|
Title:
|
FACIAL RECOGNITION, AUTONOMOUS LEARNING,
BASED ON IMAGE FRAGMENTATION |
|
Author(s):
|
Danilo Daniel González Guacte and Diego Alberto Aracena Pizarro |
|
ISBN:
|
978-989-8533-91-3 |
|
Editors:
|
Katherine Blashki and Yingcai Xiao |
|
Year:
|
2019 |
|
Edition:
|
Single |
|
Keywords:
|
Facial Recognition, Image Fragmentation, HOG, SVM, Region of Interest, Hyperplanes |
|
Type:
|
Full Paper |
|
First Page:
|
299 |
|
Last Page:
|
306 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
This paper uses variations in the image fragmentation approach, considering the number of fragments, number of samples
per person, number of hyperplanes and size in the region of interest. Computational vision techniques, in particular
gradient histogram (HOG) as feature space descriptor, automatic learning methods, such as vector support machines
(SVM) for model construction and a face detection algorithm, are used to replicate these experiments in a real time
context. Tests are performed on a population of 40 people, samples taken in uncontrolled situations, in this way some
states are discarded, refining the parameters until arriving at a configuration that complies with delivering the best results
in this experiment and under these conditions. |
|
|
|
|
|
|
