In this paper, we propose the sequential input of a noisy image patch and the impulse response of a low-pass filter (LPF) in the training of the conventional fast and flexible solution for CNN-based image denoising (FFDNet) architecture, which enhances denoising performance and edge preservation and achieves high perceptual quality. The proposed method consists of two steps. In the first step, the power spectrum sparsity is utilized to determine the impulse response of LPF and the resulting impulse response is added to the noisy image patch in a sequential form to estimate the low- and high-frequency components of the input image. In this step, the use of three different types of LPF is also considered. In the second step, the FFDNet architecture, a deep-learning-based image denoiser, is employed. The proposed method achieves satisfactory denoising performance for grayscale and color datasets on synthetic additive white Gaussian noise (AWGN) in terms of the peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), feature similarity index (FSIM), and learned perceptual image patch similarity (LPIPS) compared with the original FFDNet. The performances on realistic noise and for chest X-ray images are also investigated.

In this paper, we propose a blind noisy image quality estimation method of simultaneously utilizing three statistical features extracted from three different domains of the input noisy image. The statistical features used in this paper are (i) eigen-based variance by the covariance matrix of image blocks in the spatial domain, (ii) the spectral entropy of the power spectrum in the frequency domain, and the standard deviation in the wavelet domain. The extracted statistical features are fed into an extreme learning machine algorithm for mapping into perceptual quality scores. The model is trained and tested on images with six common noise distortion types commonly occurring in real-world applications: additive white Gaussian noise, additive Gaussian noise in color component, high-frequency noise, masked noise, impulse noise, and multiplicative noise. For the CSIQ, TID2008, TID2013, and KADID10k databases, the experimental results show that our method covers noise distortions wider than those of the conventional methods and achieves consistently better performance for blind noisy image quality assessment.

Heaviside reformulated the Maxwell equations because he considered that electromagnetic fields and waves have duality. As a result of the reformulation, the Poynting vector was obtained. When the variations of an electromagnetic field propagate in space as waves, this wave is referred to as an electromagnetic wave. The Poynting vector represents the traveling direction of the electromagnetic wave. In this Session, we reexamine electromagnetic fields and waves by focusing on the relationship between the Poynting vector and the duality. According to Wikipedia, no current flows in a vacuum because there are no electrons or electric charges. However, this seems to be incorrect, and the current I(x) given by rotH = I (x) flows in a vacuum. Moreover, a voltage V(x) given by rotE =−V (x) is generated because the magnetic field is the dual of the electric field and the current is the dual of the voltage. As a result, the presence of a coil in a vacuum is expressed by rotE =−V (x) =−∂B / ∂t =− pLI (x) . Namely, the Maxwell equations indicate that “self-induction can occur everywhere in the atmosphere”, as described by Heaviside in the book written by Nahin. Moreover, a capacitor in the atmosphere, including a vacuum, is also given by an equation because it is the dual of the coil. Thus, electromagnetic waves have physical properties of circuit elements including coils and capacitors, which are different from those of lines of forces, such as lines of electric and magnetic forces. The physics of electromagnetic waves is included in classical physics but is different from Newtonian mechanics and uses complex numbers.