Creating a PyCharm Project - marios2019/MAI644-Computer-Vision-Fall-2023-2024 GitHub Wiki

Follow these steps to create a new PyCharm project for your MAI644 Computer Vision course:

1. Launch PyCharm:

   • Open PyCharm from your applications or program list.

2. Create a New Project:

   • Click on "File" in the top menu.
   • Select "New Project."

3. Project Location:

   • Choose a location on your computer where you want to create the project folder. You can click the "..." button to browse and select a location.

4. Select Project Interpreter:

   • In the "Python Interpreter" section, select the Conda environment you created earlier (e.g., mai644) as the project interpreter (Previously configured interpreter). This environment should have Python 3.11 and the required packages.

5. Specify Project Details:

   • Enter the name of your project in the "Project name" field.

6. Project Template:

   • Select the appropriate project template based on your project type. For most Python projects, you can choose the "Pure Python" template.

7. Create Project:

   • Click the "Create" button to create your project.

8. Verify:

   • Download the following images

building_right.jpg

building_left.jpg

• Run the following piece of code in order to verify that the newly created project is using the correct Python interpreter:

import numpy as np
import cv2
from matplotlib import pyplot as plt


def main():
    # Load images
    img1 = cv2.imread('building_left.jpg', cv2.IMREAD_UNCHANGED)
    img2 = cv2.imread('building_right.jpg', cv2.IMREAD_UNCHANGED)

    # Convert to gray scale
    img1GRAY = cv2.cvtColor(img1, cv2.COLOR_BGR2GRAY)
    img2GRAY = cv2.cvtColor(img2, cv2.COLOR_BGR2GRAY)

    # Initiate SIFT detector
    sift = cv2.SIFT.create()

    # find the keypoints and descriptors with SIFT
    kp1, des1 = sift.detectAndCompute(img1GRAY, None)
    kp2, des2 = sift.detectAndCompute(img2GRAY, None)

    # BFMatcher with default params
    bf = cv2.BFMatcher()
    matches = bf.knnMatch(des1, des2, k=2)

    # Apply ratio test
    good = []
    for m, n in matches:
        if m.distance < 0.75 * n.distance:
            good.append([m])

    # cv2.drawMatchesKnn expects list of lists as matches.
    img3 = np.empty((max(img1.shape[0], img2.shape[0]), img1.shape[1] + img2.shape[1], 3), dtype=np.uint8)
    cv2.drawMatchesKnn(img1, kp1, img2, kp2, outImg=img3, matches1to2=good, flags=2)

    # Plot images
    plt.figure("Feature Matching")

    ax1 = plt.subplot(2, 2, 1)
    ax1.axis("off")  # Remove axes
    ax1.imshow(cv2.cvtColor(img1, cv2.COLOR_BGR2RGB))  # Convert BGR to RGB
    ax1.set_title("Left Image")

    ax2 = plt.subplot(2, 2, 2)
    ax2.axis("off")
    ax2.imshow(cv2.cvtColor(img2, cv2.COLOR_BGR2RGB))
    ax2.set_title("Right Image")

    ax3 = plt.subplot2grid((2, 2), (1, 0), colspan=2)
    ax3.axis("off")
    ax3.imshow(cv2.cvtColor(img3, cv2.COLOR_BGR2RGB))
    ax3.set_title('Feature Correspondences')

    plt.show()


if __name__ == '__main__':
    main()

• If everything was set up correctly, you should be able to see the following figure:

Your PyCharm project is now set up and ready for you to start working on your MAI644 Computer Vision assignments. Happy coding!