Application of Convolutional Neural Networks to Classify Ambiguous Categories
DOI:
https://doi.org/10.47611/jsrhs.v12i1.3981Keywords:
Artificial Intelligence, Deep Learning, Convolutional Neural Network, Image ClassificationAbstract
Neural networks are often used for classifying images of specific objects, people, animals, and other objects of interest because of their ability to find particular patterns for categories. In this paper, we apply a Convolutional Neural Network (CNN) to classify images from a dataset of 4 semi-ambiguous classes and compare the scores of different architectures of neural networks and how different preprocessing techniques can affect their performance.
Downloads
References or Bibliography
R. Google Scraped Image Dataset. (2022). Retrieved 27 August 2022, from https://www.kaggle.com/datasets/duttadebadri/image-classification
Rawat, W., & Wang, Z. (2017). Deep convolutional neural networks for image classification: A comprehensive review. Neural computation, 29(9), 2352-2449. https://doi.org/10.1162/neco_a_00990
Albawi, S., Mohammed, T. A., & Al-Zawi, S. (2017, August). Understanding of a convolutional neural network. In 2017 international conference on engineering and technology (ICET) (pp. 1-6). Ieee. https://doi.org/10.1109/ICEngTechnol.2017.8308186
Santurkar, S., Tsipras, D., Ilyas, A., & Madry, A. (2018). How does batch normalization help optimization?. Advances in neural information processing systems, 31. https://doi.org/10.48550/arXiv.1805.11604l
Published
How to Cite
Issue
Section
Copyright (c) 2023 Arjun Rai; Guillermo Goldsztein
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
