Visual Data Recognition and Modeling Based on Local Markovian Models

We propose textural features, which are invariant to illumination spectrum and extremely robust to illumination direction. They require only a single training image per texture and no knowledge of illumination direction or spectrum. Hence, these features are suitable for content-based image retrieval (CBIR) of realistic scenes with colour textured objects and variable illumination. The illumination invariants are derived from Markov random field based texture representations. Our illumination invariant features are favourably compared with frequented features in this area - the local binary patterns, steerable pyramid and Gabor textural features, respectively. The superiority of our new invariant features is demonstrated in the illumination invariant recognition of the most advanced representation for realistic real-world materials - bidirectional texture function (BTF) textures.

Previous work has demonstrated the effectiveness of the expectation-maximization algorithm to restore noisy and blurred single- channel images and simultaneously identify its blur. In addition, a gen- eral framework for processing multichannel images using single-channel techniques has been developed. The authors combine and extend the two approaches to the simultaneous blur identification and restoration of multichannel images. Explicit equations for that purpose are developed for the general case when cross-channel degradations are present. An important difference from the single-channel problem is that the cross power spectra are complex quantities, which further complicates the analysis of the algorithm. The proposed algorithm is very effective at restoring multichannel images, as is demonstrated experimentally.

For original article see Galatsanos et al. (IEEE Trans. Signal Processing, vol.39, p.2222-36, Oct. 1991). In this correspondence, we give the correct matrix formulation arising from the constrained optimization of the least squares restoration of multichannel images in Galatsanos et al.

Computed tomography (CT) blurring caused by point spread function leads to errors in quantification and visualization. In this paper, multichannel blind CT image restoration is proposed to overcome the effect of point spread function. The main advantage from multichannel blind CT image restoration is to exploit the diversity and redundancy of information in different acquisitions. The proposed approach is based on a variable splitting to obtain an equivalent constrained optimization formulation, which is addressed with the alternating direction method of multipliers and simply implemented in the Fourier domain. Numerical experiments illustrate that our method obtains a higher average gain value of at least 1.21 dB in terms of Q metric than the other methods, and it requires only 7 iterations of alternating minimization to obtain a fast convergence.

Digital image restoration of monochrome images has been studied extensively, however, problems associated with the restoration of multichannel images still remain to be investigated. In this paper, the Wiener solution of a multichannel restoration system is presented. Using block Toeplitz to block circulant approximation, the inversion of the multichannel imaging system becomes feasible by utilizing a fast iterative matrix inversion procedure. The restoration uses both the within-channel and between-channel correlation, hence the restored result is a better estimate than the one produced by independent channel restoration. Simulations are also presented.

In this paper, we develop a multichannel image restoration algorithm using compound Gauss-Markov random fields (CGMRF) models. The line process in the CGMRF allows the channels to share important information regarding the objects present in the scene. In order to estimate the underlying multichannel image, two new iterative algorithms are presented and their convergence is established. They can be considered as extensions of the classical simulated annealing and iterative conditional methods. Experimental results with color images demonstrate the effectiveness of the proposed approaches.

This work derives the multichannel Bussgang restoration algorithm for blind image restoration problems. In its basic outline, the derived Bussgang restoration algorithm is based on iteratively filtering the measurements by means of a bank of FIR filters, and updating the filter-bank on the base of a nonlinear estimate of the original image. The filters are updated by solving a linear system (multichannel normal equations) whose coefficients' matrices depend on the cross-correlations between the measurements and a nonlinear estimate of the original image, this latter obtained using a Bayesian criterion. Experimental results pertaining to restoration of motion blurred text images and out-of-focus star field images are reported.

In this paper, we present a new unsupervised colour image segmentation algorithm using competitive and morphological concepts. The algorithm is carried out in three processing stages. It starts by an estimation of the density function, followed by a training competitive neural network with a new criterion of resemblance called Mahalanobis distance which detects local maxima of the density function, and ends by the extraction of modal regions using an original method based on the morphological concept. The so detected modes are then used for the classification process. Compared to the K-means clustering or to the clustering approaches based on the different competitive learning schemes, the proposed algorithm has proven, under a number of real and synthetic test images, that it is automatic, has a fast convergence and does not need priori information about the data structure.

