A Silent Password Recognition Framework Based on Lip Analysis

Abstract

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.

Deep Learning-Based Approach for Arabic Visual Speech Recognition

“…The features are passed individually into HMM to recognize the corresponding digit. The SURF, HoG, and Haar techniques are also applied for feature extraction in [10] to build the Silent password recognition framework. The model has five layers to provide Arabic digit prediction for the password matching process, and then each feature separately is fed into the HMM.…”

Lip Movement Recognition using Histogram of Oriented Gradient (HOG) and Support Machine Vector (SVM) for Arabic Word

“…In addition, this technique is used for various purposes such as improving speech recognition where there is a lot of noise [3], security systems [4], forensic investigations [5], and others. Petar S. Aleksic describes the exploration of changes in visual features extracted from the mouth region to obtain visual feature information that can improve the performance of speech recognition systems and be more resistant to forgery attempts [6].…”

Comparing Speaker Adaptation Methods for Visual Speech Recognition for Continuous Spanish

“…This challenging task, known as Visual Speech Recognition (VSR), has been a focus of interest during the last few decades [12]. Moreover, recognising speech without the need for acoustic stream data offers a wide range of applications, such as silent speech passwords [13], visual keyword spotting [14], or the development of silent speech interfaces that would be able to improve the lives of people who experience difficulties in producing speech [15][16][17].…”