Implementation of a survey form marking system using image processing techniques on an Imputer

This paper describes the feasibility of the application of an Imputer in a multiple choice answer sheet marking system based on image processing techniques.

Invasive and non-invasive modalities of imaging carotid stenosis

Despite recent therapeutic advances, acute ischemic complications of atherosclerosis remain the primary cause of morbidity and mortality in Western countries, with carotid atherosclerotic disease one of the major preventable causes of stroke. As the impact of this disease challenges our healthcare systems, we are becoming aware that factors influencing this disease are more complex than previously realized. In current clinical practice, risk stratification relies primarily on evaluation of the degree of luminal stenosis and patient symptomatology. Adequate investigation and optimal imaging are important factors that affect the quality of a carotid endarterectomy (CEA) service and are fundamental to patient selection. Digital subtraction angiography is still perceived as the most accurate imaging modality for carotid stenosis and historically has been the cornerstone of most of the major CEA trials but concerns regarding potential neurological complications have generated substantial interest in non-invasive modalities, such as contrast-enhanced magnetic resonance angiography. The purpose of this review is to give an overview to the vascular specialist of the current imaging modalities in clinical practice to identify patients with carotid stenosis. Advantages and disadvantages of each technique are outlined. Finally, limitations of assessing luminal stenosis in general are discussed. This article will not cover imaging of carotid atheroma morphology, function and other emerging imaging modalities of assessing plaque risk, which look beyond simple luminal measurements.

Comparison of standard image segmentation methods for segmentation of brain tumors from 2D MR images

In the analysis of medical images for computer-aided diagnosis and therapy, segmentation is often required as a preliminary step. Medical image segmentation is a complex and challenging task due to the complex nature of the images. The brain has a particularly complicated structure and its precise segmentation is very important for detecting tumors, edema, and necrotic tissues in order to prescribe appropriate therapy. Magnetic Resonance Imaging is an important diagnostic imaging technique utilized for early detection of abnormal changes in tissues and organs. It possesses good contrast resolution for different tissues and is, thus, preferred over Computerized Tomography for brain study. Therefore, the majority of research in medical image segmentation concerns MR images. As the core juncture of this research a set of MR images have been segmented using standard image segmentation techniques to isolate a brain tumor from the other regions of the brain. Subsequently the resultant images from the different segmentation techniques were compared with each other and analyzed by professional radiologists to find the segmentation technique which is the most accurate. Experimental results show that the Otsu’s thresholding method is the most suitable image segmentation method to segment a brain tumor from a Magnetic Resonance Image.

Prospective imaging study of asymptomatic patellar tendinopathy in elite junior basketball players

To evaluate the ability of ultrasonography to predict eventual symptoms in an at-risk population, 52 elite junior basketball players' patellar tendons were studied at baseline and again 16 months later. The group consisted of 10 study tendons (ultrasonographically hypoechoic at baseline) and 42 control tendons (ultrasonographically normal at baseline). By design, all tendons were asymptomatic at baseline. No differences were noted between subjects and controls at baseline for age, height, weight, training hours, and vertical jump. Functional (P < 0.01) and symptomatic outcome (P < 0.05) were poorer for subjects' tendons than for controls. Relative risk for developing symptoms of jumper's knee was 4.2 times greater in case tendons than in control tendons. Men were more likely to develop ultrasonographic changes than women (P < 0.025), and they also had significantly increased training hours per week (P < 0.01) in the study period. Half (50%) of abnormal tendons in women became ultrasonographically normal in the study period. Our data suggest that presence of an ultrasonographic hypoechoic area is associated with a greater risk of developing jumper's knee symptoms. Ultrasonographic patellar tendon changes may resolve, but this is not necessary for an athlete to become asymptomatic. Qualitative or quantitative analysis of baseline ultrasonographic images revealed it was not possible to predict which tendons would develop symptoms or resolve ultrasonographically.

