Interest points reduction using evolutionary algorithms and CBIR for face recognition
- PDF / 3,789,426 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 72 Downloads / 174 Views
ORIGINAL ARTICLE
Interest points reduction using evolutionary algorithms and CBIR for face recognition Juan Villegas-Cortez1 · César Benavides-Alvarez2 · Carlos Avilés-Cruz2 · Graciela Román-Alonso3 · Francisco Fernández de Vega4 · Francisco Chávez4 · Salomón Cordero-Sánchez5
© Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Face recognition has become a fundamental biometric tool that ensures identification of people. Besides a high computational cost, it constitutes an open problem for identifying faces under ideal conditions as well as those under general conditions. Though the advent of high memory and inexpensive computer technologies has made the implementation of face recognition possible in several devices and authentication systems, achieving 100% face recognition in real time is still a challenging task. This paper implements an evolutionary computer genetic algorithm for optimizing the number of interest points on faces, intended to get a quick and precise facial recognition using local analysis texture technique applied to CBIR methodology. Our approach was evaluated using different databases, getting an efficient facial recognition of up to 100% considering only seven interest points from a total of 54 cited in the literature. The interest points reduction was possible through a parallel implementation of our approach using a 54-processor cluster that executes the similar task up to 300% more faster. Keywords Multi-objective · Face recognition · Parallel algorithms · CBIR · Genetic algorithm
1 Introduction Over the last few years, the study of the geometry and the descriptive features of the human face, as we perceive it,
B
Juan Villegas-Cortez [email protected] César Benavides-Alvarez [email protected]
1
Departamento de Sistemas, Universidad Autónoma Metropolitana, Azcapotzalco, Av. San Pablo Xalpa No.180, Col Reynosa Tamaulipas, CP 02200 Ciudad de México, México
2
Departamento de Electrónica, Universidad Autónoma Metropolitana, Azcapotzalco, Av. San Pablo Xalpa No.180, Col Reynosa Tamaulipas, CP 02200 Ciudad de México, México
3
Departamento de Ing. Eléctrica, Universidad Autónoma Metropolitana, Iztapalapa, San Rafael Atlixco 186, Vicentina, CP 09340 Ciudad de México, México
4
Department of Computer Science, University of Extremadura, C/. Santa Teresa de Jornet, 38, CP: 06800 Mérida, Spain
5
Departamento de Química, Universidad Autónoma Metropolitana, Iztapalapa, San Rafael Atlixco 186, Vicentina, CP 09340 Ciudad de México, México
along with the automatic identification process have been the subject of several research projects. Partly, this is due to the increase in computer efficiency both in speed and parallelization of the execution process, as well as the cost reduction.1 However, this type of study is not easy to carry out due to the great number of floating point operations involved. Authors of [5] and [16] sought to minimize the number of operations and steps of the corresponding algorithm; however, this minimization process poses a challenging problem to
Data Loading...