Figure 1.
Data flow chart of the system
TABLE I.
OVERALL STRUCTURE OF THE INCEPTION V3 NETWORK MODEL
| Type | Size of Convolution Kernel/Step Size |
|---|---|
| convolution | 3×3/2 |
| convolution | 3×3/1 |
| convolution | 3×3/1 |
| pooling | 3×3/2 |
| convolution | 3×3/1 |
| convolution | 3×3/2 |
| convolution | 3×3/1 |
| Inception modules | 3 Inception Module |
| Inception modules | 3 Inception Module |
| Inception modules | 3 Inception Module |
| pooling | 8×8 |
| linear | logits |
| Softmax | Classification of output |
TABLE II.
IMPLEMENTATION OF THE MOBILENET V2 CORE BUILDING MODULE
| Input | Operator | Output |
|---|---|---|
| H×W×N | 1×1 conv2d, ReLU6 | H×W×t N |
| H×W×t N | 3×3 dwise s=s, ReLU6 | H/s ×W/s×t N |
| H s ×W s ×t N | linear 1×1 conv2d | H/s ×W/s ×t N |
TABLE III.
OVERALL ARCHITECTURE OF MOBILENET V2
| Input | Operator | t | c | n | s |
|---|---|---|---|---|---|
| 224×224×3 | Conv2d | - | 32 | 1 | 2 |
| 112×112×32 | Bottleneck | 1 | 16 | 1 | 1 |
| 112×112×16 | Bottleneck | 6 | 24 | 2 | 2 |
| 56×56×24 | Bottleneck | 6 | 32 | 3 | 2 |
| 28×28×32 | Bottleneck | 6 | 64 | 4 | 2 |
| 14×14×64 | Bottleneck | 6 | 96 | 3 | 1 |
| 14×14×96 | Bottleneck | 6 | 160 | 3 | 2 |
| 7×7×160 | Bottleneck | 6 | 320 | 1 | 1 |
| 7×7×320 | Conv2d 1×1 | - | 1280 | 1 | 1 |
| 7×7×1280 | Avg pool 7×7 | - | 1 | - | |
| 7×7×1280 | Conv2d 1×1 | - | 1000 | - |
Figure 2.
Treatment diagram of the sample rotated by 30° around the eye
Figure 3.
Treatment diagram of the sample rotated by 60°around the eye
Figure 4.
Treatment diagram of the sample rotated by 90°around the eye
Figure 5.
Treatment diagram of the sample rotated by 120°around the eye
Figure 6.
Treatment diagram of the sample rotated by 150°around the eye
Figure 7.
Treatment diagram of the sample rotated by 180°around the eye
TABLE IV.
SAMPLE EYE PERIPHERAL DATASET
| Eye Peripheral Data Set | Original Training Set | Raw Verification Set | Raw Test Set | Total Original Sample | Original Sample Type |
|---|---|---|---|---|---|
| CASIA-Iris-Thousand | 6000 | 2000 | 2000 | 10000 | 1000 |
Figure 8.
Diagram of 000L partial eye sample
TABLE V.
AMPLIFIED SAMPLES OF THE DATA SET AROUND THE EYE
| Eye Peripheral Data Set | Training Set | Verification Set | Test Set | Total sample | Sample Type |
|---|---|---|---|---|---|
| CASIA-Iris-Thousand | 42000 | 14000 | 14000 | 70000 | 1000 |
TABLE VI.
PARAMETER SETTINGS
| Parameter Types | Parameter Settings |
|---|---|
| Max number of steps | 20000 |
| Batch size | 24 |
| Learning rate | 0. 001 |
| Learning rate decay type | fixed |
| optimizer | RMSProp |
| Weight decay | 0. 00004 |
Figure 9.
Loss function diagram of InceptionV3 network model
TABLE VII.
NETWORK MODEL PARAMETER SETTING
| Parameter Types | Parameter Settings |
|---|---|
| Max number of steps | 100000 |
| Batch size | 32 |
| Learning rate | 0. 001 |
| Learning rate decay type | Fixed |
| optimizer | RMSProp |
| Weight decay | 0. 00004 |
Figure 10.
Change diagram of loss function of the MobileNet V2 lightweight network model
TABLE VIII.
COMPARISON OF INCPETION V3 AND MOBILENET V2 METHODS
| Methods | Verification Accuracy | Test Accuracy | Model Size |
|---|---|---|---|
| IncpetionV3 | 98. 55% | 98. 5% | 93MB |
| MobileNetV2 | 98. 21% | 98. 4% | 24MB |
Figure 11.
302R test sample diagram
Figure 12.
Specular interference around the eye sample