Torfinn Taxt

FEATURE EXTRACTION METHODS FOR CHARACTER RECOGNITION--A SURVEY

This paper presents an overview of feature extraction methods for off-line recognition of segmented (isolated) characters. Selection of a feature extraction method is probably the single most important factor in achieving high recognition performance in character recognition systems. Different feature extraction methods are designed for different representations of the characters, such as solid binary characters, character contours, skeletons (thinned characters) or gray-level subimages of each individual character. The feature extraction methods are discussed in terms of invariance properties, reconstructability and expected distortions and variability of the characters. The problem of choosing the appropriate feature extraction method for a given application is also discussed. When a few promising feature extraction methods have been identified, they need to be evaluated experimentally to find the best method for the given application.

Anti-VEGF treatment reduces blood supply and increases tumor cell invasion in glioblastoma

Bevacizumab, an antibody against vascular endothelial growth factor (VEGF), is a promising, yet controversial, drug in human glioblastoma treatment (GBM). Its effects on tumor burden, recurrence, and vascular physiology are unclear. We therefore determined the tumor response to bevacizumab at the phenotypic, physiological, and molecular level in a clinically relevant intracranial GBM xenograft model derived from patient tumor spheroids. Using anatomical and physiological magnetic resonance imaging (MRI), we show that bevacizumab causes a strong decrease in contrast enhancement while having only a marginal effect on tumor growth. Interestingly, dynamic contrast-enhanced MRI revealed a significant reduction of the vascular supply, as evidenced by a decrease in intratumoral blood flow and volume and, at the morphological level, by a strong reduction of large- and medium-sized blood vessels. Electron microscopy revealed fewer mitochondria in the treated tumor cells. Importantly, this was accompanied by a 68% increase in infiltrating tumor cells in the brain parenchyma. At the molecular level we observed an increase in lactate and alanine metabolites, together with an induction of hypoxia-inducible factor 1α and an activation of the phosphatidyl-inositol-3-kinase pathway. These data strongly suggest that vascular remodeling induced by anti-VEGF treatment leads to a more hypoxic tumor microenvironment. This favors a metabolic change in the tumor cells toward glycolysis, which leads to enhanced tumor cell invasion into the normal brain. The present work underlines the need to combine anti-angiogenic treatment in GBMs with drugs targeting specific signaling or metabolic pathways linked to the glycolytic phenotype.

A Markov random field model for classification of multisource satellite imagery

A general model for multisource classification of remotely sensed data based on Markov random fields (MRF) is proposed. A specific model for fusion of optical images, synthetic aperture radar (SAR) images, and GIS (geographic information systems) ground cover data is presented in detail and tested. The MRF model exploits spatial class dependencies (spatial context) between neighboring pixels in an image, and temporal class dependencies between different images of the same scene. By including the temporal aspect of the data, the proposed model is suitable for detection of class changes between the acquisition dates of different images. The performance of the proposed model is investigated by fusing Landsat TM images, multitemporal ERS-1 SAR images, and GIS ground-cover maps for land-use classification, and on agricultural crop classification based on Landsat TM images, multipolarization SAR images, and GIS crop field border maps. The performance of the MRF model is compared to a simpler reference fusion model. On an average, the MRF model results in slightly higher (2%) classification accuracy when the same data is used as input to the two models. When GIS field border data is included in the MRF model, the classification accuracy of the MRF model improves by 8%. For change detection in agricultural areas, 75% of the actual class changes are detected by the MRF model, compared to 62% for the reference model. Based on the well-founded theoretical basis of Markov random field models for classification tasks and the encouraging experimental results in our small-scale study, the authors conclude that the proposed MRF model is useful for classification of multisource satellite imagery.

Evaluation of binarization methods for document images

This paper presents an evaluation of eleven locally adaptive binarization methods for gray scale images with low contrast, variable background intensity and noise. Niblacks method (1986) with the addition of the postprocessing step of Yanowitz and Brucksteins method (1989) added performed the best and was also one of the fastest binarization methods. >

Multisource classification of remotely sensed data: fusion of Landsat TM and SAR images

Proposes a new method for statistical classification of multisource data. The method is suited for land-use classification based on the fusion of remotely sensed images of the same scene captured at different dates from multiple sources. It incorporates a priori information about the likelihood of changes between the acquisition of the different images to be fused. A framework for the fusion of remotely sensed data based on a Bayesian formulation is presented. First, a simple fusion model is given, and then the basic model is extended to take into account the temporal attribute if the different data sources are acquired at different dates. The performance of the model is evaluated by fusing Landsat TM images and ERS-1-SAR images for land-use classification. The fusion model gives significant improvements in the classification error rates compared to the conventional single-source classifiers. >

Restoration of medical ultrasound images using two-dimensional homomorphic deconvolution

