Dynamic Feature Matching for Partial Face Recognition

He, Lingxiao; Li, Haiqing; Zhang, Qi; Sun, Zhenan

doi:10.1109/tip.2018.2870946

Cited by 67 publications

(26 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the publication of AlexNet architecture in 2012 by krizhevsky et al [14], deep CNN have become a common approach in face recognition. It has also been successfully used in face recognition under occlusion variation [15]. We nd deep learning based method based on the fact that human visual system automatically ignores the occluded regions and only focuses on the non-occluded ones.…”

Section: Related Workmentioning

confidence: 99%

Efficient Masked Face Recognition Method during the COVID-19 Pandemic

Hariri

2020

Preprint

View full text Add to dashboard Cite

The COVID-19 is an unparalleled crisis leading to huge number of casualties and security problems. In order to reduce the spread of coronavirus, people often wear masks to protect themselves. This makes the face recognition a very difficult task since certain parts of the face are hidden. A primary focus of researchers during the ongoing coronavirus pandemic is to come up with suggestions to handle this problem through rapid and efficient solutions. In this paper, we propose a reliable method based on discard masked region and deep learning based features in order to address the problem of masked face recognition process. The first step is to discard the masked face region. Next, we apply a pre-trained deep Convolutional neural networks (CNN) to extract the best features from the obtained regions (mostly eyes and forehead regions). Finally, the Bag-of-features paradigm is applied on the feature maps of the last convolutional layer in order to quantize them and to get a slight representation comparing to the fully connected layer of classical CNN. Finally, Multilayer Perceptron (MLP) is applied for the classification process. Experimental results on Real-World-Masked-Face-Dataset show high recognition performance.

show abstract

Section: Related Workmentioning

confidence: 99%

Efficient Masked Face Recognition Method during the COVID-19 Pandemic

Hariri

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Since the publication of AlexNet architecture in 2012 by krizhevsky et al [10], deep CNN have become a common approach in face recognition. It has also been successfully used in face recognition under occlusion variation [7]. We nd deep learning based method based on the fact that human visual system automatically ignores the occluded regions and only focuses on the non-occluded ones.…”

Section: Related Workmentioning

confidence: 99%

Efficient Masked Face Recognition Method during the COVID-19 Pandemic

Hariri

2020

Preprint

View full text Add to dashboard Cite

Abstract The COVID-19 is an unparalleled crisis leading to huge number of casualties and security problems. In order to reduce the spread of coronavirus, people often wear masks to protect themselves. This makes the face recognition a very difficult task since certain parts of the face are hidden. A primary focus of researchers during the ongoing coronavirus pandemic is to come up with suggestions to handle this problem through rapid and efficient solutions. In this paper, we propose a reliable method based on discard masked region and deep learning based features in order to address the problem of masked face recognition process. The first step is to discard the masked face region. Next, we apply a pre-trained deep Convolutional neural networks (CNN) to extract the best features from the obtained regions (mostly eyes and forehead regions). Finally, the Bag-of-features paradigm is applied on the feature maps of the last convolutional layer in order to quantize them and to get a slight representation comparing to the fully connected layer of classical CNN. Finally, MLP is applied for the classification process. Experimental results on Real-World-Masked-Face-Dataset show high recognition performance.

show abstract

“…In the proposed approach, the HMM model is used as it is much simpler than the LSTM. The proposed model relies on the assumption that the state transitions depend mainly on calculating all possible frame sequences and the maximum likelihood frame is selected based on the previous or current frame, as presented in equations (7) and (8). So like always, these assumptions are valid.…”

Section: Comparative Modelsmentioning

confidence: 99%

“…mobiles, tablets, etc.). So the SURF, HoG and Haar techniques have been chosen based on their remarkable efficacy and reported accuracy in image recognition as shown in [8], [9] and [10]. The Hidden Markov Model (HMM) is used on the proposed silent lip recognition framework instead of deep learning LSTM because deep learning requires large amount of data while the Arabic dataset used in the silent lip recognition is limited.…”

Section: Introductionmentioning

confidence: 99%

A Silent Password Recognition Framework Based on Lip Analysis

2020

View full text Add to dashboard Cite

Securing passwords either written or spoken is considered one of the challenging authentication issues faced by individuals and organizations. Written passwords could be easily stolen by look over, or manbehind, while spoken passwords could be recorded and replayed by attackers. A proposed silent password which is based on a dual security model for lip movement analysis will be a promoting solution to these attacks. The goal of the current research is to propose a hybrid voting framework for silent passwords recognition using lip movement analysis. The proposed framework is built for Arabic language by extracting figures from predefined Arabic lexicon. The predefined lexicon mainly contains the Arabic figures from zero to nine with different shapes. The framework takes a video or sequence of images as an input, and outputs the corresponding silent password for the frames extracted from the input video. In this paper, three techniques will be employed to extract effective visual features from mouth-lip movement. Such techniques are SURF, HoG and Haar feature extractor. The resultant features in each technique are fed separately into a classification model, namely, the hidden Markov model (HMM). The HMM identifies corresponding Arabic figure from a predefined lexicon based on input features. The final classification models that are produced from the three techniques have been grouped in a voting scheme to produce the final classification result. The proposed model will be tested on handcrafted data set of lip movement, and it has shown a promising result with improved accuracy of Arabic figures recognition. INDEX TERMS Hidden Markov model, lip analysis, silent password, voting scheme.

show abstract

Dynamic Feature Matching for Partial Face Recognition

Cited by 67 publications

References 42 publications

Efficient Masked Face Recognition Method during the COVID-19 Pandemic

Efficient Masked Face Recognition Method during the COVID-19 Pandemic

Efficient Masked Face Recognition Method during the COVID-19 Pandemic

A Silent Password Recognition Framework Based on Lip Analysis

Contact Info

Product

Resources

About