There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality.

Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

I and i

다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

https://minerva-access.unimelb.edu.au/bitstream/handle/11343/197439/1207.0203v1.pdf

Internet of Things (IoT): A vision, architectural elements, and future directions

We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component separately, our method jointly optimizes all layers. Our deep CNN has a lightweight structure, yet demonstrates state-of-the-art restoration quality, and achieves fast speed for practical on-line usage. We explore different network structures and parameter settings to achieve trade-offs between performance and speed. Moreover, we extend our network to cope with three color channels simultaneously, and show better overall reconstruction quality.

Image Super-Resolution Using Deep Convolutional Networks

Block matching has been used for motion estimation and motion compensation in MPEG standards for years. While it has an acceptable performance in describing motion between frames, it requires quite a few bits to represent the motion vectors. In certain circumstances, the use of whole frame affine motion models would perform equally well or even better than block matching in terms of motion accuracy, while it results in the coding of only 6 parameters. In this paper, we modify an MPEG-4 codec by adding: (1) 6 affine model parameters to the frame header; and (2) mode selection among INTRA, SKIP, INTER-16/spl times/16, INTER-8/spl times/8, and GLOBAL-AFFINE modes by Lagrange optimal rate-distortion criteria. Simulation results demonstrate 10-20% decrease in bit-rate, compared to the MMS codec for an average coded P-frame with the same reconstruction PSNR.

An adaptive coding scheme using affine motion model for MPEG P-VOP

The compression of video can reduce the accuracy of automated tracking algorithms. This is problematic for centralized applications such as transportation surveillance systems, where remotely captured and compressed video is transmitted to a central location for tracking. In typical systems, the majority of communications bandwidth is spent on representing events such as capture noise or local changes to lighting. We propose a pre- and post-processing algorithm that identifies and removes such events of low tracking interest, significantly reducing the bitrate required to transmit remotely captured video while maintaining comparable tracking accuracy. Using the H.264/AVC video coding standard and a commonly used state-of-the-art tracker we show that our algorithm allows for up to 90% bitrate savings while maintaining comparable tracking accuracy.

Tracking-optimal pre- and post-processing for H.264 compression in traffic video surveillance applications

Erratum: Applications of artificial neural networks in image processing III (Proceedings of SPIE: Applications of Artificial Neural Networks in Image Processing III (26-27 January 1998))

Most current state of the art blind image deconvolution methods model the underlying image (either in the image or filter space) using sparsity promoting priors and perform inference, that is, image, blur, and parameter estimation using variational approximation. In this paper we propose the use of the spike-and-slab prior model in the filter space and a variational posterior approximation more expressive than mean field. The spike-and-slab prior model, which is the "gold-standard" in sparse machine learning, has the ability to selectively shrink irrelevant variables while relevant variables are mildly regularized. This allows to discard irrelevant information while preserving important features for the estimation of the blur which results in more precise and less noisy blur kernel estimates. In this paper we present a variational inference algorithm for estimating the blur in the filter space, which is both more efficient than MCMC and more accurate than the standard mean field variational approximation. The parameters of the prior model are automatically estimated together with the blur. Once the blur is estimated, a non-blind image restoration algorithm is used to obtain the sharp image. We prove the efficacy of our method on both synthetically generated and real images.

/pdf/parameter-estimation-in-spike-and-slab-variational-inference-5atkp7s1p0.pdf

Parameter estimation in spike and slab variational inference for blind image deconvolution

In this paper, regularized estimation of the displacement vector field (DVF) of a dynamic image sequence is considered. A new class of non-quadratic convex regularization functionals is employed to estimate the motion field in the presence of motion discontinuities and occlusions. The derivation of the functionals is based on entropy considerations and does not require parameter tuning as in previously proposed methods. This new class of functionals is both robust and convex making it possible to preserve motion boundaries and obtain a globally optimum solution. The performance of entropic functionals is compared to previously suggested functionals for motion estimation using real and synthetic image sequences.

Aggelos K. Katsaggelos

Papers

An adaptive coding scheme using affine motion model for MPEG P-VOP

Tracking-optimal pre- and post-processing for H.264 compression in traffic video surveillance applications

Erratum: Applications of artificial neural networks in image processing III (Proceedings of SPIE: Applications of Artificial Neural Networks in Image Processing III (26-27 January 1998))

Parameter estimation in spike and slab variational inference for blind image deconvolution

Regularized motion estimation using robust entropic functionals