THE 3 rd INTERNATIONAL SCIENTIFIC CONFERENCES OF STUDENTS AND YOUNG RESEARCHERS dedicated to the 99
th
anniversary of the National Leader of Azerbaijan Heydar Aliyev
181
3. AdaBoost training
In order to classify the image a classifier is created with the help of
AdaBoost. A classifier is formed by a small number of features from a large
set of classifier using AdaBoost. Unlike other methods, AdaBoost algorithm
gives desired region of the object discarding unnecessary background.
4. Cascading classifiers
By using a cascade of stages Viola-Jones algorithm eliminates face
canditates quickly. Elimination happens if the canditate fails to pass the strict
requirements of that stage. In each stage difficulty increases and if the
canditate passes all the stages a face is detected.
Figure 2. Cascades using for face detection.
In this work, implementation of Viola-Jones face recognition algorithm
has been explored in a Raspberry Pi 4 Model B board.It is a single board
minicomputer with a 1.5 GHz 64-bit quad core ARM Cortex-A72 processor.It
runs on Linux and requires microSD card to load its operating system since
it does not have any built-in storage.To get the images from a real-time video
Pi camera Module 2 is used.Other hardware used in this project includes a
microSD card with 32GB of storage. For the coding Phyton programming
language is used.
References: [1] P. Viola and M. Jones, "Rapid object detection using a boosted cascade of simple features,"
Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and
Pattern Recognition. CVPR 2001, 2001, pp. I-I, doi: 10.1109/CVPR.2001.990517.
[2] Cen, Kaiqi. “Study of Viola-Jones Real Time Face Detector.” (2016).
[3] A. Srivastava, S. Mane, A. Shah, N. Shrivastava and B. Thakare, "A survey of face
detection algorithms," 2017 International Conference on Inventive Systems and Control
(ICISC), 2017, pp. 1-4, doi: 10.1109/ICISC.2017.8068607.