Browsing by Author "Jimada-Ojuolape Bilkisu"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Enhancing Automated Face Recognition with Makeup Detection: A CNN-Based Approach
    (COVENANT JOURNAL OF ENGINEERING TECHNOLOGY (CJET),, 2024-05-20) Balogun, O. Monsurat; Jimada-Ojuolape Bilkisu; Odeniyi A. Latifat
    This study delves into the complex issue posed by facial makeup, which has the potential to significantly alter the appearance of individuals, posing a challenge to automated face recognition systems, as well as age and beauty estimation methods. A model solution aimed at automatically detecting makeup in facial images to improve the accuracy of recognition systems was proposed in this work. The approach revolves around utilizing a sophisticated model that harnesses a feature vector encapsulating crucial aspects of facial attributes including shape, texture, and color. Employing an advanced Convolutional Neural Network (CNN) architecture, the model detects the presence of makeup by analyzing key facial landmarks such as eye distance, nose width, eye socket depth, cheekbones, jawline, and chin. Experiments were performed on a dataset consisting of 200 facial images to assess the effectiveness of the proposed method. The model achieved a validation accuracy of 100%, demonstrating its robustness in makeup face detection. Notably, the computational runtime for the validation process was 1 minute and 40 seconds, underscoring the efficiency of the proposed approach. Moreover, an innovative adaptive pre-processing strategy that capitalizes on makeup information to enhance the performance of facial recognition systems was developed. This strategy aims to optimize the recognition process by leveraging insights gained from makeup detection. By integrating this adaptive pre-processing step, further advancements in the accuracy and reliability of facial recognition technology, particularly in scenarios where makeup may confound traditional recognition methods, are envisioned.
  • Thumbnail Image
    Item
    Exploring the Influence of Noise on Voice Recognition Systems: A Case Study of Supervised Learning Algorithms
    (Published by the Faculty of Engineering, University of Maiduguri, Nigeria, 2024-05-20) Balogun M onsurat Omolara; Jimada-Ojuolape Bilkisu; Mahmoud Mahmoud O.
    Speech recognition systems have become increasingly prevalent in various applications, ranging from virtual assistants to voice-controlled devices and dictation software. The desire to design human-computer interfaces that are more accessible, intuitive, and efficient cannot be overemphasized. Such advancements hold significant potential to enhance accessibility, productivity, safety, and user experience across various domains and industries.. Despite significant advancements in speech recognition technology, several challenges persist. One primary challenge is achieving high accuracy and robustness across diverse speaking styles, accents, and environmental conditions. Background noise, variations in pronunciation, and overlapping speech can introduce errors and degrade performance, especially in real-world scenarios. This study explores the pursuit of accurate and lightweight algorithms in biometric applications, focusing on voice recognition. Using a dataset featuring renowned leaders' voices, the research compares K-Nearest Neighbors (KNN) and Artificial Neural Network (ANN) techniques. Employing Mel Frequency Cepstral Coefficients (MFCC) and considering noisy and noiseless environments, the study reveals that ANN outperforms KNN. In noisy conditions, ANN achieves 62.4% accuracy, while KNN reaches 33.4%. In noiseless settings, ANN's accuracy rises to 95%, surpassing KNN's 88%. Assessment metrics like False Acceptance Rate, False Rejection Rate, F1 Score, Recall, Precision, and Receiver Operator Characteristics Curve are analyzed. The study emphasizes the detrimental impact of noise on recognition accuracy and underscores ANN's consistent superiority over KNN. Despite challenges posed by noisy environments, the research highlights the potential benefits of these approaches, emphasizing ANN's superior performance across scenarios. This research showcases the significance of accurate biometric systems, emphasizing ANN's advantages in enhancing usability and precision, especially in real-world noisy conditions.
  • Thumbnail Image
    Item
    Feasibility of Wind Energy Utilization for Sustainable Power Generation in Ilorin, Kwara State, Nigeria's North-Central Region
    (ABUAD Journal of Engineering Research and Development (AJERD, 2024-05-16) Balogun Monsurat Omolara; Jimada-Ojuolape Bilkisu; Taiwo James Ayo; Olusi Titilayo
    The escalating energy demands across Nigeria, especially in remote rural areas, have outpaced the capacity of the national electricity grid, necessitating the development of independent and sustainable energy sources. Among the renewable options, wind energy stands out as a promising solution. This study focuses on assessing the potential of wind energy in Ilorin, located in Kwara State, within Nigeria's north-central region. Utilizing data collected from 2007 to 2021 by the Nigerian Meteorological Agency, the research examines monthly average wind speeds at two specific coordinates in Ilorin, considering variations in air density. The study utilizes a 15-year set of monthly average wind velocities obtained from the Nigerian Meteorological Agency (NiMet) Headquarters in Abuja, measured at a height of 10 meters above ground level. By employing the 2-coefficient Weibull statistical model and extrapolation principles across different altitudes ranging from 150 to 900 meters above ground level, the study reveals distinct seasonal patterns of wind speeds ranging from 1.1 to 5.1 m/s in Ilorin. Furthermore, wind power density values ranging from 6.7 to 39.20 W/m2 are identified, with optimal wind attributes observed at altitudes exceeding 900 meters. These findings provide valuable insights for assessing the feasibility of wind energy utilization and designing efficient systems in Nigeria's north-central regions, aiding in the sustainable energy transition.