Навчання моделей згорткових нейронних мереж виявленню об’єктів, сцен і контекстів на зображеннях
Journal Title: Challenges and Issues of Modern Science - Year 2024, Vol 3, Issue 1
Abstract
Purpose. The study focuses on developing an optimized convolutional neural network (CNN) for detecting objects, scenes, and contexts in diverse images. It emphasizes improving the architecture, training methods, and performance of CNNs in computer vision tasks, which are essential for various industries. Design / Method / Approach. The study uses Python, TensorFlow, and Keras to create and train a CNN on dataset CIFAR-10. Hyperparameter tuning and data augmentation techniques were applied to enhance model performance. Findings. The CNN model trained on CIFAR-10 demonstrated strong performance with an accuracy of approximately 85% on the test set, highlighting its ability to classify diverse objects. Data augmentation techniques significantly improved the overall performance by making the model more robust to image variations. Theoretical Implications. The study emphasizes the importance of proper data preparation, including image normalization and augmentation, to achieve high accuracy in CNN models. Practical Implications. The application of convolutional neural networks in real-world scenarios such as security, medicine, and autonomous systems is transformative. These models can accurately detect objects and understand contexts, opening new possibilities for innovation and automation in various industries. Originality / Value. This study makes a valuable contribution to research on convolutional neural networks by showcasing the successful training and optimization of a CNN for object detection. The combination of data augmentation, architecture design, and hyperparameter tuning highlights an effective approach to achieving high accuracy in computer vision tasks. Research Limitations / Future Research. Future research could explore alternative CNN architectures and larger datasets to further enhance object detection accuracy. Additionally, integrating new learning strategies could improve the model's performance in more complex and varied environments. Paper Type. Applied Research.
Authors and Affiliations
Роман Орлов, Сергій Таборанський
Keywords
Related Articles
- EP ID EP753121
- DOI https://purl.org/cims/2403.018
- Views 1
- Downloads 0
Методика вибору кроку дискретизації моделі в інформаційно-вимірювальних технологіях
Purpose. The main aim of the research is to produce recommendations in the form of a methodology that permits designers to establish a discretization step for a simulation model, when that model is being prepared to be i...
Internet of Things (IoT) technologies: features, development prospects and potential threats
Purpose. The article aims to explore the characteristics, development prospects, and possible threats associated with Internet of Things (IoT) technologies. With IoT rapidly integrating into multiple industries, understa...
Розробка автоматизованої системи управління температурним режимом випікання хлібобулочних виробів із використанням нечіткого контролера
Purpose. The purpose of the work is to improve the main indicator of the economic efficiency of the production of bakery products - the saving of electricity for heating inside the chamber. Design / Method / Approach. Ac...
Аналіз можливостей створення безпілотного літального апарату для радіаційного моніторингу
Purpose. This research focuses on analyzing the feasibility of developing an unmanned aerial vehicle (UAV) specifically designed for measuring radiation levels. Such a UAV would enhance safety and provide essential data...
Методика супутникового моніторингу вирубування лісів за даними Sentinel-2A/B
Purpose. The main goal of the research was development and testing of the methodology of automated processing and analysis of multispectral satellite images of medium spatial resolution for the detection of deforestation...