A Proposed Authentication Approach Based on Voice and Fuzzy Logic

Abdul-Hassan, Alia K.; Hadi, Iman Hassoon

doi:10.1007/978-981-13-9406-5_60

Cited by 3 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Artificial intelligence [1,2] and deep learning [3,4] techniques have contributed to the establishment of many applications. One of these applications is the so-called deepfake, which is a type of manipulation implemented on the video to replace a person's face with another person's face to create a kind of illusion that the target person is the one who made these movements [5].…”

Section: Introductionmentioning

confidence: 99%

Unmasking Deepfakes by Fusing Rich Features from Two-Stream CNN Model

Hadi

2022

basjs

View full text Add to dashboard Cite

In contrast to the traditional object detection methods, image manipulation detection focuses on tampering artifacts instead of image content, indicating that more depth features must be learned to detect image manipulation. Deepfakes are one of these techniques that have appeared in recent times and need to learn a lot of the richer features to be detected. Deepfakes are a harmful application that affects all segments of society. It is meant to change the person's face and replace it with another person using deep learning techniques. In this paper, we contribute to finding a solution to detect the fakes. A new two-stream CNN model-based deep learning is developed, where two streams are combined, exploiting the fusion layer. Following the fusion layer, the data is classified using the classification layer. The first stream is a semantic stream to extract specific features from the RGB image input to identify manipulation artifacts such as blurring variation, the boundary of the face mask, and lighting difference. The second stream is a texture stream that exploits the texture features extracted from a Gabor bank filters layer. The proposed strategy significantly outperformed the previous methods that were in use. The measured performance metrics have an accuracy of more than 99.5%.

show abstract

Section: Introductionmentioning

confidence: 99%

Unmasking Deepfakes by Fusing Rich Features from Two-Stream CNN Model

Hadi

2022

basjs

View full text Add to dashboard Cite

show abstract

“…ASR comprises two phases (training and testing). In the training phase, known speech is recorded and stored in a speech database as a parametric representation (Badr and Abdul-Hassan, 2020;Abdul-Hassan and Hadi, 2020). In the testing phase, the ASR system compares the retrieved features to trained reference templates to identify the utterance (Gamit and Dhameliya, 2015).…”

Section: Introductionmentioning

confidence: 99%

Driver Drowsiness Detection Using Gray Wolf Optimizer Based on Voice Recognition

Jasim

Hassan

Turner

2022

ARO

View full text Add to dashboard Cite

Globally, drowsiness detection prevents accidents. Blood biochemicals, brain impulses, etc., can measure tiredness. However, due to user discomfort, these approaches are challenging to implement. This article describes a voice-based drowsiness detection system and shows how to detect driver fatigue before it hampers driving. A neural network and Gray Wolf Optimizer are used to classify sleepiness automatically. The recommended approach is evaluated in alert and sleep-deprived states on the driver tiredness detection voice real dataset. The approach used in speech recognition is mel-frequency cepstral coefficients (MFCCs) and linear prediction coefficients (LPCs). The SVM algorithm has the lowest accuracy (71.8%) compared to the typical neural network. GWOANN employs 13-9-7-5 and 30-20-13-7 neurons in hidden layers, where the GWOANN technique had 86.96% and 90.05% accuracy, respectively, whereas the ANN model achieved 82.50% and 85.27% accuracy, respectively.

show abstract

A broad review on non-intrusive active user authentication in biometrics

Thomas¹,

Mathew

2021

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Authentication is the process of keeping the user's personal information as confidential in digital applications. Moreover, the user authentication process in the digital platform is employed to verify the own users by some authentication methods like biometrics, voice recognition, and so on. Traditionally, a one-time login based credential verification method was utilized for user authentication. Recently, several new approaches were proposed to enhance the user authentication framework but those approaches have been found inconsistent during the authentication execution process. Hence, the main motive of this review article is to analyze the advantage and disadvantages of authentication systems such as voice recognition, keystroke, and mouse dynamics. These authentication models are evaluated in a continuous non-user authentication environment and their results have been presented in way of tabular and graphical representation. Also, the common merits and demerits of the discussed authentication systems are broadly explained discussion section. Henceforth, this study will help the researchers to adopt the best suitable method at each stage to build an authentication framework for non-intrusive active authentication.

show abstract

A Proposed Authentication Approach Based on Voice and Fuzzy Logic

Cited by 3 publications

References 6 publications

Unmasking Deepfakes by Fusing Rich Features from Two-Stream CNN Model

Unmasking Deepfakes by Fusing Rich Features from Two-Stream CNN Model

Driver Drowsiness Detection Using Gray Wolf Optimizer Based on Voice Recognition

A broad review on non-intrusive active user authentication in biometrics

Contact Info

Product

Resources

About