Redirigiendo al acceso original de articulo en 23 segundos...
ARTÍCULO
TITULO

Hybrid Siamese Network for Unconstrained Face Verification and Clustering under Limited Resources

Nehal K. Ahmed    
Elsayed E. Hemayed and Magda B. Fayek    

Resumen

In this paper, we propose an unconstrained face verification approach that is dependent on Hybrid Siamese architecture under limited resources. The general face verification trend suggests that larger training datasets and/or complex architectures lead to higher accuracy. The proposed approach tends to achieve high accuracy while using a small dataset and a simple architecture by directly learn face?s similarity/dissimilarity from raw face pixels, which is critical for various applications. The proposed architecture has two branches; the first part of these branches is trained independently, while the other parts shared their parameters. A multi-batch algorithm is utilized for training. The training process takes a few hours on a single GPU. The proposed approach achieves near-human accuracy (98.9%) on the Labeled Faces in the Wild (LFW) benchmark, which is competitive with other techniques that are presented in the literature. It reaches 99.1% on the Arabian faces dataset. Moreover, features learned by the proposed architecture are used in building a face clustering system that is based on an updated version of the Density-Based Spatial Clustering of Applications with Noise (DBSCAN). To handle the cluster quality challenge, a novel post-clustering optimization procedure is proposed. It outperforms popular clustering approaches, like K-Means and spectral by 0.098 and up to 0.344 according to F1-measure.

 Artículos similares

       
 
Mario Aragonés Lozano, Israel Pérez Llopis and Manuel Esteve Domingo    
The number and the diversity in nature of daily cyber-attacks have increased in the last few years, and trends show that both will grow exponentially in the near future. Critical Infrastructures (CI) operators are not excluded from these issues; therefor... ver más

 
Mohammed A. Mohammed, Manel Boujelben and Mohamed Abid    
Recently, the advent of blockchain (BC) has sparked a digital revolution in different fields, such as finance, healthcare, and supply chain. It is used by smart healthcare systems to provide transparency and control for personal medical records. However,... ver más
Revista: Future Internet

 
William Villegas-Ch., Angel Jaramillo-Alcázar and Aracely Mera-Navarrete    
This research was aimed at designing an image recognition system that can help increase children?s interest in learning natural numbers between 0 and 9. The research method used was qualitative descriptive, observing early childhood learning in a face-to... ver más
Revista: Future Internet

 
Ferry Astika Saputra, Muhammad Salman, Jauari Akhmad Nur Hasim, Isbat Uzzin Nadhori and Kalamullah Ramli    
Snort is a well-known, signature-based network intrusion detection system (NIDS). The Snort sensor must be placed within the same physical network, and the defense centers in the typical NIDS architecture offer limited network coverage, especially for re... ver más

 
Geovanny Proaño Parra,Ricardo Tendero Caballero     Pág. 51 - 61
This work tries to analyze how through the Guadua cane, the Academic and Research Unit Eco- materials (UAIE) of the Faculty of Architecture of the Catholic University of Santiago de Guayaquil, as well as the experience in construction with guadua in Ecua... ver más