Title | ||
---|---|---|
Deep Convolutional Neural Network Using Triplet Loss To Distinguish The Identical Twins |
Abstract | ||
---|---|---|
In face recognition, distinguishing identical twins faces is a challenging task because of the high level of correlation in facial appearance.Generally, facial recognition is easy to make mistakes when it comes to twins or similar faces. To deal with the high level of correlation in similar faces, we proposed a deep convolutional neural network (CNN) using triplet loss function to differentiate the identical twins. We applied a hybrid strategy by combining the deep CNN model, which learns an embedding from facial images to Euclidean space and triplet loss function to evaluate the 12 distance between facial images into Euclidean space, Obtained L2 distance shows the level of similarity between corresponding faces. We implemented two different CNN models on our raw pixel images; additionally, we used different techniques to reduce the overfilling problem such as dropout and batch normalization, additionally 12 regularization. Our method achieves the best mean validation accuracy above 87.2%. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/GCWkshps45667.2019.9024704 | 2019 IEEE GLOBECOM WORKSHOPS (GC WKSHPS) |
Keywords | DocType | ISSN |
Triplet loss function, Convolutional neural network (CNN), Euclidean space, L2 distance, Face recognition | Conference | 2166-0069 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Belal Ahmad | 1 | 5 | 2.60 |
Mohd Usama | 2 | 17 | 3.22 |
Jiayi Lu | 3 | 12 | 2.32 |
Wenjing Xiao | 4 | 0 | 0.34 |
Jiafu Wan | 5 | 1866 | 100.02 |
Jun Yang | 6 | 0 | 0.34 |