Browsing by Author "Asaju Christine Bukola,"

Now showing 1 - 2 of 2
  • Item
    Transfer Learning: An Enhanced Feature Extraction Techniques for Facial Emotion Classification
    (IEEE, 2021-07) Asaju Christine Bukola,; Ugwu Kingsley; Eze Chinemerem Christian; Ugbedeojo Musa
    The process of extracting features from images from the scratch in the field of machine learning is a very challenging and time-consuming task. Previous work focused on a technique for feature extraction in which a CNN is pre-trained on some data sets and then in turn used to learn the pattern from other datasets on which it was not originally trained. This paper proposed transfer learning as the ability of a pre-trained CNN model to learn patterns from data which it was not originally trained on. Several pre-trained CNN architectures have been proposed by researchers to improve the system performance. Some of these include the ResNet, Xception, VGG16, VGG19, InceptionResnetV2, InceptionV3, DenseNet, MobileNet, etc., all trained on ImageNet datasets. However, not all of these networks have the ability to effectively perform feature extraction on facial datasets. This paper attempts to compare the efficiencies of five pre-trained networks namely, VGG19, VGG16, ResNet50, inceptionResNetV3, and InceptionV2 which have been pre-trained on the ImageNet dataset as features extractors on the DISFA plus facial emotion dataset for classification. The extracted features are used for training and testing a simple linear regression classifier. Testing the classifier network with features extracted by these networks produced different accuracies. It was discovered in the process that out of the five networks being tested, the VGG19 architecture performed more accurately than other pre-trained networks on the classifier with an accuracy of 97%. The work, therefore, presumes that the VGG19 network has a better generalization ability on facial data than other networks.
  • Item
    You Only Look Once (YOLO) Real-time Object Detection Algorithms: A Systematic Literature Review
    (2025-07) Asaju Christine Bukola,; Florence Funke Abiola
    Real-time object detection is essential in various computer vision applications, such as autonomous driving, surveillance, and robotics. Among deep learning based object detection frameworks, the You Only Look Once (YOLO) algorithm family stands out for its impressive speed, accuracy, and efficiency. This paper provides a systematic review of YOLO-based object detection models, examining their development over the years, enhancements, and practical uses. It explores the evolution of YOLO from its initial version to the latest advancements, focusing on key architectural changes, training methodologies, and performance optimizations. Furthermore, YOLO is compared with other leading object detection models, which outline its strengths and limitations. The review also explores domain-specific applications of YOLO, including medical imaging, autonomous navigation, and industrial automation. By consolidating findings from recent research, this study sheds light on existing challenges and potential future directions in real-time object detection using YOLO.