Abstract: This paper is concerned with an improved algorithm
based on the piecewise-smooth Mumford and Shah (MS) functional
for an efficient and reliable segmentation. In order to speed up
convergence, an additional force, at each time step, is introduced
further to drive the evolution of the curves instead of only driven by
the extensions of the complementary functions u + and u - . In our
scheme, furthermore, the piecewise-constant MS functional is
integrated to generate the extra force based on a temporary image that
is dynamically created by computing the union of u + and u - during
segmenting. Therefore, some drawbacks of the original algorithm,
such as smaller objects generated by noise and local minimal problem
also are eliminated or improved. The resulting algorithm has been
implemented in Matlab and Visual Cµ, and demonstrated efficiently
by several cases.
Abstract: Needs of an efficient information retrieval in recent
years in increased more then ever because of the frequent use of
digital information in our life. We see a lot of work in the area of
textual information but in multimedia information, we cannot find
much progress. In text based information, new technology of data
mining and data marts are now in working that were started from the
basic concept of database some where in 1960.
In image search and especially in image identification,
computerized system at very initial stages. Even in the area of image
search we cannot see much progress as in the case of text based
search techniques. One main reason for this is the wide spread roots
of image search where many area like artificial intelligence,
statistics, image processing, pattern recognition play their role. Even
human psychology and perception and cultural diversity also have
their share for the design of a good and efficient image recognition
and retrieval system.
A new object based search technique is presented in this paper
where object in the image are identified on the basis of their
geometrical shapes and other features like color and texture where
object-co-relation augments this search process.
To be more focused on objects identification, simple images are
selected for the work to reduce the role of segmentation in overall
process however same technique can also be applied for other
images.
Abstract: In this paper, we present a method for edge
segmentation of satellite images based on 2-D Phase Congruency
(PC) model. The proposed approach is composed by two steps: The
contextual non linear smoothing algorithm (CNLS) is used to smooth
the input images. Then, the 2D stretched Gabor filter (S-G filter)
based on proposed angular variation is developed in order to avoid
the multiple responses in the previous work. An assessment of our
proposed method performance is provided in terms of accuracy of
satellite image edge segmentation. The proposed method is compared
with others known approaches.
Abstract: As the world changes more rapidly, the demand for update information for resource management, environment monitoring, planning are increasing exponentially. Integration of Remote Sensing with GIS technology will significantly promote the ability for addressing these concerns. This paper presents an alternative way of update GIS applications using image processing and high resolution images. We show a method of high-resolution image segmentation using graphs and morphological operations, where a preprocessing step (watershed operation) is required. A morphological process is then applied using the opening and closing operations. After this segmentation we can extract significant cartographic elements such as urban areas, streets or green areas. The result of this segmentation and this extraction is then used to update GIS applications. Some examples are shown using aerial photography.
Abstract: This paper proposes a method for speckle reduction in
medical ultrasound imaging while preserving the edges with the
added advantages of adaptive noise filtering and speed. A nonlinear
image diffusion method that incorporates local image parameter,
namely, scatterer density in addition to gradient, to weight the
nonlinear diffusion process, is proposed. The method was tested for
the isotropic case with a contrast detail phantom and varieties of
clinical ultrasound images, and then compared to linear and some
other diffusion enhancement methods. Different diffusion parameters
were tested and tuned to best reduce speckle noise and preserve
edges. The method showed superior performance measured both
quantitatively and qualitatively when incorporating scatterer density
into the diffusivity function. The proposed filter can be used as a
preprocessing step for ultrasound image enhancement before
applying automatic segmentation, automatic volumetric calculations,
or 3D ultrasound volume rendering.
Abstract: Information Retrieval has the objective of studying
models and the realization of systems allowing a user to find the
relevant documents adapted to his need of information. The
information search is a problem which remains difficult because the
difficulty in the representing and to treat the natural languages such
as polysemia. Intentional Structures promise to be a new paradigm to
extend the existing documents structures and to enhance the different
phases of documents process such as creation, editing, search and
retrieval. The intention recognition of the author-s of texts can reduce
the largeness of this problem. In this article, we present intentions
recognition system is based on a semi-automatic method of
extraction the intentional information starting from a corpus of text.
This system is also able to update the ontology of intentions for the
enrichment of the knowledge base containing all possible intentions
of a domain. This approach uses the construction of a semi-formal
ontology which considered as the conceptualization of the intentional
information contained in a text. An experiments on scientific
publications in the field of computer science was considered to
validate this approach.
Abstract: In this paper we present a new method for over-height
vehicle detection in low headroom streets and highways using digital
video possessing. The accuracy and the lower price comparing to
present detectors like laser radars and the capability of providing
extra information like speed and height measurement make this
method more reliable and efficient. In this algorithm the features are
selected and tracked using KLT algorithm. A blob extraction
algorithm is also applied using background estimation and
subtraction. Then the world coordinates of features that are inside the
blobs are estimated using a noble calibration method. As, the heights
of the features are calculated, we apply a threshold to select overheight
features and eliminate others. The over-height features are
segmented using some association criteria and grouped using an
undirected graph. Then they are tracked through sequential frames.
The obtained groups refer to over-height vehicles in a scene.
Abstract: If organizations like Mellat Bank want to identify its
customer market completely to reach its specified goals, it can
segment the market to offer the product package to the right segment.
Our objective is to offer a segmentation model for Iran banking
market in Mellat bank view. The methodology of this project is
combined by “segmentation on the basis of four part-quality
variables" and “segmentation on the basis of different in means".
Required data are gathered from E-Systems and researcher personal
observation. Finally, the research offers the organization that at first
step form a four dimensional matrix with 756 segments using four
variables named value-based, behavioral, activity style, and activity
level, and at the second step calculate the means of profit for every
cell of matrix in two distinguished work level (levels α1:normal
condition and α2: high pressure condition) and compare the segments
by checking two conditions that are 1- homogeneity every segment
with its sub segment and 2- heterogeneity with other segments, and
so it can do the necessary segmentation process. After all, the last
offer (more explained by an operational example and feedback
algorithm) is to test and update the model because of dynamic
environment, technology, and banking system.
Abstract: Unified Speech Audio Coding (USAC), the latest MPEG standardization for unified speech and audio coding, uses a speech/audio classification algorithm to distinguish speech and audio segments of the input signal. The quality of the recovered audio can be increased by well-designed orchestra/percussion classification and subsequent processing. However, owing to the shortcoming of the system, introducing an orchestra/percussion classification and modifying subsequent processing can enormously increase the quality of the recovered audio. This paper proposes an orchestra/percussion classification algorithm for the USAC system which only extracts 3 scales of Mel-Frequency Cepstral Coefficients (MFCCs) rather than traditional 13 scales of MFCCs and use Iterative Dichotomiser 3 (ID3) Decision Tree rather than other complex learning method, thus the proposed algorithm has lower computing complexity than most existing algorithms. Considering that frequent changing of attributes may lead to quality loss of the recovered audio signal, this paper also design a modified subsequent process to help the whole classification system reach an accurate rate as high as 97% which is comparable to classical 99%.
Abstract: We developed a non-contact method for the in-situ
monitoring of the thermal forming of glass and Si foils to optimize
the manufacture of mirrors for high-resolution space x-ray
telescopes. Their construction requires precise and light-weight
segmented optics with angular resolution better than 5 arcsec. We
used 75x25 mm Desag D263 glass foils 0.75 mm thick and 0.6 mm
thick Si foils. The glass foils were shaped by free slumping on a
frame at viscosities in the range of 109.3-1012 dPa·s, the Si foils by
forced slumping above 1000°C. Using a Nikon D80 digital camera,
we took snapshots of a foil-s shape every 5 min during its isothermal
heat treatment. The obtained results we can use for computer
simulations. By comparing the measured and simulated data, we can
more precisely define material properties of the foils and optimize
the forming technology.
Abstract: This work presents a fusion of Log Gabor Wavelet
(LGW) and Maximum a Posteriori (MAP) estimator as a speech
enhancement tool for acoustical background noise reduction. The
probability density function (pdf) of the speech spectral amplitude is
approximated by a Generalized Laplacian Distribution (GLD).
Compared to earlier estimators the proposed method estimates the
underlying statistical model more accurately by appropriately
choosing the model parameters of GLD. Experimental results show
that the proposed estimator yields a higher improvement in
Segmental Signal-to-Noise Ratio (S-SNR) and lower Log-Spectral
Distortion (LSD) in two different noisy environments compared to
other estimators.
Abstract: Images of human iris contain specular highlights due
to the reflective properties of the cornea. This corneal reflection
causes many errors not only in iris and pupil center estimation but
also to locate iris and pupil boundaries especially for methods that
use active contour. Each iris recognition system has four steps:
Segmentation, Normalization, Encoding and Matching. In order to
address the corneal reflection, a novel reflection removal method is
proposed in this paper. Comparative experiments of two existing
methods for reflection removal method are evaluated on CASIA iris
image databases V3. The experimental results reveal that the
proposed algorithm provides higher performance in reflection
removal.
Abstract: There are two common methodologies to verify
signatures: the functional approach and the parametric approach. This
paper presents a new approach for dynamic handwritten signature
verification (HSV) using the Neural Network with verification by the
Conjugate Gradient Neural Network (NN). It is yet another avenue in
the approach to HSV that is found to produce excellent results when
compared with other methods of dynamic. Experimental results show
the system is insensitive to the order of base-classifiers and gets a
high verification ratio.
Abstract: This paper presents an effective traffic lights
recognition method at the daytime. First, Potential Traffic Lights
Detector (PTLD) use whole color source of YCbCr channel image and
make each binary image of green and red traffic lights. After PTLD
step, Shape Filter (SF) use to remove noise such as traffic sign, street
tree, vehicle, and building. At this time, noise removal properties
consist of information of blobs of binary image; length, area, area of
boundary box, etc. Finally, after an intermediate association step witch
goal is to define relevant candidates region from the previously
detected traffic lights, Adaptive Multi-class Classifier (AMC) is
executed. The classification method uses Haar-like feature and
Adaboost algorithm. For simulation, we are implemented through Intel
Core CPU with 2.80 GHz and 4 GB RAM and tested in the urban and
rural roads. Through the test, we are compared with our method and
standard object-recognition learning processes and proved that it
reached up to 94 % of detection rate which is better than the results
achieved with cascade classifiers. Computation time of our proposed
method is 15 ms.
