Figure. 1.
The human eye
Figure. 2.
Flowchart of iris recognition
Figure. 3.
Example of two iris images
Figure. 4.
Flow of LMD improvement algorithm
Figure. 5.
Basic flow of Faster R-CNN model
Figure. 6.
U-net network structure
TABLE I.
Comparison of the content of the two datasets
| Training Set | Test Set | Training Set | Test Set | |
|---|---|---|---|---|
| Number of categories | 50 | 8 | 45 | 6 |
| Number of images/classes | 20 | 20 | 10 | 10 |
| Total number of images | 342 | 58 | 342 | 58 |
Figure. 7.
CNN recognition result rate
TABLE II.
Analysis of experimental data
| Test Methods | Training Set | Test Set | Number Of Correct Identifications | Recognition Rate % (Crr) |
|---|---|---|---|---|
| CNN | 400 | 60 | 56 | 92 |
| LMD | 400 | 60 | 47 | 78 |
Figure. 8.
Code Run Diagram
Figure. 9.
Front-end page display
Figure. 10.
Selecting the iris image to be matched against the image in the database
Figure. 11.
Image matching demonstration
Figure. 12.
Interface display
Figure. 13.
Edge extraction to obtain iris
Figure. 14.
Image after normalization and feature extraction
Figure. 15.
Matching successful image