Spectral coding methods for speech compression and speaker identification

This thesis investigates aspects of encoding the speech spectrum at low bit rates, with extensions to the effect of such coding on automatic speaker identification. Vector quantization (VQ) is a technique for jointly quantizing a block of samples at once, in order to reduce the bit rate of a coding system. The major drawback in using VQ is the complexity of the encoder. Recent research has indicated the potential applicability of the VQ method to speech when product code vector quantization (PCVQ) techniques are utilized. The focus of this research is the efficient representation, calculation and utilization of the speech model as stored in the PCVQ codebook. In this thesis, several VQ approaches are evaluated, and the efficacy of two training algorithms is compared experimentally. It is then shown that these productcode vector quantization algorithms may be augmented with lossless compression algorithms, thus yielding an improved overall compression rate. An approach using a statistical model for the vector codebook indices for subsequent lossless compression is introduced. This coupling of lossy compression and lossless compression enables further compression gain. It is demonstrated that this approach is able to reduce the bit rate requirement from the current 24 bits per 20 millisecond frame to below 20, using a standard spectral distortion metric for comparison. Several fast-search VQ methods for use in speech spectrum coding have been evaluated. The usefulness of fast-search algorithms is highly dependent upon the source characteristics and, although previous research has been undertaken for coding of images using VQ codebooks trained with the source samples directly, the product-code structured codebooks for speech spectrum quantization place new constraints on the search methodology. The second major focus of the research is an investigation of the effect of lowrate spectral compression methods on the task of automatic speaker identification. The motivation for this aspect of the research arose from a need to simultaneously preserve the speech quality and intelligibility and to provide for machine-based automatic speaker recognition using the compressed speech. This is important because there are several emerging applications of speaker identification where compressed speech is involved. Examples include mobile communications where the speech has been highly compressed, or where a database of speech material has been assembled and stored in compressed form. Although these two application areas have the same objective - that of maximizing the identification rate - the starting points are quite different. On the one hand, the speech material used for training the identification algorithm may or may not be available in compressed form. On the other hand, the new test material on which identification is to be based may only be available in compressed form. Using the spectral parameters which have been stored in compressed form, two main classes of speaker identification algorithm are examined. Some studies have been conducted in the past on bandwidth-limited speaker identification, but the use of short-term spectral compression deserves separate investigation. Combining the major aspects of the research, some important design guidelines for the construction of an identification model when based on the use of compressed speech are put forward.

Coding speech signals at very low rates (below 1 kb/s) with high intelligibility

This thesis presents an original approach to parametric speech coding at rates below 1 kbitsjsec, primarily for speech storage applications. Essential processes considered in this research encompass efficient characterization of evolutionary configuration of vocal tract to follow phonemic features with high fidelity, representation of speech excitation using minimal parameters with minor degradation in naturalness of synthesized speech, and finally, quantization of resulting parameters at the nominated rates. For encoding speech spectral features, a new method relying on Temporal Decomposition (TD) is developed which efficiently compresses spectral information through interpolation between most steady points over time trajectories of spectral parameters using a new basis function. The compression ratio provided by the method is independent of the updating rate of the feature vectors, hence allows high resolution in tracking significant temporal variations of speech formants with no effect on the spectral data rate. Accordingly, regardless of the quantization technique employed, the method yields a high compression ratio without sacrificing speech intelligibility. Several new techniques for improving performance of the interpolation of spectral parameters through phonetically-based analysis are proposed and implemented in this research, comprising event approximated TD, near-optimal shaping event approximating functions, efficient speech parametrization for TD on the basis of an extensive investigation originally reported in this thesis, and a hierarchical error minimization algorithm for decomposition of feature parameters which significantly reduces the complexity of the interpolation process. Speech excitation in this work is characterized based on a novel Multi-Band Excitation paradigm which accurately determines the harmonic structure in the LPC (linear predictive coding) residual spectra, within individual bands, using the concept 11 of Instantaneous Frequency (IF) estimation in frequency domain. The model yields aneffective two-band approximation to excitation and computes pitch and voicing with high accuracy as well. New methods for interpolative coding of pitch and gain contours are also developed in this thesis. For pitch, relying on the correlation between phonetic evolution and pitch variations during voiced speech segments, TD is employed to interpolate the pitch contour between critical points introduced by event centroids. This compresses pitch contour in the ratio of about 1/10 with negligible error. To approximate gain contour, a set of uniformly-distributed Gaussian event-like functions is used which reduces the amount of gain information to about 1/6 with acceptable accuracy. The thesis also addresses a new quantization method applied to spectral features on the basis of statistical properties and spectral sensitivity of spectral parameters extracted from TD-based analysis. The experimental results show that good quality speech, comparable to that of conventional coders at rates over 2 kbits/sec, can be achieved at rates 650-990 bits/sec.