I would like to add the following features: the ability to output images beyond the box detection range, the ability to normalize facial images to the same size based on facial proportion, the ability to process images with alpha channels, and the ability to output images with alpha channels. #11413
Labels
Search before asking
Description
the ability to output images beyond the box detection range,
the ability to normalize facial images to the same size based on facial proportion,
the ability to process images with alpha channels,
and the ability to output images with alpha channels.
Use case
I am an art professional, and I dislike cutting images. I hope to automate the image processing.
Additional
By modifying plots.py, I successfully increased the cropping range of the cropped image. (I modified pad=300.)
def save_one_box(xyxy, im, file=Path('im.jpg'), gain=1.02, pad=300, square=False, BGR=False, save=True):
However, I couldn't handle the issue with the alpha channel. My coding skills are poor, so I could only write two scripts - one for adding a green background to the image, and another for removing the green background from the image - to deal with the transparency issue.
Add a green background
批量添加绿幕.txt
Remove a green background.
批量去除绿幕.txt
This is my processing workflow: original image with alpha channel > add green background to images using batch processing script > use YOLOv5 to detect faces > crop beyond the detected box > remove green background from output images using batch processing script.
I really need these features! Please help me out!
Are you willing to submit a PR?
The text was updated successfully, but these errors were encountered: