Abstract: Segmentation of left ventricle (LV) from cardiac
ultrasound images provides a quantitative functional analysis of the
heart to diagnose disease. Active Shape Model (ASM) is widely used
for LV segmentation, but it suffers from the drawback that
initialization of the shape model is not sufficiently close to the target,
especially when dealing with abnormal shapes in disease. In this work,
a two-step framework is improved to achieve a fast and efficient LV
segmentation. First, a robust and efficient detection based on Hough
forest localizes cardiac feature points. Such feature points are used to
predict the initial fitting of the LV shape model. Second, ASM is
applied to further fit the LV shape model to the cardiac ultrasound
image. With the robust initialization, ASM is able to achieve more
accurate segmentation. The performance of the proposed method is
evaluated on a dataset of 810 cardiac ultrasound images that are mostly
abnormal shapes. This proposed method is compared with several
combinations of ASM and existing initialization methods. Our
experiment results demonstrate that accuracy of the proposed method
for feature point detection for initialization was 40% higher than the
existing methods. Moreover, the proposed method significantly
reduces the number of necessary ASM fitting loops and thus speeds up
the whole segmentation process. Therefore, the proposed method is
able to achieve more accurate and efficient segmentation results and is
applicable to unusual shapes of heart with cardiac diseases, such as left
atrial enlargement.
Abstract: Bezier curves have useful properties for path
generation problem, for instance, it can generate the reference
trajectory for vehicles to satisfy the path constraints. Both algorithms
join cubic Bezier curve segment smoothly to generate the path. Some
of the useful properties of Bezier are curvature. In mathematics,
curvature is the amount by which a geometric object deviates from
being flat, or straight in the case of a line. Another extrinsic example
of curvature is a circle, where the curvature is equal to the reciprocal
of its radius at any point on the circle. The smaller the radius, the
higher the curvature thus the vehicle needs to bend sharply. In this
study, we use Bezier curve to fit highway-like curve. We use
different approach to find the best approximation for the curve so that
it will resembles highway-like curve. We compute curvature value by
analytical differentiation of the Bezier Curve. We will then compute
the maximum speed for driving using the curvature information
obtained. Our research works on some assumptions; first, the Bezier
curve estimates the real shape of the curve which can be verified
visually. Even though, fitting process of Bezier curve does not
interpolate exactly on the curve of interest, we believe that the
estimation of speed are acceptable. We verified our result with the
manual calculation of the curvature from the map.
Abstract: The aim of this paper is to propose a general
framework for storing, analyzing, and extracting knowledge from
two-dimensional echocardiographic images, color Doppler images,
non-medical images, and general data sets. A number of high
performance data mining algorithms have been used to carry out this
task. Our framework encompasses four layers namely physical
storage, object identification, knowledge discovery, user level.
Techniques such as active contour model to identify the cardiac
chambers, pixel classification to segment the color Doppler echo
image, universal model for image retrieval, Bayesian method for
classification, parallel algorithms for image segmentation, etc., were
employed. Using the feature vector database that have been
efficiently constructed, one can perform various data mining tasks
like clustering, classification, etc. with efficient algorithms along
with image mining given a query image. All these facilities are
included in the framework that is supported by state-of-the-art user
interface (UI). The algorithms were tested with actual patient data
and Coral image database and the results show that their performance
is better than the results reported already.
Abstract: This paper introduces an effective method of
segmenting Korean text (place names in Korean) from a Korean road
sign image. A Korean advanced directional road sign is composed of
several types of visual information such as arrows, place names in
Korean and English, and route numbers. Automatic classification of
the visual information and extraction of Korean place names from the
road sign images make it possible to avoid a lot of manual inputs to a
database system for management of road signs nationwide. We
propose a series of problem-specific heuristics that correctly segments
Korean place names, which is the most crucial information, from the
other information by leaving out non-text information effectively. The
experimental results with a dataset of 368 road sign images show 96%
of the detection rate per Korean place name and 84% per road sign
image.
Abstract: The aim of this work is to detect geometrical shape
objects in an image. In this paper, the object is considered to be as a
circle shape. The identification requires find three characteristics,
which are number, size, and location of the object. To achieve the
goal of this work, this paper presents an algorithm that combines
from some of statistical approaches and image analysis techniques.
