Part of the main face recognition program that shows the two main loops

Download 0,51 Mb. Pdf ko'rish
bet	7/9
Sana	31.05.2024
Hajmi	0,51 Mb.
	#258703

1 2 3 4 5 6 7 8 9

Bog'liq
Integration Of Face Recognition Model to a Biometr

Part of the main face recognition program that shows the two main loops.
Results and discussion
Gathered Data
In order to determine the models’ prediction, it is tested by showing it 100 faces for each iteration. The model will judge whether the
faces shown is inside the syst
em or not. The models’ prediction will be recorded manually by the researcher with the help of the
confusion matrix table which are divided mainly into 4 categories which are true positive, false positive, false negative, and true
negative. The recorded data will be shown throughout Tables 1 to 5 and Table 6 will show the average of the four categories
throughout the five iterations.

149 |
P a g e
Table 1.
Confusion Matrix of the model (1
st
Iteration).
Predicted Values
Actual Values
Positive
Negative
Positive
3
25
Negative
0
72

Table 2.
Confusion Matrix of the model (2
nd
Iteration).
Predicted Values
Actual Values
Positive
Negative
Positive
3
20
Negative
0
77

Table 3.
Confusion Matrix of the model (3
rd
Iteration).
Predicted Values
Actual Values
Positive
Negative
Positive
3
28
Negative
0
69

Table 4.
Confusion Matrix of the model (4
th
Iteration).
Predicted Values
Actual Values
Positive
Negative
Positive
3
30
Negative
0
67

Table 5.
Confusion Matrix of the model (5
th
Iteration).
Predicted Values
Actual Values
Positive
Negative
Positive
3
23
Negative
0
74

Download 0,51 Mb.

1 2 3 4 5 6 7 8 9

Download 0,51 Mb.

Pdf ko'rish