Home | Team Members | Project Description | Code | UML Diagrams | Results |

Code 

alpha_blending_v2.py: everything¶

import tkinter as tk

from tkinter import filedialog, messagebox

from tkinter import ttk

import configparser

import cv2

import numpy as np

import os

import logging

from PIL import Image, ImageTk

# Setup logging

logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')

# ConfigReader class definition

class ConfigReader:

    def __init__(self, config_path):

        self.config_parser = configparser.ConfigParser()

        self.config_parser.read(config_path)

    def getImageName(self):

        return str(self.config_parser['DEFAULT']['image_name'])

    def getProjectedImageWidth(self):

        return int(self.config_parser['DEFAULT']['projected_image_width'])

    def getProjectedOverlapWidth(self):

        return int(self.config_parser['DEFAULT']['projected_overlap_width'])

    def getGamma(self):

        return float(self.config_parser['DEFAULT']['gamma'])

    def getImageSide(self):

        return int(self.config_parser['DEFAULT']['image_side'])

    def getTransparencyFactor(self):

        return float(self.config_parser['DEFAULT'].get('transparency_factor', 1.0))

# MainDisplay class definition

class MainDisplay:

    def readImage(self, image_path):

        # Loads an image from the specified path with 3 channels (BGR)

        image = cv2.imread(image_path, cv2.IMREAD_COLOR)

        if image is None:

            logging.error(f"Error loading image at {image_path}")

        else:

            logging.info(f"Loaded image {image_path} with shape: {image.shape}")

        return image

    def setImage(self, image):

        # Placeholder for image processing if necessary

        # Here you can modify or prepare the image before displaying

        logging.info(f"Setting image with shape: {image.shape}")

        return image

# MaskCreator class definition

class MaskCreator:

    def __init__(self, image, transparency_factor):

        self.__image = image

        self.__alpha_gradient = None

        self.__gamma_corrected = None

        self.result_image = None

        self.__mask = None

        self.transparency_factor = transparency_factor

    def smoothstep(self, edge0, edge1, x):

        # Smoothstep function for smoother transition (non-linear gradient)

        x = np.clip((x - edge0) / (edge1 - edge0), 0, 1)

        return x * x * (3 - 2 * x)

    def create_mask(self, image_side, mask_width, image_width):

        self.__mask = self.__image.shape[1] * mask_width // image_width

        gradient = np.linspace(0, 1, self.__mask)

        # Apply smoothstep to create a smoother gradient

        smooth_gradient = self.smoothstep(0, 1, gradient)

        # Apply transparency factor to adjust the strength of the blending

        smooth_gradient = smooth_gradient * self.transparency_factor

        if image_side == 1:

            # Gradient from transparent to opaque (middle to right)

            self.__alpha_gradient = smooth_gradient

        elif image_side == 0:

            # Gradient from opaque to transparent (left to middle)

            self.__alpha_gradient = smooth_gradient[::-1]  # Reverse for the left side

    def gammaCorrection(self, gamma):

        # Apply gamma correction

        inv_gamma = 1.0 / gamma

        table = np.array([((i / 255.0) ** inv_gamma) * 255

                          for i in np.arange(256)]).astype("uint8")

        self.__gamma_corrected = cv2.LUT(self.__image, table)

        logging.info(f"Applied gamma correction with gamma={gamma}")

        # Save gamma corrected image for inspection

        cv2.imwrite("gamma_corrected.png", self.__gamma_corrected)

    def alpha_blending(self, image_side):

        """ 

        Applies alpha blending on the gamma-corrected image.

        Combines the gamma-corrected part of the image with a black background using the alpha gradient mask.

        """ 

        # Initialize result_image to be the gamma-corrected image

        self.result_image = self.__gamma_corrected.copy()

        if image_side == 1:  # Right side

            # Create a region of interest (ROI) where blending will occur (right side of the image)

            roi = self.result_image[:, :self.__mask].astype(np.float32)

            # Create black background for blending

            black_background = np.zeros_like(roi, dtype=np.float32)

            # Apply the alpha mask to blend gamma-corrected image with black background

            alpha = self.__alpha_gradient.reshape(1, -1, 1).astype(np.float32)

            blended = (alpha * roi + (1 - alpha) * black_background)

            blended = np.clip(blended, 0, 255).astype(np.uint8)

            # Place the blended region back in the result image

            self.result_image[:, :self.__mask] = blended

            logging.info(f"Applied alpha blending on the right side with mask width {self.__mask}")

            # Save blended region for debugging

            cv2.imwrite("blended_right_side.png", blended)

        elif image_side == 0:  # Left side

            # Create a region of interest (ROI) where blending will occur (left side of the image)

            roi = self.result_image[:, -self.__mask:].astype(np.float32)

            # Create black background for blending

            black_background = np.zeros_like(roi, dtype=np.float32)

            # Apply the alpha mask to blend gamma-corrected image with black background

            alpha = self.__alpha_gradient.reshape(1, -1, 1).astype(np.float32)

            blended = (alpha * roi + (1 - alpha) * black_background)

            blended = np.clip(blended, 0, 255).astype(np.uint8)

            # Place the blended region back in the result image

            self.result_image[:, -self.__mask:] = blended

            logging.info(f"Applied alpha blending on the left side with mask width {self.__mask}")

            # Save blended region for debugging

            cv2.imwrite("blended_left_side.png", blended)

def process_image(config_path, main_display):

    """ 

    Processes an image based on the provided configuration.

