145 |
P a g e
OpenCV
OpenCV is an open-source library focusing on Computer Vision. It was originally developed by Intel Corporation, the
American tech company. Computers are unable to process images like humans, they see objects as a binary, numbers
that shows the color codes, red, green, blue, and a combination of the 3 colors. OpenCV was developed in C and C++
[programming language, but it has now been developed to be used in other programming languages such as MATLAB,
Java, and Python.
Confusion Matrix
The machine learning m
odels’ prediction can be classified into 4 categories which are true positive, true negative, false
positive, and false negative. The true category means that the model has predicted the shown value correctly or
corresponding to the actual value which can be positive, in this case the model detected a face, and negative in which it
did not detect a face. The false category means that the model predicted the shown value wrongly or not corresponding
to the actual value which can be positive which means that the model detected a face when it was not supposed to and
negative, where it did not detect a face when it was supposed to. When we combine the categories to make a table, they
will form a confusion matrix that will be shown in
Figure 3.
Figure 3.
The confusion matrix table [6].
Accuracy, Sensitivity, and Specificity
The data gathered from the experiment will be analyzed with the help of 3 equations shown from Equations 1 to 3 [7].
The accuracy of the model shows the number of correct predictions that the model has made. The sensitivity of the model
or SN refers to the rate of actual positive that is predicted as a positive value by the model, the sensitivity is also known
as the true positive rate. The specificity of the model or SP refers to the rate where the negative value is predicted as a
negative value, the specificity is also known as the true negative rate.
𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦 =
𝑇𝑃 + 𝑇𝑁
𝑇𝑃 + 𝐹𝑃 + 𝐹𝑃 + 𝑇𝑁
(1)
𝑆𝑁 =
𝑇𝑃
𝑇𝑃 + 𝐹𝑁
=
𝑇𝑃
𝑃
(2)
𝑆𝑃 =
𝑇𝑁
𝑇𝑁 + 𝐹𝑃
=
𝑇𝑁
𝑁
(3)
