Azizah Abdul Manaf
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Azizah Abdul Manaf has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Mazdak Zamani
Department of Computer Science, New York University, 251 Mercer, New York, NY 10012, USA
3 shared publications - Adamu I. Abubakar
International Islamic University Malaysia
2 shared publications - Ala Abdulsalam Alarood
College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia
2 shared publications - Izzat Alsmadi
Texas A&M University San Antonio, San Antonio, TX, USA
2 shared publications - Mohammed Salem Atoum
Computer Science Department, King Abdullah II Faculty of Information Technology, The University of Jordan, Amman, Jordan
2 shared publications - Fatemeh Mirzaei Asl
Department of Computer Engineering, Khorramabad Branch, Islamic Azad University, Khorramabad 6817816645, Iran
1 shared publication
Latest Publications
- Open Access
- 15 October 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (15) , 1-23
Enhanced obstacle detection using bilateral vision-aided transformer neural network for visually impaired persons
Obstacle detection remains vital in autonomous navigation and assistive technologies, especially for visually impaired individuals. This work introduces an enhanced obstacle detection framework based on a Bilateral Vision Transformer and Convolution Kernel Neural Network (BViT-CKNN). The system incorporates stereo vision data and applies a bilateral filter to reduce noise while preserving edge details. A Vision Transformer (ViT) model is then used for global feature extraction, and a Convolution Kernel Neural Network (CKNN) captures fine-grained local features. Evaluated using the COCO dataset, the proposed BViT-CKNN achieves superior performance in precision (0.93), recall (0.91), F1-score (0.92), and Mean Absolute Error (MAE) reduction (3.16%) compared to existing methods.
- 15 October 2025
- Published by Springer Nature in Cluster Computing
- Vol. 28 (15) , 1-23
Open AccessEnhanced obstacle detection using bilateral vision-aided transformer neural network for visually impaired persons
Obstacle detection remains vital in autonomous navigation and assistive technologies, especially for visually impaired individuals. This work introduces an enhanced obstacle detection framework based on a Bilateral Vision Transformer and Convolution Kernel Neural Network (BViT-CKNN). The system incorporates stereo vision data and applies a bilateral filter to reduce noise while preserving edge details. A Vision Transformer (ViT) model is then used for global feature extraction, and a Convolution Kernel Neural Network (CKNN) captures fine-grained local features. Evaluated using the COCO dataset, the proposed BViT-CKNN achieves superior performance in precision (0.93), recall (0.91), F1-score (0.92), and Mean Absolute Error (MAE) reduction (3.16%) compared to existing methods.
- Open Access
- 12 June 2025
- Published by Springer Nature in Research Square
Enhanced Obstacle Detection Using Bilateral Vision-Aided Transformer Neural Network for Visually Impaired Persons
Obstacle detection remains vital in autonomous navigation and assistive technologies, especially for visually impaired individuals. This work introduces an enhanced obstacle detection framework based on a Bilateral Vision Transformer and Convolution Kernel Neural Network (BViT-CKNN). The system incorporates stereo vision data and applies a bilateral filter to reduce noise while preserving edge details. A Vision Transformer (ViT) model is then used for global feature extraction, and a Convolution Kernel Neural Network (CKNN) captures fine-grained local features. Evaluated using the COCO dataset, the proposed BViT-CKNN achieves superior performance in precision (0.93), recall (0.91), F1-score (0.92), and Mean Absolute Error (MAE) reduction (3.16%) compared to existing methods.
- 12 June 2025
- Published by Springer Nature in Research Square
Open AccessEnhanced Obstacle Detection Using Bilateral Vision-Aided Transformer Neural Network for Visually Impaired Persons
Obstacle detection remains vital in autonomous navigation and assistive technologies, especially for visually impaired individuals. This work introduces an enhanced obstacle detection framework based on a Bilateral Vision Transformer and Convolution Kernel Neural Network (BViT-CKNN). The system incorporates stereo vision data and applies a bilateral filter to reduce noise while preserving edge details. A Vision Transformer (ViT) model is then used for global feature extraction, and a Convolution Kernel Neural Network (CKNN) captures fine-grained local features. Evaluated using the COCO dataset, the proposed BViT-CKNN achieves superior performance in precision (0.93), recall (0.91), F1-score (0.92), and Mean Absolute Error (MAE) reduction (3.16%) compared to existing methods.