    Args:

        config_path (str): Path to the configuration file.

        main_display (MainDisplay): Instance of MainDisplay for image operations.

    Returns:

        tuple: Processed image and its corresponding name.

    """ 

    # Load configuration

    config_reader = ConfigReader(config_path)

    # Retrieve configuration parameters

    mask_width = config_reader.getProjectedOverlapWidth()

    image_width = config_reader.getProjectedImageWidth()

    gamma = config_reader.getGamma()

    image_side = config_reader.getImageSide()

    image_path = config_reader.getImageName()

    transparency_factor = config_reader.getTransparencyFactor()

    # Determine image side name

    if image_side == 0:

        image_name = 'left'

    elif image_side == 1:

        image_name = 'right'

    else:

        logging.error(f"Invalid ImageSide value in {config_path}. Use 0 for left image, 1 for right image.")

        return None, None

    # Load image

    image = main_display.readImage(image_path)

    if image is None:

        logging.error(f"Image loading failed for {image_path}. Skipping...")

        return None, None

    # Initialize result image

    result_image = main_display.setImage(image).copy()

    cv2.imwrite("initial_result_image.png", result_image)  # Save initial image

    # Initialize MaskCreator

    mask_creator = MaskCreator(image, transparency_factor)

    # Apply image modifications

    mask_creator.create_mask(image_side, mask_width, image_width)

    mask_creator.gammaCorrection(gamma)

    mask_creator.result_image = result_image

    mask_creator.alpha_blending(image_side)

    # Save final result for inspection

    cv2.imwrite("final_result_image.png", mask_creator.result_image)

    return mask_creator.result_image, image_name

def save_image(image, name):

    """ 

    Save the processed image to the project folder.

    Args:

        image (np.ndarray): The image to be saved.

        name (str): Name of the image (left or right).

    """ 

    # Define the output path

    output_dir = os.path.join(os.getcwd(), "processed_images")

    os.makedirs(output_dir, exist_ok=True)

    # Create the output file name

    output_path = os.path.join(output_dir, f"processed_image_{name}.png")

    # Save the image

    cv2.imwrite(output_path, image)

    logging.info(f"Saved processed image: {output_path}")

# GUI Application class definition

class ImageProcessingApp:

    def __init__(self, root):

        self.root = root

        self.root.title("Image Processing Application")

        # UI elements

        self.config_left = "" 

        self.config_right = "" 

        self.left_image_label = tk.Label(root, text="Left Image: None", anchor="w")

        self.left_image_label.pack(fill="x", padx=5, pady=5)

        self.right_image_label = tk.Label(root, text="Right Image: None", anchor="w")

        self.right_image_label.pack(fill="x", padx=5, pady=5)

        self.select_left_button = tk.Button(root, text="Select Left Config", command=self.select_left_config)

        self.select_left_button.pack(pady=5)

        self.select_right_button = tk.Button(root, text="Select Right Config", command=self.select_right_config)

        self.select_right_button.pack(pady=5)

        self.process_button = tk.Button(root, text="Process Images", command=self.process_images, state="disabled")

        self.process_button.pack(pady=10)

        self.progress_bar = ttk.Progressbar(root, orient="horizontal", length=300, mode="determinate")

        self.progress_bar.pack(pady=10)

        self.image_display = tk.Label(root)

        self.image_display.pack()

    def select_left_config(self):

        self.config_left = filedialog.askopenfilename(title="Select Left Config File",

                                                      filetypes=[("INI files", "*.ini")])

        if self.config_left:

            self.left_image_label.config(text=f"Left Image Config: {os.path.basename(self.config_left)}")

            self.enable_process_button()

    def select_right_config(self):

        self.config_right = filedialog.askopenfilename(title="Select Right Config File",

                                                       filetypes=[("INI files", "*.ini")])

        if self.config_right:

            self.right_image_label.config(text=f"Right Image Config: {os.path.basename(self.config_right)}")

            self.enable_process_button()

    def enable_process_button(self):

        if self.config_left and self.config_right:

            self.process_button.config(state="normal")

    def process_images(self):

        config_files = [self.config_left, self.config_right]

        processed_images = {}

        self.progress_bar["value"] = 0

        self.root.update_idletasks()

        for i, config_file in enumerate(config_files):

            image, name = process_image(config_file, MainDisplay())

            if image is not None and name is not None:

                processed_images[name] = image

            self.progress_bar["value"] += 50

            self.root.update_idletasks()

        for name, img in processed_images.items():

            save_image(img, name)

        self.display_image(processed_images)

        self.progress_bar["value"] = 100

        self.root.update_idletasks()

        messagebox.showinfo("Processing Complete", "Images processed and saved successfully.")

    def display_image(self, processed_images):

        for name, img in processed_images.items():

            img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

            pil_img = Image.fromarray(img_rgb)

            img_tk = ImageTk.PhotoImage(pil_img)

            self.image_display.config(image=img_tk)

            self.image_display.image = img_tk

def main():

    root = tk.Tk()

    app = ImageProcessingApp(root)

    root.mainloop()

if __name__ == "__main__":

    main()