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

Engineering & Materials Science

• Neural networks 100%
• Convolutional neural networks 75%
• Network layers 45%
• Logistic regression 22%
• Image classification 21%
• Random forests 21%
• Network architecture 19%
• Support vector machines 16%
• Classifiers 14%