This algorithm has been implemented to arrive at the major
objectives in this paper. The algorithm has been evaluated by using
simulated data, and yields good results, and then it has been applied
to real data.
Abstract: Liver segmentation from medical images poses more
challenges than analogous segmentations of other organs. This
contribution introduces a liver segmentation method from a series of
computer tomography images. Overall, we present a novel method for
segmenting liver by coupling density matching with shape priors.
Density matching signifies a tracking method which operates via
maximizing the Bhattacharyya similarity measure between the
photometric distribution from an estimated image region and a model
photometric distribution. Density matching controls the direction of
the evolution process and slows down the evolving contour in regions
with weak edges. The shape prior improves the robustness of density
matching and discourages the evolving contour from exceeding liver’s
boundaries at regions with weak boundaries. The model is
implemented using a modified distance regularized level set (DRLS)
model. The experimental results show that the method achieves a
satisfactory result. By comparing with the original DRLS model, it is
evident that the proposed model herein is more effective in addressing
the over segmentation problem. Finally, we gauge our performance of
our model against matrices comprising of accuracy, sensitivity, and
specificity.
Abstract: Given the increase in the number of e-commerce sites,
the number of competitors has become very important. This means
that companies have to take appropriate decisions in order to meet the
expectations of their customers and satisfy their needs. In this paper,
we present a case study of applying LRFM (length, recency,
frequency and monetary) model and clustering techniques in the
sector of electronic commerce with a view to evaluating customers’
values of the Moroccan e-commerce websites and then developing
effective marketing strategies. To achieve these objectives, we adopt
LRFM model by applying a two-stage clustering method. In the first
stage, the self-organizing maps method is used to determine the best
number of clusters and the initial centroid. In the second stage, kmeans
method is applied to segment 730 customers into nine clusters
according to their L, R, F and M values. The results show that the
cluster 6 is the most important cluster because the average values of
L, R, F and M are higher than the overall average value. In addition,
this study has considered another variable that describes the mode of
payment used by customers to improve and strengthen clusters’
analysis. The clusters’ analysis demonstrates that the payment method is
one of the key indicators of a new index which allows to assess the
level of customers’ confidence in the company's Website.
Abstract: Novel wind-lens turbine designs can augment power
output. Vacuum-Assisted Resin Transfer Molding (VARTM) is used
to form large and complex structures from a Carbon Fiber Reinforced
Polymer (CFRP) composite. Typically, wind-lens turbine structures
are fabricated in segments, and then bonded to form the final structure.
This paper introduces five new adhesive joints, divided into two
groups: one is constructed between dry carbon and CFRP fabrics, and
the other is constructed with two dry carbon fibers. All joints and
CFRP fabrics were made in our laboratory using VARTM
manufacturing techniques. Specimens were prepared for tensile testing
to measure joint performance. The results showed that the second
group of joints achieved a higher tensile strength than the first group.
On the other hand, the tensile fracture behavior of the two groups
showed the same pattern of crack originating near the joint ends
followed by crack propagation until fracture.
Abstract: In this paper genetic based test data compression is
targeted for improving the compression ratio and for reducing the
computation time. The genetic algorithm is based on extended pattern
run-length coding. The test set contains a large number of X value
that can be effectively exploited to improve the test data
compression. In this coding method, a reference pattern is set and its
compatibility is checked. For this process, a genetic algorithm is
proposed to reduce the computation time of encoding algorithm. This
coding technique encodes the 2n compatible pattern or the inversely
compatible pattern into a single test data segment or multiple test data
segment. The experimental result shows that the compression ratio
and computation time is reduced.
