• Publications
  • Influence
A Robust Real-Time Automatic License Plate Recognition Based on the YOLO Detector
TLDR
This paper presents a robust and efficient ALPR system based on the state-of-the-art YOLO object detector. Expand
  • 124
  • 13
  • PDF
An Efficient and Layout-Independent Automatic License Plate Recognition System Based on the YOLO detector
TLDR
We present an efficient and layout-independent Automatic License Plate Recognition (ALPR) system based on the state-of-the-art YOLO object detector that contains a unified approach for license plate (LP) detection and layout classification to improve the recognition results using post-processing rules. Expand
  • 22
  • 5
  • PDF
Real-Time Automatic License Plate Recognition through Deep Multi-Task Networks
TLDR
We propose a technique that is able to perform ALPR using only two deep networks, the first performs license plate detection (LPD) and the second performs License plate recognition (LPR). Expand
  • 15
  • 1
Multi-task Learning for Low-Resolution License Plate Recognition
TLDR
We use a multi-task network to perform the last two steps of the pipeline known as segmentation and recognition of the characters. Expand
  • 5
  • 1
A Benchmark for Iris Location and a Deep Learning Detector Evaluation
TLDR
The iris is considered as the biometric trait with the highest unique probability. Expand
  • 21
  • 1
  • PDF
Fully Convolutional Networks and Generative Adversarial Networks Applied to Sclera Segmentation
TLDR
In this work, we proposed two new approaches to sclera segmentation based on Fully Convolutional Network (FCN) and Generative Adversarial Network (GAN) are introduced in this work. Expand
  • 17
  • 1
  • PDF
Convolutional neural networks for automatic meter reading
TLDR
We tackle automatic meter reading (AMR) by leveraging the high capability of convolutional neural networks (CNNs). Expand
  • 17
  • 1
  • PDF
The Impact of Preprocessing on Deep Representations for Iris Recognition on Unconstrained Environments
TLDR
We propose the use of deep representations, more specifically, architectures based on VGG and ResNet-50 networks, for dealing with the images using (and not) iris segmentation and normalization. Expand
  • 11
  • 1
  • PDF
Vehicle Re-identification: exploring feature fusion using multi-stream convolutional networks
TLDR
We propose a novel two-stream convolutional neural network (CNN) that simultaneously uses two of the most distinctive and persistent features available: the vehicle appearance and its license plate. Expand
  • 3
  • 1
  • PDF
Robust Iris Segmentation Based on Fully Convolutional Networks and Generative Adversarial Networks
TLDR
The iris can be considered as one of the most important biometric traits due to its high degree of uniqueness. Expand
  • 13
  • PDF