Blind image quality assessment for multiply distorted images via convolutional neural networks.
Jie FuHanli WangLingxuan ZuoPublished in: ICASSP (2016)
Keyphrases
- distorted images
- convolutional neural networks
- blind image quality assessment
- natural scene statistics
- image quality assessment
- image quality
- human perception
- structural similarity
- human visual system
- perceptual quality
- quality assessment
- geometric distortions
- test images
- focal length
- natural images
- quality metrics
- visual quality
- image database
- pixel values
- multiscale
- correlation coefficient
- high quality
- quality evaluation
- low level