Kinship verification from face images in discriminative subspaces of color components

被引:13
作者
Laiadi, Oualid [1 ,5 ]
Ouamane, Abdelmalik [2 ]
Boutellaa, Elhocine [3 ]
Benakcha, Abdelhamid [4 ]
Taleb-Ahmed, Abdelmalik [5 ]
Hadid, Abdenour [3 ]
机构
[1] Univ Biskra, Lab LESIA, Biskra, Algeria
[2] Univ Biskra, Biskra, Algeria
[3] Univ Oulu, Ctr Machine Vis & Signal Anal, Oulu, Finland
[4] Univ Biskra, Lab LGEB, Biskra, Algeria
[5] Polytech Univ Hauts De France, IEMN DOAE UMR CNRS 8520 Lab, Famars, France
关键词
Kinship verification; Face images; Two-step learning; Gray-scale; Color spaces; Chrominance and luminance; KIN RECOGNITION SIGNALS;
D O I
10.1007/s11042-018-7027-9
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Automatic facial kinship verification is a challenging topic in computer vision due to its complexity and its important role in many applications such as finding missing children and forensics. This paper presents a Facial Kinship Verification (FKV) approach based on an automatic and more efficient two-step learning into color/texture information. Most of the proposed methods in automatic kinship verification from face images consider the luminance information only (i.e. gray-scale) and exclude the chrominance information (i.e. color) that can be helpful, as an additional cue, for predicting relationships. We explore the joint use of color-texture information from the chrominance and the luminance channels by extracting complementary low-level features from different color spaces. More specifically, the features are extracted from each color channel of the face image and fused to achieve better discrimination. We investigate different descriptors on the existing face kinship databases, illustrating the usefulness of color information, compared with the gray-scale counterparts, in seven various color spaces. Especially, we generate from each color space three subspaces projection matrices and then score fusion methodology to fuse three distances belonging to each test pair face images. Experiments on three benchmark databases, namely the Cornell KinFace, the KinFaceW (I & II) and the TSKinFace database, show superior results compared to the state of the art.
引用
收藏
页码:16465 / 16487
页数:23
相关论文
共 50 条
[31]   Kinship Verification Using Facial Images by Robust Similarity Learning [J].
Xu, Min ;
Shang, Yuanyuan .
MATHEMATICAL PROBLEMS IN ENGINEERING, 2016, 2016
[32]   Kinship verification in childhood images using curvelet transformed features [J].
Oruganti, Madhu ;
Meenpal, T. ;
Majumder, Saikat .
COMPUTERS & ELECTRICAL ENGINEERING, 2024, 118
[33]   A pyramid multi-level face descriptor: application to kinship verification [J].
Moujahid, A. ;
Dornaika, F. .
MULTIMEDIA TOOLS AND APPLICATIONS, 2019, 78 (07) :9335-9354
[34]   A pyramid multi-level face descriptor: application to kinship verification [J].
A. Moujahid ;
F. Dornaika .
Multimedia Tools and Applications, 2019, 78 :9335-9354
[35]   Enhanced kinship verification analysis based on color and texture handcrafted techniques [J].
Nader, Nermeen ;
EL-Gamal, Fatma EL-Zahraa A. ;
Elmogy, Mohammed .
VISUAL COMPUTER, 2024, 40 (04) :2325-2346
[36]   Enhanced kinship verification analysis based on color and texture handcrafted techniques [J].
Nermeen Nader ;
Fatma EL-Zahraa A. EL-Gamal ;
Mohammed Elmogy .
The Visual Computer, 2024, 40 :2325-2346
[37]   Kinship verification using multi-level dictionary pair learning for multiple resolution images [J].
Goyal, Aarti ;
Meenpal, Toshanlal .
PATTERN RECOGNITION, 2023, 143
[38]   Automated kinship verification and identification through human facial images: a survey [J].
Almuashi, Mohammed ;
Hashim, Siti Zaiton Mohd ;
Mohamad, Dzulkifli ;
Alkawaz, Mohammed Hazim ;
Ali, Aida .
MULTIMEDIA TOOLS AND APPLICATIONS, 2017, 76 (01) :265-307
[39]   Automated kinship verification and identification through human facial images: a survey [J].
Mohammed Almuashi ;
Siti Zaiton Mohd Hashim ;
Dzulkifli Mohamad ;
Mohammed Hazim Alkawaz ;
Aida Ali .
Multimedia Tools and Applications, 2017, 76 :265-307
[40]   A review on kinship verification from facial information [J].
Mzoughi, Mohamed Charfeddine ;
Ben Aoun, Najib ;
Naouali, Sami .
VISUAL COMPUTER, 2025, 41 (03) :1789-1809