Skip to Main content Skip to Navigation
Conference papers

Kinship Verification based Deep and Tensor Features through Extreme Learning Machine

Oualid Laiadi 1, 2 Abdelmalik Ouamane Abdelhamid Benakcha Abdelmalik Taleb-Ahmed 1, 2 Abdenour Hadid 1, 2 
1 COMNUM - IEMN - COMmunications NUMériques - IEMN
IEMN-DOAE - Institut d’Électronique, de Microélectronique et de Nanotechnologie - Département Opto-Acousto-Électronique - UMR 8520
Abstract : Checking the kinship of facial images is a difficult research topic in computer vision that has attracted attention in recent years. The methods suggested so far are not strong enough to predict kinship relationships only by facial appearance. To mitigate this problem, we propose a new approach called Deep-Tensor+ELM to kinship verification based on deep (VGG-Face descriptor) and tensor (BSIF-Tensor & LPQ-Tensor using MSIDA method) features through Extreme Learning Machine (ELM). While ELM aims to deal with small size training features dimension, deep and tensor features are proven to provide significant enhancement over shallow features or vector-based counterparts. We evaluate our proposed method on the largest kinship benchmark namely FIW database using four Grandparent-Grandchild relations (GF-GD, GF-GS, GM-GD and GM-GS). The results obtained are positively compared with some modern methods, including those that rely on deep learning.
Complete list of metadata

https://hal-uphf.archives-ouvertes.fr/hal-03572289
Contributor : Kathleen TORCK Connect in order to contact the contributor
Submitted on : Monday, February 14, 2022 - 11:08:38 AM
Last modification on : Wednesday, May 4, 2022 - 11:44:02 AM

Links full text

Identifiers

Citation

Oualid Laiadi, Abdelmalik Ouamane, Abdelhamid Benakcha, Abdelmalik Taleb-Ahmed, Abdenour Hadid. Kinship Verification based Deep and Tensor Features through Extreme Learning Machine. 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), May 2019, Lille, France. pp.735-738, ⟨10.1109/FG.2019.8756627⟩. ⟨hal-03572289⟩

Share

Metrics

Record views

16