Analysis of the proficiency of fully connected neural networks in the process of classifying digital images. Benchmark of different classification algorithms on high-level image features from convolutional layers

• Published in: Expert systems with applications Vol. 135; pp. 12 - 38
• Main Authors: Janke, Jonathan, Castelli, Mauro, Popovič, Aleš
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 30.11.2019; Elsevier BV
• Subjects: Algorithms; Artificial neural networks; Benchmarks; Classification; Computer vision; Convolutional neural networks; Digital imaging; Image classification; Image filters; Neural networks; Regression analysis; Support vector machines; Convolutional neural networks; Computer vision; Image classification

•Research that investigates CNN architectures for classification task.•Two steps method that combines CNN with other ML classifiers.•Large experimental phase considering different architectures and datasets.•Results used to provide guidelines on the choice of the best classifiers.•CNNs can improve t...