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.
Jonathan JankeMauro CastelliAles PopovicPublished in: Expert Syst. Appl. (2019)
Keyphrases
- digital images
- high level
- neural network
- fully connected
- image features
- classification algorithm
- pattern recognition
- data analysis
- support vector
- training set
- image processing
- supervised learning
- support vector machine svm
- fault diagnosis
- learning algorithm
- feature extraction
- artificial neural networks
- computer vision
- information retrieval