Halidou AMINOU

2026Other

DynaCIS-PIR: Churn-Resilient and Access-Pattern-Private Coverless Image Steganography

Stéphane Gael Raymond Ekodeck, Serge Ebele, Aminou Halidou, Arthur Sandor Voundi Koe, Arthur Ulrich Ewane, Chantal Marguerite Mveh-Abia and 1 more

Zenodo (CERN European Organization for Nuclear Research)

Companion research artifact and manuscript source package for the DynaCIS-PIR paper. The repository contains the source code, experiment scripts, raw results, and manuscript assets used to evaluate churn-resilient and access-pattern-private coverless image steganography. This release includes the identifier-profile PIR bandwidth mitigation, two-VPS benchmark results, updated manuscript sources, and rebuilt PDF variants.

View publication DOI

2026Other

DynaCIS-PIR: Churn-Resilient and Access-Pattern-Private Coverless Image Steganography

Stéphane Gael Raymond Ekodeck, Serge Ebele, Aminou Halidou, Arthur Sandor Voundi Koe, Arthur Ulrich Ewane, Chantal Marguerite Mveh-Abia and 1 more

Open MIND

View publication DOI

2026Journal article

Enhanced OTP and facial recognition for e-learning authentication

Aminou Halidou, Stéphane Gael R. Ekodeck, Daramy Vandi Von Kallon, Christophe Armel Nteme, Jocelyn Edinio Zacko Gbadoubissa

Systems and Soft Computing

Online services, particularly e-learning platforms, face significant challenges in authenticating users due to the absence of physical identification. This vulnerability can lead to security breaches that compromise the credibility of assessments. A robust authentication mechanism is crucial during the evaluation phase to ensure integrity and fairness. A two-phase, multi-factor authentication framework is presented to strengthen security in e-learning environments. The first phase involves user authentication through credential submission and a OTP (One-Time Password) sent by SMS or email, establishing a 2FA (Two-Factor Authentication) process. The second phase employs real-time facial recognition during online examinations, utilizing a feature-based face detection technique with the Haar Cascade classifier and webcam images captured during registration. The experimental results show an authentication accuracy of 80% in well lit conditions and 62% in low light environments, indicating a substantial improvement in security over existing methods. This approach provides a minimally intrusive but effective means of improving the reliability of online assessments. • This work propose a two-phase 3-Factor authentication process to improve access and increase the credibility of online assessment. • It is a real-time facial recognition. • The proposed solution presents less cumbersome for the user and more efficient for online authentication.

View publication DOI

2025Journal articleOpen access

Convolutional Neural Network-Based Xception, MobileNetV2 and InceptionV3 Models for Plant Disease Identification in Sub-Saharan Africa

Aminou Halidou, Youssoufa Mohamadou, Pascalin Tiam Apen, Daramy Vandi Von Kallon, William John Baraza, Mbouna Gildas Patrick and 2 more

International Journal of Computer Applications

Plant disease identification in Sub-Saharan Africa poses a significant challenge, hindered by costly laboratory tests or subjective visual assessments.Recent advances in image-based disease identification show promise, but existing methods are limited in accuracy and efficiency.This study addresses these shortcomings by presenting a convolutional neural network (CNN)-based plant disease classifier, leveraging transfer learning from pre-trained models Xception, MobileNetV2, and InceptionV3.A high generalization rate of 98.76% is achieved in the test data, demonstrating the potential for efficient and accurate identification of plant disease.This research contributes to innovative agricultural management solutions in Sub-Saharan Africa, with implications for improving crop yields, food security, and sustainable agriculture.

View publication DOI

2025Journal articleOpen access

Voter Authentication Using Enhanced ResNet50 for Facial Recognition

Aminou Halidou, Daniel Georges Olle Olle, Arnaud Nguembang Fadja, Daramy Vandi Von Kallon, Tchana Ngninkeu Gil Thibault

Signals

Electoral fraud, particularly multiple voting, undermines the integrity of democratic processes. To address this challenge, this study introduces an innovative facial recognition system that integrates an enhanced 50-layer Residual Network (ResNet50) architecture with Additive Angular Margin Loss (ArcFace) and Multi-Task Cascaded Convolutional Neural Networks (MTCNN) for face detection. Using the Mahalanobis distance, the system verifies voter identities by comparing captured facial images with previously recorded biometric features. Extensive evaluations demonstrate the methodology’s effectiveness, achieving a facial recognition accuracy of 99.85%. This significant improvement over existing baseline methods has the potential to enhance electoral transparency and prevent multiple voting. The findings contribute to developing robust biometric-based electoral systems, thereby promoting democratic trust and accountability.

View publication DOI

2024Preprint

Diagnosis of Plant Diseases Using Mobilenet and Inception Architectures

Aminou Halidou, Daniel Georges Olle Olle, Daramy Vandi Von Kallon, William John Baraza, Obam Akou Yannick Serge, Fokam Ninyim Astride Melvin

SSRN Electronic Journal

View publication DOI

2024Preprint

Enhanced Otp and Facial Recognition for E-Learning Authentication

Aminou Halidou, St ́ephane Gael R. Ekodeck, Daramy Vandi Von Kallon, Christophe Armel Nteme, Jocelyn Gbadouissa

SSRN Electronic Journal

View publication DOI

2023Preprint

People Counting Using Ir-Uwb Radar Sensors with Machine Learning Techniques

Ange Njanda, Jocelyn Gbadouissa, Emanuel Rădoi, Ado Adamou ABBA ARI, Roua Youssef, Aminou Halidou

