Face_Segmentation

Analysis of the problem statement and Dataset:

In this project, the goal is to train a model for segmenting various parts of face.

Dataset: link

Number of Images: Train(19535) and Validation (2653)

Original Dataset have 18 classes can be referred from here, However, I compounded classes like left_ear and right_ear to ear, etc. and also neglected the unnecessary classes like hair, hat, etc.

Classes: 8

• 0: Background
• 1: Face Skin
• 2: Eyebrows
• 4: Eyes
• 6: Nose
• 7: Mouth
• 13: Ears
• 16: Glasses

Evaluation Metric: Precision, Recall, Dice Score (F1-Score), Jacard Score (mIoU Score)

Loss: Dice Loss + Categorical_Cross_Entropy Loss + Jacard Loss

Images are in very big in size with varying orientation (Portrait as well as Landscape). So, for this project, I have decided to used images and masks of resized value of 256 x 256.

Pixel wise distribution of classes per image:

Model Training:

• I used PSPNet with ResNet50 as a backbone and Deeplabv3+ model with EfficientNetB0 as a backbone
• I used 4000 training images and 800 validation images only for training because of shortage of infrastructure
• I trained the model for 39 epochs with initial learning rate of 0.1 with SGD (Stochastic Gradient Descent) optimizer and Reduce Learning Rate on Plateau with patience of 4 and factor of 0.5)
• I also used Early Stopping callback with patience of 10 epochs to prevent overfitting

Graphs (Loss, DiceScore (F1-Score), IOU_Score):

• PSPNet

Learning Rate	loss	F1	IOU

• Deeplab

Learning Rate	loss	F1	IOU

Predictions on 3 images from Test Dataset:

• PSPNet

Image	Ground Truth	Prediction

• Deeplab

Image	Ground Truth	Prediction

Performance Comparison:

• On Complete (Train: 4000 and Val: 800 images) Dataset:

• On Test Dataset (7766 images):

Future Steps:

• Try training model with complete dataset
• Try training model with different loss functions
• Try training Deeplabv3+ and PSPNet models with different backbones
• Try with different model such as Unet, LinkNet, ICNet with different backbones
• Try training model further for more epochs
• Try gathering more data for training by new annotations and augmentations
• Try training the model further with smaller learning rate with Adam or SGD (with momentum)