Skip to content

Latest commit

 

History

History
36 lines (25 loc) · 1.31 KB

README.md

File metadata and controls

36 lines (25 loc) · 1.31 KB
Raw

tensorflow_person_image_remove_background

  • Model weights url
  • Object Detection: SSD ResNet50 V1 FPN 640x640 (RetinaNet50)
  • Image Segmentation: Unet

Target

  • Remove person images or videos background
  • 此模組適合正面且單人的圖片
  • This model is suitable for frontal and single-person images.

Using

  • Python
  • Tensorflow
  • Opencv
  • Numpy
  • and so on.

What our code do?

  1. Object Detection > Get boxes
  2. Image Segmentation in each detected image boxes > Get mask
  3. Remove background > Result

You can try this model.

References