Abstract: Obturator Foramen is a specific structure in Pelvic
bone images and recognition of it is a new concept in medical image
processing. Moreover, segmentation of bone structures such as
Obturator Foramen plays an essential role for clinical research in
orthopedics. In this paper, we present a novel method to analyze the
similarity between the substructures of the imaged region and a hand
drawn template as a preprocessing step for computation of Pelvic
bone rotation on hip radiographs. This method consists of integrated
usage of Marker-controlled Watershed segmentation and Zernike
moment feature descriptor and it is used to detect Obturator Foramen
accurately. Marker-controlled Watershed segmentation is applied to
separate Obturator Foramen from the background effectively. Then,
Zernike moment feature descriptor is used to provide matching
between binary template image and the segmented binary image for
final extraction of Obturator Foramens. Finally, Pelvic bone rotation
rate calculation for each hip radiograph is performed automatically to
select and eliminate hip radiographs for further studies which depend
on Pelvic bone angle measurements. The proposed method is tested
on randomly selected 100 hip radiographs. The experimental results
demonstrated that the proposed method is able to segment Obturator
Foramen with 96% accuracy.
Abstract: In this paper, we present an application of Riemannian
geometry for processing non-Euclidean image data. We consider the
image as residing in a Riemannian manifold, for developing a new
method to brain edge detection and brain extraction. Automating this
process is a challenge due to the high diversity in appearance brain
tissue, among different patients and sequences. The main contribution, in this paper, is the use of an edge-based
anisotropic diffusion tensor for the segmentation task by integrating
both image edge geometry and Riemannian manifold (geodesic,
metric tensor) to regularize the convergence contour and extract
complex anatomical structures. We check the accuracy of the
segmentation results on simulated brain MRI scans of single
T1-weighted, T2-weighted and Proton Density sequences. We
validate our approach using two different databases: BrainWeb
database, and MRI Multiple sclerosis Database (MRI MS DB). We
have compared, qualitatively and quantitatively, our approach with
the well-known brain extraction algorithms. We show that using
a Riemannian manifolds to medical image analysis improves the
efficient results to brain extraction, in real time, outperforming the
results of the standard techniques.
Abstract: In the context of the handwriting recognition, we
propose an off line system for the recognition of the Arabic
handwritten words of the Algerian departments. The study is based
mainly on the evaluation of neural network performances, trained
with the gradient back propagation algorithm. The used parameters to
form the input vector of the neural network are extracted on the
binary images of the handwritten word by several methods. The
Distribution parameters, the centered moments of the different
projections of the different segments, the centered moments of the
word image coding according to the directions of Freeman, and the
Barr features applied binary image of the word and on its different
segments. The classification is achieved by a multi layers perceptron.
A detailed experiment is carried and satisfactory recognition results
are reported.
Abstract: The Gezi Park protests of 2013 have significantly changed the Turkish agenda and its effects have been felt historically. The protests, which rapidly spread throughout the country, were triggered by the proposal to recreate the Ottoman Army Barracks to function as a shopping mall on Gezi Park located in Istanbul’s Taksim neighbourhood despite the oppositions of several NGOs and when trees were cut in the park for this purpose. Once the news that the construction vehicles entered the park on May 27 spread on social media, activists moved into the park to stop the demolition, against whom the police used disproportioned force. With this police intervention and the then prime-minister Tayyip Erdoğan's insistent statements about the construction plans, the protests turned into anti- government demonstrations, which then spread to the rest of the country, mainly in big cities like Ankara and Izmir. According to the Ministry of Internal Affairs’ June 23rd reports, 2.5 million people joined the demonstrations in 79 provinces, that is all of them, except for the provinces of Bayburt and Bingöl, while even more people shared their opinions via social networks. As a result of these events, 8 civilians and 2 security personnel lost their lives, namely police chief Mustafa Sarı, police officer Ahmet Küçükdağ, citizens Mehmet Ayvalıtaş, Abdullah Cömert, Ethem Sarısülük, Ali İsmail Korkmaz, Ahmet Atakan, Berkin Elvan, Burak Can Karamanoğlu, Mehmet İstif, and Elif Çermik, and 8163 more were injured. Besides being a turning point in Turkish history, the Gezi Park protests also had broad repercussions in both in Turkish and in global media, which focused on Turkey throughout the events. Our study conducts content analysis of three Turkish reporting newspapers with varying ideological standpoints, Hürriyet, Cumhuriyet ve Yeni Şafak, in order to reveal their basic approach to news casting in context of the Gezi Park protests. Headlines, news segments, and news content relating to the Gezi protests were treated and analysed for this purpose. The aim of this study is to understand the social effects of the Gezi Park protests through media samples with varying political attitudes towards news casting.
