insightface/recognition/_tools_/README.md

I. CPP-Align

II. Face Mask Renderer

We provide a simple tool to add masks on face images automatically.

We can use this tool to do data augmentation while training our face recognition models.

Face Image	OP	Mask Image	Out
	+F
	+F
	+H

F means FULL while H means HALF.

Prepare

• insightface package library

  pip install -U insightface

• insightface model pack

  bash> insightface-cli model.download antelope

• BFM models

  Please follow the tutorial of https://github.com/YadiraF/face3d/tree/master/examples/Data/BFM to generate BFM.mat and BFM_UV.mat. Put them into the insightface model pack directory, such as ~/.insightface/models/antelope/

• mask images

  some mask images are included in insightface package, such as 'mask_blue', 'mask_white', 'mask_black' and 'mask_green'.

Add Mask to Face Image

Please refer to make_renderer.py for detail example.

(1) init renderer:

import insightface
from insightface.app import MaskRenderer
tool = MaskRenderer()
tool.prepare(ctx_id=0, det_size=(128,128)) #use gpu

(2) load face and mask images

image = cv2.imread("../../deploy/Tom_Hanks_54745.png")
mask_image  = "mask_blue"

(3) build necessary params for face image, this can be done in offline.

params = tool.build_params(image)

(4) do mask render, it costs about 10ms on 224x224 UV size, CPU single thread.

mask_out = tool.render_mask(image, mask_image, params)

(5) do half mask render.

mask_half_out = tool.render_mask(image, mask_image, params, positions=[0.1, 0.5, 0.9, 0.7])