Volume 1
Machine Learning and Deep Learning Algorithms in Image Classification: A Review
Authors
Esmat Jafarpour Lashkami, Abdoljalil Addeh
Abstract
Machine learning (ML) and deep learning (DL) methods are extensively applied in image classification, each offering distinct advantages depending on the dataset and application requirements. A lack of comprehensive information comparing these methods prompted the creation of this short review. Popular ML methods, such as Support Vector Machines (SVM), Random Forests (RF), and k-Nearest Neighbors (k-NN), are contrasted with advanced DL techniques, particularly Convolutional Neural Networks (CNNs), for their ability to automatically extract hierarchical features, making them more effective for tasks like image classification. The analysis highlights performance factors, including accuracy, interpretability, and computational demands, ultimately recommending DL methods for large-scale tasks and ML methods for smaller, interpretable applications.
Keyword: Machine learning, Deep learning, Image classification, CNN, SVM, Random Forest, k-NN
PDF [ 220.65 Kb ] | Endnote File | XML