Abstract: In Multiple Sclerosis, pathological changes in the
brain results in deviations in signal intensity on Magnetic Resonance
Images (MRI). Quantitative analysis of these changes and their
correlation with clinical finding provides important information for
diagnosis. This constitutes the objective of our work. A new approach
is developed. After the enhancement of images contrast and the brain
extraction by mathematical morphology algorithm, we proceed to the
brain segmentation. Our approach is based on building statistical
model from data itself, for normal brain MRI and including clustering
tissue type. Then we detect signal abnormalities (MS lesions) as a
rejection class containing voxels that are not explained by the built
model. We validate the method on MR images of Multiple Sclerosis
patients by comparing its results with those of human expert
segmentation.
Abstract: Interpretation of aerial images is an important task in
various applications. Image segmentation can be viewed as the essential
step for extracting information from aerial images. Among many
developed segmentation methods, the technique of clustering has been
extensively investigated and used. However, determining the number
of clusters in an image is inherently a difficult problem, especially
when a priori information on the aerial image is unavailable. This
study proposes a support vector machine approach for clustering
aerial images. Three cluster validity indices, distance-based index,
Davies-Bouldin index, and Xie-Beni index, are utilized as quantitative
measures of the quality of clustering results. Comparisons on the
effectiveness of these indices and various parameters settings on the
proposed methods are conducted. Experimental results are provided
to illustrate the feasibility of the proposed approach.
Abstract: In this paper, we present a comparative study between two computer vision systems for objects recognition and tracking, these algorithms describe two different approach based on regions constituted by a set of pixels which parameterized objects in shot sequences. For the image segmentation and objects detection, the FCM technique is used, the overlapping between cluster's distribution is minimized by the use of suitable color space (other that the RGB one). The first technique takes into account a priori probabilities governing the computation of various clusters to track objects. A Parzen kernel method is described and allows identifying the players in each frame, we also show the importance of standard deviation value research of the Gaussian probability density function. Region matching is carried out by an algorithm that operates on the Mahalanobis distance between region descriptors in two subsequent frames and uses singular value decomposition to compute a set of correspondences satisfying both the principle of proximity and the principle of exclusion.
Abstract: Design and modeling of nonlinear systems require the
knowledge of all inside acting parameters and effects. An empirical
alternative is to identify the system-s transfer function from input and
output data as a black box model. This paper presents a procedure
using least squares algorithm for the identification of a feed drive
system coefficients in time domain using a reduced model based on
windowed input and output data. The command and response of the
axis are first measured in the first 4 ms, and then least squares are
applied to predict the transfer function coefficients for this
displacement segment. From the identified coefficients, the next
command response segments are estimated. The obtained results
reveal a considerable potential of least squares method to identify the
system-s time-based coefficients and predict accurately the command
response as compared to measurements.
Abstract: In this paper we study the use of a new code called
Random Diagonal (RD) code for Spectral Amplitude Coding (SAC)
optical Code Division Multiple Access (CDMA) networks, using
Fiber Bragg-Grating (FBG), FBG consists of a fiber segment whose
index of reflection varies periodically along its length. RD code is
constructed using code level and data level, one of the important
properties of this code is that the cross correlation at data level is
always zero, which means that Phase intensity Induced Phase (PIIN)
is reduced. We find that the performance of the RD code will be
better than Modified Frequency Hopping (MFH) and Hadamard code
It has been observed through experimental and theoretical simulation
that BER for RD code perform significantly better than other codes.
Proof –of-principle simulations of encoding with 3 channels, and 10
Gbps data transmission have been successfully demonstrated together
with FBG decoding scheme for canceling the code level from SAC-signal.
Abstract: Freeways are originally designed to provide high
mobility to road users. However, the increase in population and
vehicle numbers has led to increasing congestions around the world.
Daily recurrent congestion substantially reduces the freeway capacity
when it is most needed. Building new highways and expanding the
existing ones is an expensive solution and impractical in many
situations. Intelligent and vision-based techniques can, however, be
efficient tools in monitoring highways and increasing the capacity of
the existing infrastructures. The crucial step for highway monitoring
is vehicle detection. In this paper, we propose one of such
techniques. The approach is based on artificial neural networks
(ANN) for vehicles detection and counting. The detection process
uses the freeway video images and starts by automatically extracting
the image background from the successive video frames. Once the
background is identified, subsequent frames are used to detect
moving objects through image subtraction. The result is segmented
using Sobel operator for edge detection. The ANN is, then, used in
the detection and counting phase. Applying this technique to the
busiest freeway in Riyadh (King Fahd Road) achieved higher than
98% detection accuracy despite the light intensity changes, the
occlusion situations, and shadows.