Abstract: In this paper, a spatial multiple-kernel fuzzy C-means (SMKFCM) algorithm is introduced for segmentation problem. A linear combination of multiples kernels with spatial information is used in the kernel FCM (KFCM) and the updating rules for the linear coefficients of the composite kernels are derived as well. Fuzzy cmeans (FCM) based techniques have been widely used in medical image segmentation problem due to their simplicity and fast convergence. The proposed SMKFCM algorithm provides us a new flexible vehicle to fuse different pixel information in medical image segmentation and detection of MR images. To evaluate the robustness of the proposed segmentation algorithm in noisy environment, we add noise in medical brain tumor MR images and calculated the success rate and segmentation accuracy. From the experimental results it is clear that the proposed algorithm has better performance than those of other FCM based techniques for noisy medical MR images.
Abstract: Second generation military Filipino Amerasians
comprise a formidable contemporary segment of the estimated
250,000-plus biracial Amerasians in the Philippines today. Overall,
they are a stigmatized and socioeconomically marginalized diaspora;
historically, they were abandoned or estranged by U.S. military
personnel fathers assigned during the century-long Colonial, Post-
World War II and Cold War Era of permanent military basing (1898-
1992). Indeed, U.S. military personnel are assigned in smaller
numbers in the Philippines today. This inquiry is an outgrowth of two
recent small sample studies. The first surfaced the impact of the U.S.
military prostitution system on formation of the ‘Derivative
Amerasian Family Construct’ on first generation Amerasians; a
second, qualitative case study suggested the continued effect of the
prostitution systems' destructive impetuous on second generation
Amerasians. The intent of this current qualitative, multiple-case study
was to actively seek out second generation sex industry toilers. The
purpose was to focus further on this human phenomenon in the postbasing
and post-military prostitution system eras. As background, the
former military prostitution apparatus has transformed into a modern
dynamic of rampant sex tourism and prostitution nationwide. This is
characterized by hotel and resorts offering unrestricted carnal access,
urban and provincial brothels (casas), discos, bars and pickup clubs,
massage parlors, local barrio karaoke bars and street prostitution. A
small case study sample (N = 4) of female and male second
generation Amerasians were selected. Sample formation employed a
non-probability ‘snowball’ technique drawing respondents from the
notorious Angeles, Metro Manila, Olongapo City ‘AMO Amerasian
Triangle’ where most former U.S. military installations were sited
and modern sex tourism thrives. A six-month study and analysis of
in-depth interviews of female and male sex laborers, their families
and peers revealed a litany of disturbing, and troublesome
experiences. Results showed profiles of debilitating human poverty,
history of family disorganization, stigmatization, social
marginalization and the ghost of the military prostitution system and
its harmful legacy on Amerasian family units. Emerging were testimonials of wayward young people ensnared in a maelstrom of
deep economic deprivation, familial dysfunction, psychological
desperation and societal indifference. The paper recommends that
more study is needed and implications of unstudied psychosocial and
socioeconomic experiences of distressed younger generations of
military Amerasians require specific research. Heretofore apathetic or
disengaged U.S. institutions need to confront the issue and formulate
activist and solution-oriented social welfare, human services and
immigration easement policies and alternatives. These institutions
specifically include academic and social science research agencies,
corporate foundations, the U.S. Congress, and Departments of State,
Defense and Health and Human Services, and Homeland Security
(i.e. Citizen and Immigration Services) It is them who continue to
endorse a laissez-faire policy of non-involvement over the entire
Filipino Amerasian question. Such apathy, the paper concludes,
relegates this consequential but neglected blood progeny to the status
of humiliating destitution and exploitation. Amerasians; thus, remain
entrapped in their former colonial, and neo-colonial habitat.
Ironically, they are unwitting victims of a U.S. American homeland
that fancies itself geo-politically as a strong and strategic military
treaty ally of the Philippines in the Western Pacific.
Abstract: In some applications, such as image recognition or
compression, segmentation refers to the process of partitioning a
digital image into multiple segments. Image segmentation is typically
used to locate objects and boundaries (lines, curves, etc.) in images.
