Add face blurring functionality

sweep-ai[bot] commented 1 year ago

Description

This PR adds the functionality to detect and blur faces in videos. It includes the following changes:

Added a new function blur_faces_in_video in face_blur.py that uses OpenCV to detect faces in each frame of a video and apply a blur effect to the detected faces.
Integrated the blur_faces_in_video function into the existing video processing pipeline in the start function in main.py. Now, after the video is downloaded, the function is called to blur faces in the video before further processing.
Added a new checkbox in the GUI in download_youtube_playlist.py for the user to select whether to blur faces in the video. The value of the checkbox is passed to the start function in main.py.

Added face_blur.py with the blur_faces_in_video function for face detection and blurring.
Modified main.py to import and call the blur_faces_in_video function in the start function.
Modified download_youtube_playlist.py to add a new checkbox for face blurring in the GUI and pass the value to the start function.

Fixes #6.

To checkout this PR branch, run the following command in your terminal:

git checkout {pull_request.branch_name}

🎉 Latest improvements to Sweep:

Use Sweep Map to break large issues into smaller sub-issues, perfect for large tasks like "Sweep (map): migrate from React class components to function components"
Getting Sweep to format before committing! Check out Sweep Sandbox Configs to set it up.
We released a demo of our chunker, where you can find the corresponding blog and code.

💡 To get Sweep to edit this pull request, you can:

a0ali0taha commented 1 year ago

sweep: it should detect only woman's faces not all human faces, please refactor the code to detect and blue woman faces in the videos

sweep-ai[bot] commented 1 year ago

sweep: it should detect only woman's faces not all human faces, please refactor the code to detect and blue woman faces in the videos

Hi @a0ali0taha,

I decided to make the following changes:

File Path	Proposed Changes
`face_blur.py`	Modify face_blur.py with contents: • Update the face detection algorithm to use the new model trained specifically for women's faces.
`main.py`	Modify main.py with contents: • Modify the `blur_faces_in_video` function call in the `start` function to use the updated face detection algorithm.

a0ali0taha commented 1 year ago

sweep: search for a model to detect woman's face

sweep-ai[bot] commented 1 year ago

sweep: search for a model to detect woman's face

Hi @a0ali0taha,

I decided to make the following changes:

File Path	Proposed Changes
`path/to/new_model.xml`	Create path/to/new_model.xml with contents: • Download or create a model that can detect a woman's face and save it as "new_model.xml".
`download_youtube_playlist.py`	Modify download_youtube_playlist.py with contents: • Add a new import statement at the top of the file: `import cv2` • In the `download_button_clicked` function, add a new line after the `checkbox_telegram` variable declaration: - `checkbox_blur_var = BooleanVar()` - `checkbox_blur_var.set(False)` - `checkbox_blur = tk.Checkbutton(window, text="Blur Faces in Video", variable=checkbox_blur_var)` - `checkbox_blur.pack(pady=5)`
`face_blur.py`	Modify face_blur.py with contents: • Add a new import statement at the top of the file: `import cv2` • Modify the `blur_faces_in_video` function to use the newly created model for face detection: - Load the face detector using the new model: `face_cascade = cv2.CascadeClassifier('path/to/new_model.xml')`
`main.py`	Modify main.py with contents: • Add a new import statement at the top of the file: `from face_blur import blur_faces_in_video` • In the `start` function, after downloading the video and before calling the `handle` function, add a new line to blur faces in the video: - `blurred_video_path = blur_faces_in_video(video_path, video_path.replace('.mp4', '_blurred.mp4'))` - Pass `blurred_video_path` instead of `video_path` to the `handle` function.