- 1 February 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 49 (9) , 12431-12441
Enhancing IoT-Based Smart Home Security Through a Combination of Deep Learning and Self-Attention Mechanism
- 1 February 2024
- Published by Springer Nature in Arabian Journal for Science and Engineering
- Vol. 49 (9) , 12431-12441
Enhancing IoT-Based Smart Home Security Through a Combination of Deep Learning and Self-Attention Mechanism
- Open Access
- 29 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (19) , 4084
Secure CAPTCHA by Genetic Algorithm (GA) and Multi-Layer Perceptron (MLP)
To achieve an acceptable level of security on the web, the Completely Automatic Public Turing test to tell Computer and Human Apart (CAPTCHA) was introduced as a tool to prevent bots from doing destructive actions such as downloading or signing up. Smartphones have small screens, and, therefore, using the common CAPTCHA methods (e.g., text CAPTCHAs) in these devices raises usability issues. To introduce a reliable, secure, and usable CAPTCHA that is suitable for smartphones, this paper introduces a hand gesture recognition CAPTCHA based on applying genetic algorithm (GA) principles on Multi-Layer Perceptron (MLP). The proposed method improves the performance of MLP-based hand gesture recognition. It has been trained and evaluated on 2201 videos of the IPN Hand dataset, and MSE and RMSE benchmarks report index values of 0.0018 and 0.0424, respectively. A comparison with the related works shows a minimum of 1.79% fewer errors, and experiments produced a sensitivity of 93.42% and accuracy of 92.27–10.25% and 6.65% improvement compared to the MLP implementation. The range of the supported hand gestures can be a limit for the application of this research as a limited range may result in a vulnerable CAPTCHA. Also, the processes of training and testing require significant computational resources. In the future, we will optimize the method to run with high reliability in various illumination conditions and skin color and tone. The next development plan is to use augmented reality and create unpredictable random patterns to enhance the security of the method.
- 29 September 2023
- Published by MDPI AG in Electronics
- Vol. 12 (19) , 4084
Open AccessSecure CAPTCHA by Genetic Algorithm (GA) and Multi-Layer Perceptron (MLP)
To achieve an acceptable level of security on the web, the Completely Automatic Public Turing test to tell Computer and Human Apart (CAPTCHA) was introduced as a tool to prevent bots from doing destructive actions such as downloading or signing up. Smartphones have small screens, and, therefore, using the common CAPTCHA methods (e.g., text CAPTCHAs) in these devices raises usability issues. To introduce a reliable, secure, and usable CAPTCHA that is suitable for smartphones, this paper introduces a hand gesture recognition CAPTCHA based on applying genetic algorithm (GA) principles on Multi-Layer Perceptron (MLP). The proposed method improves the performance of MLP-based hand gesture recognition. It has been trained and evaluated on 2201 videos of the IPN Hand dataset, and MSE and RMSE benchmarks report index values of 0.0018 and 0.0424, respectively. A comparison with the related works shows a minimum of 1.79% fewer errors, and experiments produced a sensitivity of 93.42% and accuracy of 92.27–10.25% and 6.65% improvement compared to the MLP implementation. The range of the supported hand gestures can be a limit for the application of this research as a limited range may result in a vulnerable CAPTCHA. Also, the processes of training and testing require significant computational resources. In the future, we will optimize the method to run with high reliability in various illumination conditions and skin color and tone. The next development plan is to use augmented reality and create unpredictable random patterns to enhance the security of the method.
- Open Access
- 25 August 2022
- Published by MDPI AG in Future Internet
- Vol. 14 (9) , 254
Framework for Video Steganography Using Integer Wavelet Transform and JPEG Compression
In today’s world of computers everyone is communicating their personal information through the web. So, the security of personal information is the main concern from the research point of view. Steganography can be used for the security purpose of personal information. Storing and forwarding of embedded personal information specifically in public places is gaining more attention day by day. In this research work, the Integer Wavelet Transform technique along with JPEG (Joint Photograph Expert Group) compression is proposed to overcome some of the issues associated with steganography techniques. Video cover files and JPEG compression improve concealing capacity because of their intrinsic properties. Integer Wavelet Transform is used to improve the imperceptibility and robustness of the proposed technique. The Imperceptibility of the proposed work is analyzed through evaluation parameters such as PSNR (Peak Signal to Noise Ratio), MSE (Mean Square Error), SSIM (Structure Similarity Metric), and CC (Correlation Coefficient). Robustness is validated through some image processing attacks. Complexity is calculated in terms of concealing and retrieval time along with the amount of secret information hidden.
- 25 August 2022
- Published by MDPI AG in Future Internet
- Vol. 14 (9) , 254
Open AccessFramework for Video Steganography Using Integer Wavelet Transform and JPEG Compression
In today’s world of computers everyone is communicating their personal information through the web. So, the security of personal information is the main concern from the research point of view. Steganography can be used for the security purpose of personal information. Storing and forwarding of embedded personal information specifically in public places is gaining more attention day by day. In this research work, the Integer Wavelet Transform technique along with JPEG (Joint Photograph Expert Group) compression is proposed to overcome some of the issues associated with steganography techniques. Video cover files and JPEG compression improve concealing capacity because of their intrinsic properties. Integer Wavelet Transform is used to improve the imperceptibility and robustness of the proposed technique. The Imperceptibility of the proposed work is analyzed through evaluation parameters such as PSNR (Peak Signal to Noise Ratio), MSE (Mean Square Error), SSIM (Structure Similarity Metric), and CC (Correlation Coefficient). Robustness is validated through some image processing attacks. Complexity is calculated in terms of concealing and retrieval time along with the amount of secret information hidden.