Image segmentation is to classify or cluster an image into several
parts (regions) according to the feature of image, for example, the
pixel value or the frequency response. More precisely, image
segmentation is the process of assigning a label to every pixel in an
image such that pixels with the same label share certain visual
characteristics. The result of image segmentation is a set of segments
that collectively cover the entire image, or a set of contours extracted
from the image. Several image segmentation algorithms were
proposed to segment an image before recognition or compression. Up
to now, many image segmentation algorithms exist and be
extensively applied in science and daily life. According to their
segmentation method, we can approximately categorize them into
region-based segmentation, data clustering, and edge-base
segmentation. In this paper, we give a study of several popular image
segmentation algorithms that are available.
Abstract: Information technology plays an irreplaceable role in
introducing and improving business process orientation in a
company. It enables implementation of the theoretical concept,
measurement of results achieved and undertaking corrective
measures aimed at improvements. Information technology is a key
concept in the development and implementation of the business
process management systems as it establishes a connection to
business operations. Both in the literature and practice, insurance
companies are often seen as highly process oriented due to the nature
of their business and focus on customers. They are also considered
leaders in using information technology for business process
management. The research conducted aimed to investigate whether
the perceived leadership status of insurance companies is well
deserved, i.e. to establish the level of process orientation and explore
the practice of information technology use in insurance companies in
the region. The main instrument for primary data collection within
this research was an electronic survey questionnaire sent to the
management of insurance companies in the Republic of Croatia,
Bosnia and Herzegovina, Slovenia, Serbia and Macedonia. The
conducted research has shown that insurance companies have a
satisfactory level of process orientation, but that there is also a huge
potential for improvement, especially in the segment of information
technology and its connection to business processes.
Abstract: In this paper, we present a new segmentation approach
for focal liver lesions in contrast enhanced ultrasound imaging. This
approach, based on a two-cluster Fuzzy C-Means methodology,
considers type-II fuzzy sets to handle uncertainty due to the image
modality (presence of speckle noise, low contrast, etc.), and to
calculate the optimum inter-cluster threshold. Fine boundaries are
detected by a local recursive merging of ambiguous pixels. The
method has been tested on a representative database. Compared to
both Otsu and type-I Fuzzy C-Means techniques, the proposed
method significantly reduces the segmentation errors.
Abstract: This study aims to investigate the mixing behaviors of
deionized (DI) water and carboxymethyl cellulose (CMC) solutions in
C-shaped serpentine micromixers over a wide range of flow
conditions. The flow of CMC solutions exhibits shear-thinning
behaviors. Numerical simulations are performed to investigate the
effects of the mean flow speed, fluid properties and geometry
parameters on flow and mixing in the micromixers with the serpentine
channel of the same overall channel length. From the results, we can
find the following trends. When convection dominates fluid mixing,
the curvature-induced vortices enhance fluid mixing effectively. The
mixing efficiency of a micromixer consisting of semicircular C-shaped
repeating units with a smaller centerline radius is better than that of a
micromixer consisting of major segment repeating units with a larger
centerline radius. The viscosity of DI water is less than the overall
average apparent viscosity of CMC solutions, and so the effect of
curvature-induced vortices on fluid mixing in DI water is larger than
that in CMC solutions for the cases with the same mean flow speed.
Abstract: This paper presents a methodology for probabilistic
assessment of bearing capacity and prediction of failure mechanism
of masonry vaults at the ultimate state with consideration of the
natural variability of Young’s modulus of stones. First, the
computation model is explained. The failure mode corresponds to the
four-hinge mechanism. Based on this consideration, the study of a
vault composed of 16 segments is presented. The Young’s modulus of
the segments is considered as random variable defined by a mean
value and a coefficient of variation. A relationship linking the vault
bearing capacity to the voussoirs modulus variation is proposed. The
most probable failure mechanisms, in addition to that observed in the
deterministic case, are identified for each variability level as well as
their probability of occurrence. The results show that the mechanism
observed in the deterministic case has decreasing probability of
occurrence in terms of variability, while the number of other
mechanisms and their probability of occurrence increases with the
coefficient of variation of Young’s modulus. This means that if a
significant change in the Young’s modulus of the segments is proven,
taking it into account in computations becomes mandatory, both for
determining the vault bearing capacity and for predicting its failure
mechanism.