Describes how two-dimensional (2D) homomorphic deconvolution can be used to improve the lateral and radial resolution of medical ultrasound images recorded by a sector scanner. The recorded radio frequency ultrasound image in polar coordinates is considered as a 2D sequence of angle and depth convolved with a 2D space invariant point-spread function (PSF). Each polar coordinate sequence is transformed into the 2D complex cepstrum domain using the fast Fourier transform for Cartesian coordinates. The low-angle and low-depth portion of this sequence is taken as an estimate of the complex cepstrum representation of the PSF. It is transformed back to the Fourier frequency domain and is used to compute the deconvolved angle and depth sequence by 2D Wiener filtering. Two-dimensional homomorphic deconvolution produced substantial improvement in the resolution of B-mode images of a tissue-mimicking phantom in vitro and of several human tissues in vivo. It was better than lateral or radial homomorphic deconvolution alone, and better than 2D Wiener filtering with a PSF recorded in vitro.<<ETX>>

Multispectral analysis of the brain using magnetic resonance imaging

The authors demonstrate an improved differentiation of the most common tissue types in the human brain and surrounding structures by quantitative validation using multispectral analysis of magnetic resonance images. This is made possible by a combination of a special training technique and an increase in the number of magnetic resonance channel images with different pulse acquisition parameters. The authors give a description of the tissue-specific multivariate statistical distributions of the pixel intensity values and discuss how their properties may be explored to improve the statistical modeling further. A statistical method to estimate the tissue-specific longitudinal and transverse relaxation times is also given. It is concluded that multispectral analysis of magnetic resonance images is a valuable tool to recognize the most common normal tissue types in the brain and surrounding structures.

Multichannel blind deconvolution of seismic signals

A new algorithm for simultaneous wavelet estimation and deconvolution of seismic reflection signals is given. To remove the inherent ambiguity in this blind deconvolution problem, we introduce relevant a priori information. Our major assumption is sparseness of the reflectivity, which corresponds to a layered-earth model. This allows nonminimum-phase wavelets to be recovered reliably and closely spaced reflectors to be resolved. To combine a priori knowledge and data, we use a Bayesian framework and derive a maximum a posteriori estimate. Computing this estimate is a difficult optimization problem solved by a suboptimal iterative procedure. The procedure alternates steps of wavelet estimation and reflectivity estimation. The first step only requires a simple least-squares fit, while the second step is solved by the iterated window maximization algorithm proposed by Kaaresen. This enables better efficiency and optimality than established alternatives. The resulting optimization method can easily handle multichannel models with only a moderate increase of the computational load. Lateral continuity of the reflectors is achieved by modeling local dependencies between neighboring traces. Major improvements in both wavelet and reflectivity estimates are obtained by taking the wavelet to be invariant across several traces. The practicality of the algorithm is demonstrated on synthetic and real seismic data. An application to multivariate well-log segmentation is also given.

Pancreatic Lipomatosis Is a Structural Marker in Nondiabetic Children With Mutations in Carboxyl-Ester Lipase

Both pancreatic volume reduction and lipomatosis have been observed in subjects with diabetes. The underlying molecular and pathological mechanisms are, however, poorly known, and it has been speculated that both features are secondary to diabetes. We have recently described pancreatic atrophy and lipomatosis in diabetic subjects of two Norwegian families with a novel syndrome of diabetes and exocrine pancreatic dysfunction caused by heterozygous carboxyl-ester lipase (CEL) mutations. To explore the early pathological events in this syndrome, we performed radiological examinations of the pancreas in nondiabetic mutation carriers with signs of exocrine dysfunction. In a case series study at a tertiary hospital, we evaluated 11 nondiabetic and mutation-positive children with fecal elastase deficiency and 11 age- and sex-matched control subjects using ultrasound and magnetic resonance imaging (MRI) to estimate pancreatic fat content. The pancreata of nondiabetic mutation carriers exhibited increased reflectivity on ultrasound and had MRI findings indicative of lipomatosis. Apparently, carriers of heterozygous CEL mutations accumulate fat in their pancreas before the anticipated development of diabetes. Our findings suggest that lipomatosis of the pancreas reflects early events involved in the pathogenesis of diabetes and exocrine pancreatic dysfunction syndrome.

Two-dimensional noise-robust blind deconvolution of ultrasound images

This paper presents a new method for 2-D blind homomorphic deconvolution of medical B-scan ultrasound images. The method is based on noise-robust 2-D phase unwrapping and a noise-robust procedure to estimate the pulse in the complex cepstrum domain. Ordinary Wiener filtering is used in the subsequent deconvolution. The resulting images became much sharper with better defined tissue structures compared with the ordinary images. The deconvolved images had a resolution gain of the order of 3 to 7, and the signal-to-noise ratio (SNR) doubled for many of the images used in our experiments. The method gave stable results with respect to noise and gray levels through several image sequences.