Have a personal or library account? Click to login

Convolution Neural Network for Face Similarity Estimation

Journal of Automation, Mobile Robotics and Intelligent Systems
Volume 19 (2025): Issue 1 (March 2025)
By:
Open Access
|Mar 2025

Figures & Tables

Figure 1.

Example faces from the ORL database [10]
Example faces from the ORL database [10]

Figure 2.

Two images concatenated horizontally
Two images concatenated horizontally

Figure 3.

Two images concatenated vertically
Two images concatenated vertically

Figure 4.

Two images intertwined by row
Two images intertwined by row

Figure 5.

Two images intertwined by column
Two images intertwined by column

Figure 6.

Face similarity convolution network architecture
Face similarity convolution network architecture

Figure 7.

Accuracy and loss during training for horizontally concatenated pictures
Accuracy and loss during training for horizontally concatenated pictures

Figure 8.

Validation accuracy and loss for horizontally concatenated pictures
Validation accuracy and loss for horizontally concatenated pictures

Figure 9.

Precision and recall for horizontally concatenated pictures
Precision and recall for horizontally concatenated pictures

Figure 10.

Confusion matrices for model trained on horizontally concatenated images
Confusion matrices for model trained on horizontally concatenated images

Figure 11.

Accuracy and loss during training for horizontally concatenated pictures
Accuracy and loss during training for horizontally concatenated pictures

Figure 12.

Validation accuracy and loss for horizontally concatenated pictures
Validation accuracy and loss for horizontally concatenated pictures

Figure 13.

Precision and recall for horizontally concatenated pictures
Precision and recall for horizontally concatenated pictures

Figure 14.

Confusion matrices for model trained on vertically concatenated images
Confusion matrices for model trained on vertically concatenated images

Figure 15.

Accuracy and loss during training for pictures intertwined by row
Accuracy and loss during training for pictures intertwined by row

Figure 16.

Validation accuracy and loss for pictures intertwined by row
Validation accuracy and loss for pictures intertwined by row

Figure 17.

Precision and recall for pictures intertwined by row
Precision and recall for pictures intertwined by row

Figure 18.

Confusion matrices for model trained on row intertwined images
Confusion matrices for model trained on row intertwined images

Figure 19.

Accuracy and loss during training for pictures intertwined by column
Accuracy and loss during training for pictures intertwined by column

Figure 20.

Validation accuracy and loss for pictures intertwined by column
Validation accuracy and loss for pictures intertwined by column

Figure 21.

Precision and recall for pictures intertwined by column
Precision and recall for pictures intertwined by column

Figure 22.

Confusion matrices for model trained on column intertwined images
Confusion matrices for model trained on column intertwined images
DOI: https://doi.org/10.14313/jamris-2025-007 | Journal eISSN: 2080-2145 | Journal ISSN: 1897-8649
Journal RSS Feed
Language: English
Page range: 65 - 72
Submitted on: Sep 4, 2024
Accepted on: Oct 5, 2024
Published on: Mar 31, 2025
Published by: Łukasiewicz Research Network – Industrial Research Institute for Automation and Measurements PIAP
In partnership with: Paradigm Publishing Services
Publication frequency: 4 times per year
Keywords:
CNN,
face identification,
input shaping
Related subjects:
Computer sciences,
Artificial intelligence,
Engineering,
Electrical engineering,
Control engineering, metrology and testing,
Mechanical engineering,
Fundamentals of mechanical engineering

© 2025 Wojciech Domski, Adam Jankowiak, published by Łukasiewicz Research Network – Industrial Research Institute for Automation and Measurements PIAP
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Previous articleVolume 19 (2025): Issue 1 (March 2025)Next article