WaveCNet: Wavelet Integrated CNNs to Suppress Aliasing Effect for Noise-Robust Image Classification.
Qiufu LiLinlin ShenSheng GuoZhihui LaiPublished in: IEEE Trans. Image Process. (2021)
Keyphrases
- image classification
- image noise
- feature extraction
- wavelet transform
- frequency domain
- power spectrum
- multiscale
- denoising
- wavelet coefficients
- geometric distortions
- transformed image
- cellular neural networks
- noisy environments
- noise level
- random noise
- singularity detection
- imaging artifacts
- registration errors
- wavelet domain
- noise reduction
- signal to noise ratio
- bag of words
- high frequency
- image representation
- high resolution
- low frequency
- estimation error
- noise model
- noisy data
- wavelet analysis
- edge detection
- anti noise
- greater robustness
- neural network