Convolutional Neural Networks for Omnidirectional Image Quality Assessment: Pre-Trained or Re-Trained?
Abderrezzaq SendjasniMohamed-Chaker LarabiFaouzi Alaya CheikhPublished in: ICIP (2021)
Keyphrases
- pre trained
- image quality assessment
- convolutional neural networks
- convolutional network
- quality assessment
- structural similarity
- image quality
- training data
- image database
- training examples
- human visual system
- correlation coefficient
- visual perception
- human perception
- natural images
- vision system
- quality evaluation
- control signals
- quality metrics
- kullback leibler divergence
- small number
- visual quality
- high quality
- computer vision
- learning algorithm
- support vector