In most approaches, tissue and subcortical structure segmentations of MR brain scans are handled globally over the entire brain volume through two relatively independent sequential steps. We propose a fully Bayesian joint model that integrates local tissue and structure segmentations and local intensity distributions. It is based on the specification of three conditional Markov Random Field (MR...

Résumé: This paper presents HACSEG, a new ant algorithm for the image segmentation based on the Markov Random Field (MRF) and a modified version of the Ant Colony System algorithm coupled with a local search. HACSEG algorithm differs from other ant algorithms proposed for image segmentation, in the way that each artificial ant is associated with a particular partition that is modified using phe...

In this paper, we propose a method called Convolutional Neural Network-Markov Random Field (CNN-MRF) to estimate the crowd count in a still image. We first divide the dense crowd visible image into overlapping patches and then use a deep convolutional neural network to extract features from each patch image, followed by a fully connected neural network to regress the local patch crowd count. Si...

Steganography [6][13] refers to embedding information or secret message into media. This paper presents a simple and secure high-capacity steganographic algorithm for information hiding [15]. We synthesize a cover-image texture with four gray levels 32, 96, 160, and 224 of user-selected size based on a Markov Random Field (MRF) model [3]. On the other hand, each byte of the secret information (...

A new multispectral image context classification, which is based on a stochastic relaxation algorithm and Markov-Gibbs random field, is presented. The implementation of the relaxation algorithm is related to a form of optimization programming using annealing. The authors motivate a Bayesian context decision rule, and a Markov-Gibbs model for the original Landsat MSS (multispectral scanner) imag...

Belief propagation and graph cuts have emerged as powerful tools for computing efficient approximate solution to stereo disparity field modelled as the Markov random field (MRF). These algorithms have provided the best performance based on results on a standard data set [1]. However, employment of the brightness constancy (BC) assumption severely limits the range of their applications. Previous...

We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedure that synthesizes training samples from specific noise models. We demonstrate this approach on the challenging problem of natural image denoising. Using a test set with a hundred natural images, we find that convolut...

We propose a flexible prior model for the parameters of a binary Markov random field (MRF) defined on a rectangular lattice and with k ×l cliques. The prior model allows higher-order interactions to be included in the MRF. We also define a reversible jump Markov chain Monte Carlo (RJMCMC) algorithm to sample from the associated posterior distribution. The number of possible parameters for an MR...

Low-level vision is a fundamental area of computer vision that is concerned with the analysis of digital images at the pixel level and the computation of other dense, pixel-based representations of scenes such as depth and motion. Many of the algorithms and models in low-level vision rely on a representation of prior knowledge about images or other dense scene representations. In the case of im...

In this paper, we present an automatic hierarchical framework for the segmentation of a variety healthy tissues and lesions in brain MRI of patients with Multiple Sclerosis (MS). At the voxel level, lesion and tissue labels are estimated through a Markov Random Field (MRF) segmentation framework that leverages spatial prior probabilities for 9 healthy tissues through multi-atlas fusion (MALF). ...