Low-key images widely exist in imaging-based systems such as space telescopes, medical imaging equipment, machine vision systems. Unsupervised low-key image segmentation is an important process for image analysis or digital measurement in these applications. In this paper, a novel active contour model with the probability density function (PDF) of gamma distribution for image segmentation is proposed. The flexible gamma distribution is used to describe both of the heterogeneous foreground and dark background in a low-key image. Besides, an unsupervised curve initialization method is also designed in this paper, which helps to accelerate the convergence speed of curve evolution. The effectiveness of the proposed algorithm is demonstrated through comparison with the CV model. Finally, an industrial application based on proposed approach is described in this paper.

This paper proposes a new unsupervised approach for colour image segmentation. A hierarchy of image partitions is created on the basis of a function that merges spatially connected regions according to primary perceptual criteria. Likewise, a global function that measures the goodness of each defined partition is used to choose the best low-level perceptual grouping in the hierarchy. Contributions also include a comparative study with five unsupervised colour image segmentation techniques. These techniques have been frequently used as a reference in other comparisons. The results obtained by each method have been systematically evaluated using four well-known unsupervised measures for judging the segmentation quality. Our methodology has globally shown the best performance, obtaining better results in three out of four of these segmentation quality measures. Experiments will also show that our proposal finds low-level perceptual solutions that are highly correlated with the ones provided by humans.

The application of a Markov random field (MRF) state model in an expectation-maximization (EM)-based approach to unsupervised image segmentation is investigated. In the calculation of the marginal distribution of the state field, it is shown that the use of the expected state values for interacting pixel sites in the computation of the MRF energy function may be interpreted as a mean-field approximation. The implications of calculating a self-consistent expectation of the state field are considered. EM convergence criteria are considered, and a criterion based upon divergence is proposed. Experimental results based on synthetic data illustrate the performance advantage of the mean-field approximation and the computational advantage of using self-consistent expectations. >

The traditional multi-resolution Markov random field (MRMRF) model uses two-component Markov random field model on each resolution, and requires training data to estimate the necessary model parameters, which is unsuitable for unsupervised image segmentation. Under this circumstance, a new multi-resolution Markov random field model with variable potential for unsupervised texture image segmentation is presented. The new model solves this problem by introducing a variable potential function for multi-level logistic distribution (MLL) model on each scale. Using this method, the new model can automatically estimate model parameters and produce accurate unsupervised segmentation results. The results obtained on synthetic texture images and remote sensing images demonstrate that a better segmentation is achieved by our model than the traditional MRMRF model.

Content Based Image Retrieval (CBIR) has been an active and fast growing research area in both image processing and data mining. Malaysia has been recognized with a rich marine ecosystem. Challenges of these images are low resolution, translation, and transformation invariant. In this paper, we have designed an automated CBIR system to characterize the species for future research. Gradient vector flow (GVF) has been implemented in a lot of image processing applications. Inspired by its fast image restoration algorithms we applied GVF for marine images. We evaluated different automated segmentation techniques and found GVF showing better retrieval results compared to other automated segmentation techniques.

Current predefined architectures for deep learning are computationally very heavy and use tens of millions of parameters. Thus, computational costs may be prohibitive for many experimental or technological setups. We developed an ad hoc architecture for the classification of multispectral images using deep learning techniques. The architecture, called 3DeepM, is composed of 3D filter banks especially designed for the extraction of spatial-spectral features in multichannel images. The new architecture has been tested on a sample of 12210 multispectral images of seedless table grape varieties: Autumn Royal, Crimson Seedless, Itum4, Itum5 and Itum9. 3DeepM was able to classify 100% of the images and obtained the best overall results in terms of accuracy, number of classes, number of parameters and training time compared to similar work. In addition, this paper presents a flexible and reconfigurable computer vision system designed for the acquisition of multispectral images in the range of 400 nm to 1000 nm. The vision system enabled the creation of the first dataset consisting of 12210 37-channel multispectral images (12 VIS + 25 IR) of five seedless table grape varieties that have been used to validate the 3DeepM architecture. Compared to predefined classification architectures such as AlexNet, ResNet or ad hoc architectures with a very high number of parameters, 3DeepM shows the best classification performance despite using 130-fold fewer parameters than the architecture to which it was compared. 3DeepM can be used in a multitude of applications that use multispectral images, such as remote sensing or medical diagnosis. In addition, the small number of parameters of 3DeepM make it ideal for application in online classification systems aboard autonomous robots or unmanned vehicles.

Recently, multichannel image restoration gains population in many applications such as color imaging systems, image sequences, etc. In the present paper, we classify many multichannel restoration techniques as Wiener and CLS approaches, which are respectively based on stochastic and deterministic models of the original image. We also compare two approaches in the sense of both restoration performance and implementational efficiency.