Row():
+            # CLAHE
+            clahe_image = gr.Image(label="CLAHE")
+            clahe_image_histogram = gr.Image(label="CLAHE Histogram")
+            with gr.Column():
+                clahe_image_snr = gr.Textbox(label="SNR - CLAHE")
+                clahe_image_cnr = gr.Textbox(label="CNR - CLAHE")
+                clahe_image_psnr = gr.Textbox(label="PSNR - CLAHE")
+
+        with gr.Row():
+            # CLAHE + Sharpen
+            clahe_sharpen_image = gr.Image(label="CLAHE + Sharpen")
+            clahe_sharpen_image_histogram = gr.Image(label="CLAHE + Sharpen Histogram")
+            with gr.Column():
+                clahe_sharpen_image_snr = gr.Textbox(label="SNR - CLAHE + Sharpen")
+                clahe_sharpen_image_cnr = gr.Textbox(label="CNR - CLAHE + Sharpen")
+                clahe_sharpen_image_psnr = gr.Textbox(label="PSNR - CLAHE + Sharpen")
+
+        with gr.Row():
+            # CLAHE + Denoising
+            clahe_denoise_image = gr.Image(label= "CLAHE + Denoise")
+            clahe_denoise_image_histogram = gr.Image(label="CLAHE + Denoise Histogram")
+            with gr.Column():
+                clahe_denoise_image_snr = gr.Textbox(label="SNR - CLAHE + Denoise")
+                clahe_denoise_image_cnr = gr.Textbox(label="CNR - CLAHE + Denoise")
+                clahe_denoise_image_psnr =  gr.Textbox(label="PSNR - CLAHE + Denoise")
+
+
+
+        with gr.Row():
+            # CLAHE + Sharpen + Denoise
+            clahe_sharpen_denoise_image = gr.Image(label="CLAHE + Sharpen + Denoise")
+            clahe_sharpen_denoise_image_histogram = gr.Image(label="CLAHE + Sharpen + Denoise Histogram")
+            with gr.Column():
+                clahe_sharpen_denoise_image_snr = gr.Textbox(label="SNR - CLAHE + Sharpen + Denoise")
+                clahe_sharpen_denoise_image_cnr = gr.Textbox(label="CNR - CLAHE + Sharpen + Denoise")
+                clahe_sharpen_denoise_image_psnr = gr.Textbox(label="PSNR - CLAHE + Sharpen + Denoise")
+
+        with gr.Row():
+            clahe_denoise_sharpen_image = gr.Image(label= "CLAHE + Denoise + Sharpen")
+            clahe_denoise_sharpen_image_histogram = gr.Image(label="CLAHE + Denoise + Sharpen Histogram")
+            with gr.Column():
+                clahe_denoise_sharpen_image_snr = gr.Textbox(label="SNR - CLAHE + Denoise + Sharpen")
+                clahe_denoise_sharpen_image_cnr = gr.Textbox(label="CNR - CLAHE + Denoise + Sharpen")
+                clahe_denoise_sharpen_image_psnr = gr.Textbox(label="PSNR - CLAHE + Denoise + Sharpen")
+
+    processs.click(processing_pipeline,inputs=[inputImg], outputs = [org_image,clahe_image,clahe_sharpen_image,clahe_sharpen_denoise_image, clahe_denoise_sharpen_image,clahe_denoise_image,
+                                                                 org_image_histogram,clahe_image_histogram,clahe_sharpen_image_histogram,clahe_sharpen_denoise_image_histogram,clahe_denoise_sharpen_image_histogram,clahe_denoise_image_histogram ,
+                                                                 org_image_snr,clahe_image_snr,clahe_sharpen_image_snr,clahe_sharpen_denoise_image_snr,clahe_denoise_sharpen_image_snr ,clahe_denoise_image_snr,
+                                                                 org_image_cnr,clahe_image_cnr,clahe_sharpen_image_cnr,clahe_sharpen_denoise_image_cnr,clahe_denoise_sharpen_image_cnr,clahe_denoise_image_cnr,
+                                                                 org_image_psnr,clahe_image_psnr,clahe_sharpen_image_psnr,clahe_sharpen_denoise_image_psnr,clahe_denoise_sharpen_image_psnr,clahe_denoise_image_psnr] )
+
+
+demo.launch()