SSRN Electronic Journal

View publication DOI

2023Journal article

Review of wavelet denoising algorithms

Aminou Halidou, Youssoufa Mohamadou, Ado Adamou Abba Ari, Jocelyn Edinio Zacko Gbadoubissa

Multimedia Tools and Applications

View publication DOI

2017Journal articleOpen access

Robust Steganography based on Matching Pixel Locations

Aminou Halidou, Youssoufa Mohamadou, Georges Delort

International Journal of Computer Applications

Steganography consist of concealing secret information in a cover object to be sent over a public communication channel. It allows two parties to share hidden information in a way that no intruder can detect the presence of hidden information. This paper presents a novel steganography approach based on pixel location matching of the same cover image. Here the information is not directly embedded within the cover image but a sequence of 4 bits of secret data is compared to the 4 most significant bits (4MSB) of the cover image pixels. The locations of the matching pixels are taken to substitute the 2 least significant bits (2LSB) of the cover image pixels. Since the data are not directly hidden in cover image, the proposed approach is more secure and difficult to break. Intruders cannot intercept it by using common LSB techniques.

View publication DOI

2014Journal articleOpen access

Pedestrian Detection Based on Multi-Block Local Binary Pattern and Biologically Inspired Feature

Aminou Halidou, Xinge You, Bachirou Bogno

Computer and Information Science

Nowadays pedestrian detection plays an important role in security and driving assistance. Detecting moving object is complex, and some of the detection methods are comparatively ineffective and slow. In relation to human detection it is very useful to combine independent information sources, such as appearance and motion. To achieve acceptable detection performance, we propose inter-frames differencing image to compute the region of interest, and MB-BIF to extract features. The MB-BIF approach combines two well-known methods, the Multi-Block Local Binary Pattern and Biologically Inspired Method. We evaluate the performance of different features descriptors on different databases, and our method shows good efficiency.

View publication DOI

2013Other

Fast pedestrian detection using BWLSD for ROI

Aminou Halidou, Xinge You

This paper presents a pedestrian detection approach based on Multi-block Local Binary Pattern (MB-LBP) features and Weighted Region Covariance Matrix (WRCM). Multistage classifiers are used to increase the processing speed and reliability of the detection system. Using the modified 3-D B-spline Wavelet-Based Local Standard Deviation (BWLSD) techniques, the region of interest is determined. Once the pedestrian region is identified, the front end of the multistage classifier quickly determines wherever pedestrians may be present, while the back end confirms whether the first descriptor did classify correctly. The experimental results demonstrated that our approach performed well in real-time application.

View publication DOI

2024Journal article

People counting using IR-UWB radar sensors and machine learning techniques

Ange Joel Nounga Njanda, Jocelyn Edinio Zacko Gbadoubissa, Emanuel Rădoi, Ado Adamou Abba Ari, Roua Youssef, Aminou Halidou

Systems and Soft Computing

This study aims to detect and count people using impulse radio ultra-wideband radar and machine learning algorithms. However, the data quality, difficulty distinguishing human signals from noise and clutter, and instances where human presence is not detected make it challenging to count multiple humans. To overcome these challenges, we apply wavelet transformation to reduce signal size and use simple moving averages to eliminate noise. Next, we create features based on statistical and entropic properties of the signal and apply several classification algorithms, including ANN, Random Forest, KNN, XGBOOST, and multiple linear regression, to predict the number of people present. Our findings reveal that using the ANN classifier with the Daubechies 4 (db4) wavelet provides better results than other classifiers, with an accuracy rate of 99%. Additionally, filtering the data improves accuracy, and labeling the data after extracting essential characteristics significantly improves the model’s accuracy.

View publication DOI

2024PreprintOpen access

Plants diseases diagnosis based on MobileNet and Inception Architectures

Aminou Halidou, Daniel Georges Olle Olle, Daramy Vandi Von Kallon, William John Baraza, Obam Akou, Fokam Ninyim Astride Melvin

Research Square

View publication DOI

Halidou AMINOU

Publication summary

Recurring keywords

Biography

Publications

2026

DynaCIS-PIR: Churn-Resilient and Access-Pattern-Private Coverless Image Steganography

DynaCIS-PIR: Churn-Resilient and Access-Pattern-Private Coverless Image Steganography

Enhanced OTP and facial recognition for e-learning authentication

2025

Convolutional Neural Network-Based Xception, MobileNetV2 and InceptionV3 Models for Plant Disease Identification in Sub-Saharan Africa

Voter Authentication Using Enhanced ResNet50 for Facial Recognition

2024

Diagnosis of Plant Diseases Using Mobilenet and Inception Architectures

Enhanced Otp and Facial Recognition for E-Learning Authentication

Optimization of ResNet50 based on flatten and dense layer insertion applied to facial recognition voting system

2023

People Counting Using Ir-Uwb Radar Sensors with Machine Learning Techniques

Review of wavelet denoising algorithms

2020

A review of mathematical modeling, artificial intelligence and datasets used in the study, prediction and management of COVID-19

2017

Robust Steganography based on Matching Pixel Locations

2014

Fast pedestrian detection based on region of interest and multi-block local binary pattern descriptors

Pedestrian Detection Based on Multi-Block Local Binary Pattern and Biologically Inspired Feature

2013

Fast pedestrian detection using BWLSD for ROI

People counting using IR-UWB radar sensors and machine learning techniques

Plants diseases diagnosis based on MobileNet and Inception Architectures

Additional information

Publication timeline

Co-authors

UY1 researchers

Other co-authors

Profiles & networks