Image Retrieval System based on a Binary Auto-Encoder and a Convolutional Neural Network

Authors

  • Carlos Aviles Cruz UAM-AZC Multimedia Lab.
  • Andrés Ferreyra-Ramírez Universidad Autónoma Metropolitana
  • Eduardo Rodríguez-Martínez Universidad Autónoma Metropolitana
  • Fidel López Saca Universidad Autónoma Metropolitana

Keywords:

binary auto-encoder, hash, Convolutional Neural Networks

Abstract

The amount of image content on the Internet has increased dramatically in recent years; its precise search and retrieval is a challenge at present. The methods that have shown high efficiency are those based on convolution neural networks (CNN) and, particularly, binary coding methods based on hashing functions. This article presents a new image retrieval scheme based on attributes from a CNN, an efficient low-dimensional binary auto-encoder, and, finally, a near-neighbor retrieval stage. The proposed methodology was tested with two image datasets CIFAR-10 and MNIST. The results are compared with existing methods in the literature.

Author Biographies

Andrés Ferreyra-Ramírez, Universidad Autónoma Metropolitana

Profesor Investigador

Departamento de Electrónica de la Universidad Autónoma Metropolitana, Unidad Azcapotzalco, Av. San Pablo 180, Ciudad de México, México

Eduardo Rodríguez-Martínez, Universidad Autónoma Metropolitana

Departamento de Electrónica de la Universidad Autónoma Metropolitana, Unidad Azcapotzalco, Av. San Pablo 180, Ciudad de México, México

Fidel López Saca, Universidad Autónoma Metropolitana

Departamento de Electrónica de la Universidad Autónoma Metropolitana, Unidad Azcapotzalco, Av. San Pablo 180, Ciudad de México, México

Published

2020-10-02
Bookmark and Share