processes.py

@@ -0,0 +1,101 @@
+import numpy as np
+import cv2
+import matplotlib.pyplot as plt
+
+def calculate_snr(image, noise):
+    # Calculate signal power
+    signal_power = np.mean(np.square(image))
+
+    # Calculate noise power
+    noise_power = np.mean(np.square(noise))
+
+    # Calculate SNR
+    snr = 10 * np.log10(signal_power / noise_power)
+    
+    return snr
+
+def calculate_cnr(image, noise):
+    # Calculate mean signal
+    mean_signal = np.mean(image)
+
+    # Calculate mean noise
+    mean_noise = np.mean(noise)
+
+    # Calculate standard deviation of signal
+    std_signal = np.std(image)
+
+    # Calculate standard deviation of noise
+    std_noise = np.std(noise)
+
+    # Calculate CNR
+    cnr = np.abs(mean_signal - mean_noise) / np.sqrt(std_signal**2 + std_noise**2)
+
+    return cnr
+
+def calculate_psnr(image, reconstructed_image):
+    # Convert images to float64
+    image = np.float64(image)
+    reconstructed_image = np.float64(reconstructed_image)
+
+    # Calculate MSE
+    mse = np.mean((image - reconstructed_image) ** 2)
+
+    # Calculate maximum pixel value
+    max_pixel_value = np.max(image)
+
+    # Calculate PSNR
+    psnr = 20 * np.log10(max_pixel_value / np.sqrt(mse))
+
+    return psnr
+
+def clahe(img, clip_limit=2.0, tile_size=(8, 8)):
+    # Create CLAHE object
+    clahe = cv2.createCLAHE(clipLimit=clip_limit, tileGridSize=tile_size)
+    
+    # Convert image to LAB color space
+    lab = cv2.cvtColor(img, cv2.COLOR_BGR2LAB)
+    
+    # Split LAB channels
+    l, a, b = cv2.split(lab)
+    
+    # Apply CLAHE to the L channel
+    cl = clahe.apply(l)
+    
+    # Merge the CLAHE enhanced L channel with the original A and B channels
+    limg = cv2.merge((cl, a, b))
+    
+    # Convert LAB image back to BGR
+    return cv2.cvtColor(limg, cv2.COLOR_LAB2BGR)
+
+def sharpen(image, sharpen_strength=1.0):
+    # Apply sharpening using unsharp masking
+    blurred = cv2.GaussianBlur(image, (0, 0), 3)
+    sharpened = cv2.addWeighted(image, 1.0 + sharpen_strength, blurred, -sharpen_strength, 0)
+    return sharpened
+
+def denoise(image, strength=10):
+    # Apply non-local means denoising
+    denoised = cv2.fastNlMeansDenoisingColored(image, None, strength, strength, 7, 21)
+    return denoised
+
+def plot_histogram(image):
+    # Calculate histogram
+    hist = cv2.calcHist([image], [0], None, [256], [0, 256])
+    
+    # Plot histogram
+    plt.figure(figsize=(6, 4))
+    plt.plot(hist, color='black')
+    plt.xlabel('Pixel Value')
+    plt.ylabel('Frequency')
+    plt.title('Histogram')
+    plt.xlim([0, 256])
+    plt.grid(True)
+    plt.tight_layout()
+    
+    # Convert plot to numpy array
+    plt_img = plt.gcf()
+    plt_img.canvas.draw()
+    img_np = np.array(plt_img.canvas.renderer.buffer_rgba())
+    plt.close()
+    
+    return img_np[:, :, :3]

requirements.txt

@@ -0,0 +1,65 @@
+aiofiles==23.2.1
+altair==5.3.0
+annotated-types==0.6.0
+anyio==4.3.0
+attrs==23.2.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.2.1
+cycler==0.12.1
+fastapi==0.110.3
+ffmpy==0.3.2
+filelock==3.14.0
+fonttools==4.51.0
+fsspec==2024.3.1
+gradio==4.28.3
+gradio_client==0.16.0
+h11==0.14.0
+httpcore==1.0.5
+httpx==0.27.0
+huggingface-hub==0.22.2
+idna==3.7
+importlib_resources==6.4.0
+Jinja2==3.1.3
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.8.4
+mdurl==0.1.2
+numpy==1.26.4
+opencv-python==4.9.0.80
+orjson==3.10.2
+packaging==24.0
+pandas==2.2.2
+pillow==10.3.0
+pydantic==2.7.1
+pydantic_core==2.18.2
+pydub==0.25.1
+Pygments==2.17.2
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.0
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.0
+ruff==0.4.2
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.37.2
+tomlkit==0.12.0
+toolz==0.12.1
+tqdm==4.66.2
+typer==0.12.3
+typing_extensions==4.11.0
+tzdata==2024.1
+urllib3==2.2.1
+uvicorn==0.29.0
+websockets==11.0.3