You are on page 1of 21

Anthropomorphic Animal Face Masking using

Deep Convolutional Neural Network


by
Rafiul Hasan Khan

3/28/2019 MCSP 1
 Contents
• Introduction
• Dataset
• Proposed structure
• Simulation
• Result
• Layer inspection
• Proposed method for morphing

3/28/2019 MCSP 2
 Dataset
• Example of Dataset

3/28/2019 MCSP 3
 Proposed Structure

Fig : Structure of the network


3/28/2019 MCSP 4
 Schematic Diagram

3/28/2019 MCSP 5
 Simulation
• The Dataset was divided into two parts of eighty by twenty percent for ‘Training’ and ‘Testing/Validation’.

• Initial Learning rate was set to 0.001

• Number of ‘Epoch’ was set to 20.

• Mini Batch Size was set to 64.

3/28/2019 MCSP 6
 Result

Fig : Classification result of the Dataset


3/28/2019 MCSP 7
 Layer Inspection
• Input Layer

Fig : Scaled Input Image by 227x227 Fig : Data Layer activations


Fig : Unscaled Input Image

3/28/2019 MCSP 8
 Layer Inspection
• First Convolution Layer

Fig : Convolution Process

Fig : Activation of first Convolution Layer (128)


3/28/2019 MCSP 9
 Layer Inspection
• First Convolution Layer

Fig : Strongest activation Channel of First Convolution Layer


3/28/2019 MCSP 10
 Layer Inspection
• First ReLU Layer

Fig : Activation of first ReLU Layer (128)

3/28/2019 MCSP 11
Layer Inspection
• First ReLU Layer

Fig : Strongest activation Channel of First ReLU Layer


3/28/2019 MCSP 12
 Layer Inspection
• First Pooling Layer

Fig : Activation of first Pooling Layer (128)


3/28/2019 MCSP 13
 Layer Inspection
• First Pooling Layer

Fig : Strongest activation Channel of First Pooling Layer


3/28/2019 MCSP 14
 Layer Inspection
• Cross Channel Normalization Layer

Fig : Activation of Cross Channel Normalization Layer (128)


3/28/2019 MCSP 15
 Layer Inspection
• Cross Channel Normalization Layer

Fig : Strongest activation Channel of Cross Channel Normalization Layer


3/28/2019 MCSP 16
 Layer Inspection
• Second Convolution Layer

Fig : Convolution Process

Fig : Activation of Second Convolution Layer (384)


3/28/2019 MCSP 17
 Layer Inspection
• Second Convolution Layer

Fig : Strongest activation Channel of Second Convolution Layer

3/28/2019 MCSP 18
 Layer Inspection

Fig : Unscaled Input Image

Classification Bear Cat Deer ………..


Prediction 4.47e-09 1.0 7.02e-11 …………
Fig : Result of Input Image
3/28/2019 MCSP 19
 Proposed Method for Morphing
• First Convolution Layer

 For the morphing process,


the control points will
collected from the Strongest
activation Channel of First
Convolution Layer. The
channel will go through pre-
process to be eligible for
Control Point Selection
process.

Fig : Strongest activation Channel of First Convolution Layer


3/28/2019 MCSP 20
3/28/2019 MCSP 21

You might also like