ISSN: 2502-4752
Indonesian J Elec Eng & Comp Sci, Vol. 21, No. 1, January 2021 : 457 - 464
460
2.2. Images data set building
The process of building 3D faces of a human being using 2D images
within the Blinder virtual
environment (VE) requires several basic conditions that must be met in these images to achieve a high level
of performance and an ideal result. That is conditions and fundamental variables from it ought to be
accessible in Keen Tools Face builder. Which should be high-definition pictures, non- blurring,
with high
sharpness and with dimensions of frame size 1920 x 1080 pixels.
The world is witnessing daily a large increase in the number of digital images with the increase in
digital cameras and the advancement of its technologies rapidly [12], with the widespread use of digital
cameras, many users take poor quality digital photos due to a lack of experience. It is the fundamental
thought in the obtaining of a blurry photo [13]. In addition to the process of capturing 2D images using these
digital devices, varying from the highest blur and less clear to the least blur and
the highest sharpness and
clarity. Which relies on the person's association with cutting edge photography.
Accordingly, Image Data Set was built containing 2D images of the same accuracy, but they differ
in clarity and blurring, according to the following:
a)
Use the free Image data set, from Open Visual FX Blog which contains seven images of the Actor –
Tim Delano at 1920 x 1080 pixel resolution, non- blurring and high sharpness.
b)
By using the ACDSee Photo Studio Ultimate application, four different blur operations ((a) Radial blur
[14], (b) Spread blur [15], (c) Smart blur [16], (d) Gaussian blur [17]), are applied to each of the original
7 images, which were explained before, and thus we have a new images data set consisting of 35
different
images in blurry, sharpness and clarity photos, as shown in Figure 4.
Add a self-assertive number to a dataset of images. It will be promptly tried utilizing OpenCV
applications with the Python language.
Figure 4. Images data set contains original images (sharpness) and different blurry images
